Journal of Sensor and Actuator Networks doi: 10.3390/jsan15050072

Authors: Tiago Ferreira João Durães

In the industrial edge-to-cloud continuum, data is often privacy-sensitive and spans multiple organizations that do not fully trust one another, making central aggregation of raw data undesirable and often non-compliant with regulations such as the General Data Protection Regulation (GDPR). Federated Learning (FL) addresses this by sharing model updates rather than raw data, but conventional FL assumes a central coordinator, leaving it exposed to poisoning and inference attacks and to a single point of trust and failure. Decentralized Federated Learning (DFL) couples FL with Distributed Ledger Technologies (DLTs), removing the coordinator and enabling verifiable aggregation in trustless, cross-organizational environments. In this work, we assess the applicability of DFL to on-device spoken-command recognition—a representative edge audio task underpinning voice-driven industrial interfaces—by comparing decentralized and centralized training under idealized and adversarial conditions. Using a Convolutional Neural Network (CNN) replicated across edge nodes, we evaluate resilience to inter-node data imbalance, to poisoning attacks, and to a privacy-preserving noise-injection defense against inference attacks, together with model compression for resource-constrained edge devices. The system pairs this comparison with a validation-based poisoning defense in which each node scores its peers’ updates on its own held-out data, and an update is aggregated only if a majority of nodes report a weighted F1-score above a threshold—requiring neither a shared validation set nor a trusted validator. Our results indicate that the DFL system achieves accuracy comparable to centralized baselines in most scenarios (weighted F1-score 0.762 across nine nodes, against 0.896 centralized), and that a cross-node validation mechanism reliably excludes poisoned updates as long as fewer than half of the nodes are compromised (within 3.54% of the unpoisoned model). Noise-based inference defenses reduce accuracy substantially (44.7% on average at a noise standard deviation of 1.0), exposing a sharp privacy–utility trade-off, whereas model compression preserves performance (0.765 against 0.762 for pruning and format conversion, with 8-bit quantization costing up to a further 13.3%). These findings clarify both the promise and the current limitations of decentralized, privacy-preserving learning for the industrial edge-to-cloud continuum.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15050071

Authors: Nurzhigit Smailov Kydyrali Yssyraiyl Gulbahar Yussupova Askhat Batyrgaliyev Sauletbek Koshkinbayev Ainur Kuttybayeva Zhiger Zhanatayuly Akezhan Sabibolda

Spacecraft and launch-vehicle structures require lightweight multipoint monitoring under combined mechanical, thermal, and environmental loads. This study presents an analytical fiber Bragg grating (FBG) sensor-network workflow integrating reference-grating temperature compensation, regional strain assessment, opposite-surface curvature sensing, wavelength-division-multiplexing allocation, and strain-to-shape reconstruction. The deterministic compensation case is used only as a self-consistency check, whereas practical robustness is assessed through 10,000 Monte Carlo trials incorporating packaged-coefficient mismatch, temperature nonuniformity, wavelength noise, strain-transfer variation, drift, and calibration uncertainty. The calibrated estimator achieved a median strain mean absolute error of 1.73 με and a 95th-percentile error of 4.22 με. The defined finite-element benchmarks produced a maximum engine-mount truss strain of 456.2 με under the defined loads and a median full-field panel-reconstruction normalized root-mean-square error of 1.29% for 18 sensing locations with 2 με noise. Conservative WDM analysis yielded 54, 13, and 16 channels for three operating envelopes, and the prescribed random-vibration spectrum produced 6.78 grms. These results demonstrate a reproducible numerical proof of concept and define practical limits for compensation, spectral allocation, curvature interpretation, and inverse reconstruction; they do not constitute experimental validation or flight qualification.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15050070

Authors: Rafael Muñoz-Salinas Francisco J. Romero-Ramirez Sergio Garrido-Jurado

Unmanned Aerial Vehicles (UAVs) usually rely on visual fiducial markers for autonomous navigation and precision landing. However, standard markers suffer from limited operational ranges, becoming undetectable when the camera is either too far or too close. While recursive and fractal markers have been proposed to address this issue, existing approaches either require the marker’s center to remain visible, making them vulnerable to occlusion, or are limited in their recursion depth and placement. We propose a novel Recursive ArUco marker design. Our method allows any standard square fiducial marker to be transformed into a recursive marker with an arbitrary depth. By employing a modified bit-sampling strategy during detection, we embed complete markers within both the black and white bits of the parent marker. This approach guarantees unlimited recursion depth and robust detection even with partial occlusion, as it does not rely on the marker’s center being visible. Furthermore, by maintaining a single, unique identifier across all recursive scales, our proposal provides an extensive dictionary of multiple unique landing pads. Our markers allow fleets of UAVs to operate simultaneously, with each drone landing at its designated location—a feature not supported by existing approaches due to their structural and dictionary constraints.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15040069

Authors: Takahiro Miura Ken-ichiro Yabu Atsushi Katagiri Masaki Matsuo Naoyuki Okochi Keiichi Yasu Masatsugu Sakajiri Tohru Ifukube

We developed Tactule, a compact tactile display module that can be attached to host hardware ranging from PCs to game controllers, and characterized its frequency response under controlled, finger-pad-like loading. Tactule uses a 6×6 matrix of multilayer-bimorph piezoelectric pins (with the four corner pins removed; 32 channels at 2 mm pitch), together with an 8×8 variant, that delivers more than 60 μm of free displacement at AC 5 V, a regime accessible from a standard USB power supply. We measured per-pin peak-to-peak rear-face displacement at 50–800 Hz across a graded series of five silicone loads (Shore A 10 to 90) and an unloaded reference, using sinusoidal and rectangular driving signals. The unloaded response peaks at 600 Hz; Shore A 10 loading shifts the peak to 750 Hz; and above 700 Hz, the Shore A 10 amplitude exceeds the unloaded amplitude. Coupling the measured waveforms to published models of the tactile periphery shows that the module drives the Pacinian channel with a wide margin throughout the band while reaching the non-Pacinian channels only at its low-frequency edge, providing engineering knowledge for designing receptor-specific stimulation patterns in assistive applications.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15040068

Authors: Ulugbek Amirsaidov Ernazar Reypnazarov Gozzal Eshniyazova Kuanishbay Sadatdiynov Chen Lu Yunsheng Zhang Muhammad Sadiq

This paper proposes a priority-aware EP-ALOHA framework with predictive radio resource allocation for heterogeneous machine-to-machine (M2M) devices in 5G massive machine-type communication (mMTC) networks. The proposed framework extends conventional EP-ALOHA by introducing M2M priority classes, priority-dependent delay constraints, and Exploration Phase resource block (RB) allocation. The RB-allocation problem is formulated as an integer-constrained optimization problem, where the objective is to improve effective radio channel utilization while satisfying delay constraints for different priority classes. A Genetic Algorithm-based optimization procedure is used to generate optimization-derived RB-allocation targets under different traffic and system parameter settings. These targets are then used to train and evaluate predictive RB-allocation models, including Random Forest, Neural Network, Gradient Boosting, and Linear Regression. The simulation results show that the proposed priority-aware EP-ALOHA method achieves a higher successful access probability than the considered baseline schemes within the feasible operating region. For predictive RB allocation, the Neural Network achieved the best test-set performance, with MSE = 25.5002, RMSE = 5.0498 RBs, MAE = 3.2629 RBs, and R2 = 0.9810. A separate computational evaluation showed that Random Forest inference reduced the mean allocation-decision time from 213.54 ms for GA-based optimization to 15.20 ms, corresponding to a 14.05-fold speed-up on the evaluated platform. In addition, M2M device activity probability forecasting is evaluated using Bayesian estimation, LSTM, moving average, and exponential smoothing. LSTM achieves the lowest forecasting error, while exponential smoothing provides a close and computationally simpler alternative. The results indicate that the proposed framework can support proactive and priority-aware resource management for heterogeneous M2M traffic, while the learning-based components are used as approximation and forecasting tools rather than as universally superior solutions.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15040066

Authors: Geraldo Rodrigues Beltran N. Arribas João P. Castanheira Rui Melicio Paulo Gordo Duarte Valério Margarida Pinto

This paper presents the results of a low-cost environmental testing campaign performed on commercial off-the-shelf components intended for aerospace applications, specifically a housekeeping system designed for suborbital launchers. These tests encompass a broader range of thermal and mechanical testing procedures than is typically reported in the literature, providing a more comprehensive assessment of the system’s robustness. The housekeeping system is subjected to sine-equivalent dynamic loads representative of launch environments expected by vehicles such as Ariane 6, VEGA, and Falcon 9 using a shaker. In addition, thermal vacuum testing is conducted to evaluate system performance under temperature and pressure conditions representative of high-altitude flight. Following each test, the system’s functionality is assessed by comparing its performance against baseline laboratory conditions using telemetry data acquired by the system; most importantly, a critical failure on telemetry data acquisition is verified, which determines the survivability of the system. The successful completion of these environmental tests demonstrates the survivability of the housekeeping system, validating its reliability and suitability for operation in suborbital launcher missions.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15040067

Authors: Angelos Thomos Theodore Andronikos

We investigate the structural limits of Variational Quantum Classifiers (VQC) for network anomaly detection in the Noisy Intermediate-Scale Quantum (NISQ) era. Using the official 20% research subset of NSL-KDD, we train a 4-qubit classifier that embeds 16 principal components by amplitude encoding and reaches 88% accuracy on the held-out partition. On the four established attack families, an explicit many-to-one decoding of the sixteen basis outcomes attains 71.8% in-sample accuracy and a macro-averaged recall of 0.787 on held-out attack records, against 0.250 for a majority-class classifier. Aggregate accuracy conceals that separation entirely: 78.4% for the trained model against 78.7% for the trivial one. Measuring class separability in the encoded states before training, amplitude encoding retains an AUC of 0.560±0.018 at sixteen components over five seeds, against 0.762±0.020 for angle encoding. Yet a trained comparison at matched parameter count on four components converts none of that advantage into accuracy: the separation is present in the encoded geometry and absent from the classifier, which implicates the readout alongside the encoding, a distinction this design does not separate. A controlled sweep over five ansatz depths and five seeds, spanning 8 to 72 trainable parameters at fixed encoding, data and decoding, finds subsample accuracy saturating at 0.880±0.005 while the training objective keeps falling, with a parameter-matched circuit trailing a 73-parameter classical network by 7.9 points across the two protocols compared. Depth is therefore not the binding constraint. On KDDTest+, classical recall on novel signatures falls by 19 to 32 points while the variational classifier shows no comparable decline.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15040065

Authors: André Daniel Neves Almeida Tahmid Quazi Sulaiman Saleem Patel Mohamed Mostafa Hassan Mostafa

Trust Management Systems (TMSs) have recently emerged as a behavioural complement to identity-based approaches in Industrial IoT (IIoT) cybersecurity by evaluating node trustworthiness. Deep Learning (DL)-based TMSs offer favourable detection over heuristic and Machine Learning (ML) models. The computational density of DL models introduces a trade-off between inference fidelity and deployment feasibility, particularly in Edge-Fog-Cloud (EFC) IIoT architectures where latency and resources are constrained. This work proposes an EFC architectural framework that relocates DL inference to the Fog layer, reducing Cloud communication latency and Edge resource exhaustion. A lightweight Long Short-Term Memory (LSTM)-based model derives continuous trust scores from header-derived, flow-aggregated features, with inference latency bounded through fixed-size sliding windows and stateless execution. The system is trained and evaluated on CIC-IoT-2023 across Denial-of-Service (DoS), Distributed DoS (DDoS), Mirai, and benign scenarios. System scalability is assessed through ns-3 network simulation under benign conditions, with full-system behaviour further evaluated under benign, DoS, and Mirai scenarios. Offline evaluation achieves F1-score 0.9996, accuracy 0.9997, ROC-AUC 0.9999, and PR-AUC 0.9997. Architectural evaluation yields a mean inference latency of 0.049 ms, a maximum enforcement latency of 0.120 ms, and a 302 kB deployment footprint. System simulation confirms a benign False Positive Rate (FPR) 0.07% and a maximum detection latency of 0.22 ms. DoS achieves recall 0.99999 and FPR 0.00186, and Mirai achieves recall 0.99997 with FPR 0. This demonstrates that DL-based trust inference is achievable on resource-constrained Fog nodes, establishing the work as a viable solution for trust evaluation in EFC IIoT deployments.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15040064

Authors: Zhen Liu Dazhong Ma

In DC microgrid (DC-MG) clusters, distributed generation units rely on electronic communication networks to exchange voltage measurements, current information, and coordination signals for voltage recovery and current sharing. As the degree of system clustering and communication coupling increases, nodal denial-of-service (DoS) attacks may interrupt the information exchange of leaders and followers, resulting in communication topology switching and degraded cooperative control performance. Accordingly, this paper proposes an event-triggered (ET) resilient control scheme with high communication efficiency for networked DC-MG clusters under nodal DoS attacks. First, a distributed secondary control model with a cross-layer communication mechanism is constructed in accordance with the requirements of the system’s overall power distribution, which incorporates the two-layer node architecture of leaders and followers in DC-MG clusters. Second, a statistical multimode nodal DoS attack model is developed to characterize heterogeneous communication interruptions through topology-dependent attack modes and their occurrence probabilities. Finally, an exponential threshold ET mechanism based on bus-voltage recovery errors is designed within the distributed secondary control framework to reduce redundant information transmission while preserving resilience against nodal communication attacks. Simulation results demonstrate that the proposed method can maintain accurate voltage recovery and current sharing in networked DC-MG clusters under large-scale DoS attacks, while improving communication efficiency through ET updates.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15040063

Authors: Hasan M. A. Islam Md. M. R. Maharaz M. Georgiades S. M. N. Shahriar P. Akibuzzaman N. R. Aurna Md. Masum Riadul Islam

This paper introduces the Sensor Traffic Generator (STGen), a lightweight, pure-software testbed for evaluating IoT application- and transport-layer protocols at scale. Relative to existing software-based IoT evaluation platforms, STGen combines three design decisions that, to the best of our knowledge, no prior testbed offers together. Every emulated sensor node runs as an independent operating-system process using a real transport stack rather than a discrete-event model or a container. Sensor workloads are generated using physically grounded stochastic models calibrated against real deployment data. Experiments are specified in three independent tiers, IoT Protocols (N), Scenarios (M), and Networks (L), reducing configuration effort from a combinatorial N×M×L problem to a linear N+M+L workflow, with new protocols integrated by overriding a four-method abstract interface. STGen operates above OSI Layer 4 and therefore does not model PHY- or MAC-layer behavior, such as RF interference, CSMA/CA collision avoidance, or duty cycling. The sensor models are calibrated using 1,826,223 real-world readings from the Intel Berkeley Research Laboratory; for temperature, the synthetic stream matches the 37-day measurements of 54 Mica2Dot motes with a Kolmogorov–Smirnov D of 0.071 and a Jensen–Shannon divergence of 0.018, showing that STGen reproduces the statistical structure of real sensor data rather than only plausible values. By inverting these calibrated models, STGen also synthesizes labeled false-data-injection anomalies that are separable from normal traffic, with a receiver operating characteristic AUC of 0.898 for stealthy drift and 1.0 for hard physical range violations. In our experiments, STGen instantiates 6000 concurrently emulated sensor nodes on a commodity workstation in 1.02 s using 0.62 GB of memory (approximately 99 KB per node), which is more than two orders of magnitude below the per-node memory costs of container- and VM-based testbeds. STGen also exposes deployment-relevant behavior that controlled emulation alone may hide. Under live wide-area jitter, MQTT and CoAP exhibit different loss and latency patterns than those observed under uniformly degraded NetEm conditions, including MQTT reconnection storms. These results show that STGen provides a scalable and reproducible bridge between lightweight protocol emulation and practical deployment-oriented IoT protocol evaluation.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15040062

Authors: Henrique Santos Pedro Magalhães

Industrial Internet of Things (IIoT) production environments rely on automated communication between control systems and embedded devices while operating under strict availability constraints that limit the deployment of conventional IT security controls. Despite extensive research on intrusion detection systems, empirical studies based on long-term observations of real industrial networks remain scarce. This paper presents a longitudinal 92-day passive monitoring study of a production-line IIoT network comprising 22 monitored devices. A containerised instance of Zeek was deployed in promiscuous mode to collect flow-level and application-layer telemetry without interfering with operations. The resulting dataset contains more than 41.5 million network flows and 520.5 million packets, represented by 48.48 GB of structured Zeek logs. The results reveal highly deterministic communication patterns dominated by periodic HTTP polling between a central server and distributed devices. In particular, the hourly mean HTTP response size remained highly stable at 132.76 bytes, with a standard deviation of 1.37 bytes and a coefficient of variation of 1.0%. Although no confirmed malicious activity was observed, transient deviations were identified and attributed to planned production stoppages restart periods, which caused temporary traffic reductions and short-lived packet bursts. These findings demonstrate that production-line IIoT networks can exhibit predictable behaviour regimes suitable for statistical anomaly detection. The study contributes a longitudinal empirical characterisation of a real operational IIoT network, a reproducible methodology for behavioural baseline extraction using passive telemetry, and practical insights for safe monitoring deployment.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15040061

Authors: Josphat Moyo Brett Van Niekerk Richard C. Millham Halleluyah Oluwatobi Aworinde

The rapid deployment of Internet of Things (IoT)-enabled video surveillance systems has expanded the capabilities of real-time monitoring in smart cities, healthcare facilities, industrial environments and critical infrastructure. However, integrating resource-constrained cameras, heterogeneous communication protocols, edge/cloud analytics, and sensitive video data creates a complex cybersecurity landscape. This systematic review synthesizes recent evidence on security challenges and mitigation strategies in IoT-enabled video surveillance systems. Following the PRISMA 2020 guidelines, four bibliographic databases (Scopus, IEEE Xplore, Web of Science, and Google Scholar) were searched for peer-reviewed journal articles and conference papers published between January 2021 and July 2025. After duplicate removal, title/abstract screening, full-text assessment, and quality appraisal, 21 studies were included for qualitative synthesis. The findings show that vulnerabilities occur across three interdependent architectural layers: device/perception, network/communication, and application/cloud. The frequently reported weaknesses were default credentials, insecure firmware, unencrypted video streams, weak protocol configuration, metadata leakage, and inadequate cloud access control. Existing mitigation strategies, including multi-factor authentication, role-based access control, TLS/DTLS, lightweight encryption, intrusion detection systems, and secure boot, provide partial protection but remain constrained by latency, computational overhead, energy consumption, scalability, cost and legacy device compatibility. This review further identifies a persistent research–practice gap: only a small subset of studies provides evidence of real-world deployments, while most solutions remain evaluated in simulations, testbeds, or conceptual frameworks. This review contributes a domain-specific taxonomy of IoT video surveillance security, a comparative evaluation of mitigation strategies using technical, operational, and economic criteria, and deployment-oriented recommendations for smart city, industrial, healthcare, residential, and critical infrastructure settings. The study highlights the need for cross-layer security architectures, lightweight and post-quantum-ready cryptography, privacy preservation, edge AI, federated learning, zero-trust access control, and standardized security baselines.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15040060

Authors: Anton A. Esin Elmira Yu. Kalimulina

Mobile platforms such as high-speed trains and unmanned aerial vehicles (UAVs) experience quasi-periodic variation in link quality as they move through a cellular base-station lattice, so the service rate of their on-board uplink buffer is itself time-periodic. We model this buffer as a periodic M/M(t)/1 queue whose service rate follows from a signal-to-noise-ratio (SNR)-to-rate map and construct an edge-resident controller that exploits this periodic structure for real-time quality-of-service (QoS) control. From a harmonic-balance (Fourier–Galerkin) solution of the periodic regime, the controller derives backlog and tail-probability indicators and uses them to drive admission, redundancy and handover decisions on the device. The method rests on a stability criterion and a quantitative error bound for the spectral truncation, under stated regularity and stability conditions, and is validated against Monte Carlo simulation along a ∼650 km geo-anchored corridor: on the periodic backbone, the solver matches simulation to within about 1.6%, and a coefficient-driven admission rule lowers the 99th-percentile delay by about 28% relative to a reactive baseline at high load. On the full map-derived profile with aperiodic coverage gaps, the proposed proactive controller—spectral backbone admission combined with a radio-map look-ahead—attains the lowest mean and tail delay, about 27% and 21% below the reactive baseline and 54% and 42% below uncontrolled DropTail, with buffer overflow cut from 2.2% to 0.1%, at a deliberate admitted-load cost (goodput ≈0.84 vs. 0.94). An operation-count analysis indicates compatibility with sub-100ms control deadlines on a Cortex-A55-class system-on-chip. The controller runs on the device itself, without cloud or GPU, and the architecture is realised in a granted patent; end-to-end hardware benchmarking and an extension to non-Poisson traffic are left for future work.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15040059

Authors: Manolo Dulva Hina Amar Ramdane-Cherif

AI-assisted machine–environment interaction has emerged as an important research direction at the intersection of artificial intelligence (AI), sensor and actuator networks, and the Internet of Things (IoT) [...]

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15040058

Authors: Dalibor Radovanovic Nikola Savanovic Petar Kresoja Jelena Janackovic Teodor Petrovic

Industrial Internet of Things (IIoT) deployments face a security challenge that neither physics-based nor AI-based anomaly detection addresses alone: physics models are adversarially robust but miss behavioral attacks that remain within physical bounds, while AI models detect behavioral anomalies but are vulnerable to adversarial evasion and blind to physical sensor spoofing. This paper proposes PhySec-Edge, a hybrid framework integrating a Physics Validation Engine (PVE) with a multi-model Edge AI Detection Engine (EADE) in a layered, residual-sharing architecture. The PVE applies process model residuals, Kalman filter state estimation, cross-sensor consistency checks, and temporal gradient validation to generate physics-grounded anomaly signals. The EADE is designed around LSTM temporal detection, variational autoencoder reconstruction analysis, and graph neural network process monitoring augmented with PVE residuals; the current evaluation uses computationally tractable proxy implementations to provide a conservative lower bound on the benefits of residual sharing. Randomized smoothing is applied under bounded perturbation assumptions to improve adversarial robustness. PhySec-Edge is evaluated in a controlled synthetic IIoT setting parameterized using SWaT-inspired structural and statistical assumptions, comprising 9875 samples across seven attack classes. Across five random seeds, the hybrid framework achieves mean precision = 0.789 ± 0.004, recall = 0.808 ± 0.003, F1 = 0.798 ± 0.003, and FPR = 5.0% ± 0.0%, compared to F1 = 0.654 ± 0.006/FPR = 24.0% for the physics-only baseline and F1 = 0.774 ± 0.003/FPR = 5.0% for the AI-only baseline. An ablation study identifies residual augmentation as the primary individual improvement mechanism (ΔF1 = +0.017), while the full hybrid configuration achieves a combined gain of ΔF1 = +0.025 over the AI-only baseline. Critical hybrid advantages appear on adversarial evasion (+0.15 F1) and firmware implant (+0.17 F1), the two attack classes where neither layer alone is sufficient. A preliminary feasibility check on an Edge-IIoTset-inspired benchmark confirms that the architectural advantage pattern generalizes across dataset structures. Gateway latency analysis confirms compatibility with soft real-time industrial monitoring constraints.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15040057

Authors: Anar Khabay Akerke Baurzhan Amandyk Tuleshov Moldir Kuatova Nurgul Smailova Bauyrzhan Bazarbay Ainur Ormanbekova Zhazira Julayeva Yerkebulan Tuleshov

Industrial wireless sensor and actuator networks are increasingly used in closed-loop control systems. In such systems, packet dropout, channel degradation, and communication delay can deteriorate tracking performance. This paper proposes a Radio-Quality-Aware Model Predictive Control (MPC) strategy for an industrial conveyor drive system operating under time-varying wireless communication conditions. Unlike classical MPC, the proposed controller incorporates radio-channel information, including the signal-to-interference-plus-noise ratio (SINR), packet error rate (PER), and network-induced delay, into the predictive control formulation, thereby adapting the control action to degraded communication conditions. In the MATLAB simulations, an industrial load torque profile based on sensor-measured signals was used, and the wireless communication scenario was divided into three regions representing favorable, moderately degraded, and severely degraded conditions. The results demonstrate that the proposed MPC maintains the angular speed closer to its reference value than the classical MPC, particularly under severe degradation when the SINR decreases to 5 dB. Compared with the classical MPC, the proposed Radio-Quality-Aware MPC reduces the integral of absolute error (IAE) by approximately 90.6%, the root mean square error (RMSE) by 91.4%, the maximum absolute tracking error by 92.7%, and the input variation index by 67.2%, while maintaining a comparable level of control energy. Overall, these results demonstrate that the proposed Radio-Quality-Aware Model Predictive Control framework improves tracking accuracy, actuator smoothness, and system robustness in industrial wireless control applications.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15040056

Authors: Amir Ijaz Hashem Haghbayan Ethiopia Nigussie Abdul Malik Juha Plosila

This paper presents a joint communication–computation optimization (JCCO) framework for energy-efficient resource allocation in edge-assisted swarm robotics. The proposed framework jointly optimizes task offloading, bandwidth allocation, transmission power, and computational workload under latency and energy constraints. A distributed optimization strategy combined with a lightweight deep reinforcement learning controller enables adaptive and scalable decision making for resource-constrained robotic swarms. The simulation results demonstrate that the proposed method reduces the total swarm energy consumption by up to 41% while maintaining more than 99% deadline satisfaction across varying swarm sizes and communication conditions. The framework further achieves improved fairness, lower communication overhead, and efficient embedded deployment suitability for TinyML-enabled robotic platforms.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15040055

Authors: Doan Perdana Pascal Lorenz Ongko Cahyono Sri Hartati

The paper suggests a distributed cross-layer IoT architecture that combines LoRaWAN (Long Range Wide Area Network) with federated learning (FL) to improve reliability, scalability, and fault tolerance in multi-layer vertical farming systems in dense and dynamic environments. Unlike the traditional frameworks that rely on independent measures of QoS (Quality of Service), the proposed framework directly represents the inter-layer relationships, such as heterogeneity of latencies, robustness of connectivity, and propagation of faults. One of the contributions is the development of a cohesive cross-layer evaluation framework with six strictly defined metrics: MLDC (Multi-Layer Deployment Capacity), C-LCRI (Cross-Layer Connectivity Robustness Index), C-LFCI (Cross-Layer Fault Containment Index), SART (Smart Adaptive Recovery Time), and AIRSM (AI Resilience Score Metric), which allows for quantitatively characterizing latency differences, network resilience, fault containment, recovery efficiency, AI robustness, and energy-performance trade-offs. The experimental results show that the proposed Smart Distributed LoRaWAN–Federated Learning architecture operates reliably in high-density and multi-layer vertical farming environments, and is scalable to handle larger amounts of data. The proposed system guarantees a packet delivery ratio (PDR) of around 95% under a large-scale deployment with up to 1050 IoT nodes spread across seven cultivation layers, with a latency reduction of nearly 60%, less than 1.6 J/msg on average energy consumption, and a fault recovery time of less than 0.3 s in case of network disruptions. The proposed framework was validated using large-scale simulation scenarios developed based on experimentally reported LoRaWAN communication characteristics and agricultural IoT deployments, and operational conditions at the edge intelligence. This evaluation included up to 1050 sensing nodes in 7 vertical farming layers to approximate a realistic deployment of smart farming in a large-scale environment while keeping consistency with the recorded communication and reliability profile.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15040054

Authors: Archana Dhamotharan Balakumar Muniandi Vennila Anandaraj Umapathy Neya Subramanian Sowmiya Balamurugan

This paper proposes a method of fault detection in analog circuits which involves various steps, including selection of benchmark circuits, dataset preparation, signal decomposition, model training, and performance analysis. The main aim of this work is to provide solid performance even in noisy environments. Monte Carlo analysis is used to generate a synthetic dataset with 200 runs per fault class by introducing component tolerances and realistic faults. A multi-stage pipeline is proposed; it begins with resampling the signals and normalizing them, and then noise is added at different levels: 5 dB, 10 dB and 20 dB. Feature fusion is performed by combining time-, frequency-, and statistical-domain features. Statistical-domain features are extracted by applying Variational Mode Decomposition (VMD) to split them into four IMF levels, followed by the application of Continuous Wavelet Transform (CWT) for time–frequency-domain analysis. Support Vector Machine (SVM), Random Forest, and Gradient Boosting are used as base-level classification models. A stacking ensemble model is developed which uses Random Forest, Gradient Boosting, and Extra Trees as base learners and Logistic Regression as the meta-learner.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15040053

Authors: Carolina Del-Valle-Soto Carlos Mex-Perera Eduard Velazquez José Varela-Aldás Leonardo J. Valdivia Orlando Montoya-Márquez

Low-Power Wide-Area Networks based on LoRa are widely deployed in smart city, agricultural, and environmental monitoring, where their constrained energy budget makes them vulnerable to radio-frequency jamming. (1) Background: a node that keeps transmitting into a jammed channel wastes energy on undeliverable packets, yet detection and energy management are usually treated separately. (2) Methods: we present J-DEAS, a Jamming-Driven Exponential Adaptive Sleeping technique that couples a lightweight, threshold-based detector with an exponential sleep back-off scheduler. The detector uses only the RSSI and SNR reported by commodity transceivers, and a single exponentially weighted confidence variable drives the sleep interval; we analyze the decision boundary, confidence dynamics, steady-state duty cycle, and latency–energy trade-off in closed form. (3) Results: on a measurement dataset the detector reaches an AUC of 0.985 and an F1 of 0.969; under sustained jamming, J-DEAS cuts the duty cycle from 100% to 5.5% and wasted transmissions from 94.3% to 8.3%, with a single-slot median latency and a sub-2% false-sleep rate on clean channels. (4) Conclusions: the technique needs no training and no extra hardware, making it suitable for resource-constrained end devices.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15040052

Authors: Francisco-Jose Alvarado-Alcon Rafael Asorey-Cacheda Joan Garcia-Haro Laura García Antonio-Javier Garcia-Sanchez

Smart city environmental monitoring depends on sparse air quality sensor networks and analytics services that remain reliable under node additions, outages, and missing streams. We propose an operational deep learning framework for citywide cross-location forecasting from a limited set of sensors, delivering low-latency, real-time concentration heatmaps at unsensed locations by combining temporal prediction with spatial regression. We formulate single-stage spatiotemporal forecasting and benchmark nine recurrent, convolutional, and multilayer architectures against classical baselines. The framework forecasts O3, NO2, PM2.5, and PM10 over horizons from 1 h to 10 days. Using open monitoring data from Madrid (Spain) and Cali (Colombia), we evaluate generalization by holding out stations, reflecting deployment to new sensor nodes and sparse coverage regimes. We further compare missing data handling strategies and show that common imputation can substantially degrade accuracy, increasing RMSE by up to 74% in some settings. Beyond prediction, the framework provides a basis for guiding sensor network densification; confidence estimates can highlight locations where additional sensors may be most beneficial. These results provide actionable guidance for deploying AI-enabled sensing services with robust performance under realistic sensor reliability constraints while supporting real-time citywide mapping.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15040051

Authors: Sholpan Bekmukhanbetova Elmira Zhatkanbayeva Akmaral Sagybekova Daniyar Mukashev Meirambay Toilybayev Tatyana Baratova Gulbarshyn Smailova Ayaulym Rakhmatulina Kalmukhamed Tazhen

As automation increases, mechatronic manufacturing systems require supervisory solutions that combine precise control, intelligent diagnostics, and intralogistics awareness. This paper presents a networked sensor–actuator–information architecture integrating model predictive control (MPC), Random Forest (RF)-based diagnostics, and logistics-aware coordination for automated mechatronic manufacturing systems. The main contribution is the explicit coupling of logistics-related supervisory variables with the predictive control problem and the diagnostic feature space. Buffer occupancy, transport delay, and logistics-induced waiting state are incorporated into an augmented reduced-order model to support constrained control and health-state interpretation. The framework is evaluated through a comparative simulation-based feasibility study using a low-order model of a robotic production axis affected by disturbances, degradation, and logistics-related constraints. The proposed approach is compared with classical feedback control, predictive control without diagnostics, and predictive control with diagnostics but without explicit intralogistics coupling. In the reduced-order simulation scenario, the proposed method achieved the lowest mean RMSE of 0.330 ± 0.015 and the lowest mean constraint violation rate of 3.133 ± 0.280% across 40 repeated simulation runs. However, the improvement in nominal tracking accuracy over the strongest diagnostic-assisted MPC baseline was marginal. Adding logistics-related diagnostic features improved mean accuracy from 0.848 ± 0.014 to 0.874 ± 0.012 and mean F1-score from 0.844 ± 0.016 to 0.872 ± 0.013. The main advantage of the proposed architecture was observed in reliability- and continuity-oriented indicators, including reduced downtime, lower final damage accumulation, fewer cooling cycles, and improved differentiation between machine-related and logistics-induced abnormal conditions.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15040050

Authors: Dimitrios G. Fragkoulis Fotis N. Koumboulis Maria P. Tzamtzi Nikolaos D. Kouvakas Konstantinos S. Katsiavrias Klimis K. Katsiavrias

A chlorinated water station in Delfino, Greece, was studied from the control and fault diagnosis point of view, using the interaction of the devices installed to the station as well as rules resulting from the physical characteristics of the station. The DES models of the station’s devices (pumps, level sensors, flow sensors, and pressure sensors) are presented. The models of the pumps include both the activation/deactivation functionality and the regulation of the output flow of the pump. The models of the devices were validated using field data extracted from the monitoring system of the station. Towards protecting the pump from dry running and the tanks from overflow, a set of safety requirements were realized in the form of supervisor automata. Using field data, the effect of the supervisors in the activation/deactivation of the pumps was tested. A modular fault diagnosis system, where the number of fault diagnosers is equal to the number of pumps, was implemented to diagnose the faulty case of pump having stuck open despite deactivation command. A fault diagnosis system for a flow sensor of the station was developed and tested using the field data of the sensors and the pumping system. Supervisors and diagnosers were tested using one-week field data. The structured language code for PLC implementation of the diagnosers is presented.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15040049

Authors: Adrián García Jorge Beltrán Noelia Hernández Ignacio Parra Euntai Kim

Indoor localization systems based on WiFi are gaining popularity due to their low implementation cost and the widespread availability of WiFi infrastructure. However, the wide variety of existing hardware poses a significant challenge in developing systems that maintain robust and consistent performance regardless of the device used. Recent research has addressed this issue of device heterogeneity by building datasets that include data from a diverse set of devices. In this paper, we tackle this challenge by presenting a novel, multi-device, WiFi Received Signal Strength dataset collected along unconstrained trajectories using nine Android devices over a three-month period with precise ground truth positions obtained using Simultaneous Localization And Mapping. We then study the effect of heterogeneity in the localization performance using an LSTM-based neural network that leverages the temporal nature of sequential WiFi scans, and introduce two mitigation strategies: per-device Received Signal Strength normalization and the incorporation of temporal features as additional input. Our results show that these methods significantly improve cross-device performance with a mean average localization error reduction of 56% and enable generalization to previously unseen hardware with a mean average localization error 8% higher for the unseen devices.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15030048

Authors: Diana Kalita Pavel Lyakhov Valery Andreev Denis Butusov

Determining the 3D position of a vehicle from a 2D image plays a key role in video surveillance, autonomous driving, and spatial localization. However, localization accuracy can significantly degrade in conditions of incomplete or synthetic measurement noise and keypoint jitter. In this paper, we propose a new iterative 3D position estimation algorithm (KGA). This algorithm includes geometric correction and calibration steps for converting from 2D to 3D coordinates; trajectory prediction and correction using a Kalman filter; and adaptive tuning of the filter parameters using the Goldschmidt algorithm. Experiments confirm that KGA outperforms the standard (FK) and modified (MFK) Kalman filters in accuracy and convergence speed, demonstrating robustness to various camera angles and noise levels. The novelty of this approach lies in the integration of the Goldschmidt algorithm into the Kalman filter to create an adaptation mechanism that dynamically adjusts the measurement noise covariance based on instantaneous innovation magnitude. Unlike end-to-end deep learning trackers or nonlinear filters (EKF/UKF), KGA is designed as a lightweight post-processing stage that can be seamlessly integrated into existing detection pipelines while maintaining the low computational footprint required for UAV-based edge deployment. The algorithm is of practical value for computer vision systems requiring accurate and robust tracking under varying observational conditions, with current implementation suitable for offline or buffered processing, and clear pathways to real-time deployment through code optimization. The algorithm is of practical value for computer vision systems requiring accurate and robust tracking under varying observational conditions.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15030047

Authors: Wenxue Zhang Ziyi Ma Ning Zong Dušan M. Stipanović

Multi-manipulator cooperative systems are widely deployed in industrial assembly, intelligent manufacturing and other fields, but collision safety and efficient motion coordination during coordinated operation remain key challenges. In this paper, a novel cooperative control strategy based on relative velocity information is derived to guarantee collision-free maneuvers for multiple m-degree-of-freedom (m-DOF) manipulator systems with general Lagrangian dynamics. One key advantage is that it ensures reliable safety while achieving smoother avoidance maneuvers, reduced interference with objective tasks, lower energy consumption, and improved task efficiency; notably, the avoidance control depends not only on the relative distance between manipulators but also on their relative motion, making it less conservative as manipulators avoid unnecessary spreading during collision avoidance. Another is that it integrates collision avoidance, disturbance attenuation, and deadlock elimination into a unified closed-form control law, which yields a closed-form solution and is easy to implement in engineering practice. Theoretically, this paper adopts the generalized Lyapunov stability theory to rigorously prove the asymptotic convergence and persistent collision-free property. Finally, simulation results on a dual two-DOF manipulator system further verify the effectiveness and reliability of the proposed control strategy.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15030046

Authors: Zhao Liu Daniele Soria Chee Siang Ang Sukhi Shergill

Wearable inertial sensing has considerable potential for process-level analysis of upper-limb function, but further evidence is needed to understand how it can be applied within ecologically structured immersive virtual reality (VR) tasks. Most VR-based functional assessments rely primarily on outcome-level indicators, such as task completion time, success rate, or error count, which may not fully capture how a task is executed. This exploratory study investigated whether wearable IMU signals collected during an immersive VR sushi-making task could support binary detection of a core upper-limb manipulation phase and provide additional information about task execution beyond global performance outcomes. A total of 45 participants contributed usable motion recordings for this study, with five Xsens DOT sensors placed on the hands, forearms, and waist. Three signal modalities were analysed, including acceleration (ACC), gyroscope angular velocity (GYR), and Euler angles. The downstream recognition problem was formulated as a binary classification task (Placing vs. Non-Placing), and a self-supervised learning (SSL) pretrain–fine-tune strategy was evaluated against conventional machine learning and from-scratch deep learning baselines using five subject-wise validation splits. The strongest overall performance was achieved with hand-mounted accelerometer signals, with LeftHand–ACC achieving a Macro-F1 of 0.712±0.128 and RightHand–ACC achieving 0.679±0.118. Under both hand-ACC settings, SSL fine-tuning showed higher mean Macro-F1 than the Balanced Random Forest baseline and the same deep architecture trained from scratch. Recognition performance varied substantially across sensor locations, signal modalities, and task segments, with distal upper-limb sensors generally outperforming waist-based configurations. Cross-age analyses further showed that within-cohort and cross-cohort performance did not fully align, indicating sensitivity to age-related distribution shift. Beyond classification, Log Dimensionless Jerk (LDLJ) derived from the Placing action showed a significant positive association with Cognitron motor control time cost (r=0.636, p<0.001). These findings suggest that wearable IMU sensing can provide preliminary process-level information during immersive VR functional tasks, including task-phase detection, sensing-configuration comparison, cross-cohort generalisation assessment, and exploratory motion-quality analysis. The results should be interpreted as evidence of feasibility rather than as a mature biomechanical or clinical assessment model.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15030045

Authors: Alexandru-George Berciu Dan Doru Micu Eva-Henrietta Dulf

The continuous monitoring of population health is a major focus in scientific literature, with numerous studies highlighting the critical role of sleep. However, to the best of the authors’ knowledge, the multi-modal data processing required to fully map the tripartite relationship between environmental stimuli, sleep, and health has not been achieved. This paper proposes a comprehensive data fusion strategy, integrating public databases to extract common features from historical sensor data. The present paper proposes a robust processing architecture by training four classes of algorithms (mathematical, machine learning, artificial intelligence, and ensemble models) to analyse how environmental inputs impact sleep quality and, consequently, physiological health. The resulting state-of-the-art model, a multi-modal architecture comprising 10 integrated models, was tested on a massive combined dataset of 139,950 rows and 8249 columns. The model achieved an R-squared of 0.958, demonstrating superior data processing and predictive accuracy. Alongside the integrated dataset, this research establishes the computational groundwork for human-centric Digital Twins, paving the way for closed-loop IoT environments where sensor-driven analytics inform automated actuator interventions to improve sleep and health.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15030044

Authors: Evelio Astaiza Hoyos Héctor Fabio Bermúdez-Orozco Nasly Cristina Rodríguez-Idrobo

This paper investigates the integration of distributed computing and edge Artificial Intelligence (edge AI) as foundational enablers of sixth-generation (6G) mobile networks. Through a systematic review following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, encompassing over 200 peer-reviewed papers, architectural proposals, and standardization documents retrieved from IEEE Xplore, Scopus, Web of Science, MDPI, arXiv, ITU-R, 3GPP, and ETSI, this study provides a structured computational analysis of architectural approaches that integrate distributed computing paradigms and edge AI as core enablers of 6G. The analysis examines the evolution from cloud-centric to edge-centric computing, key edge AI techniques—including Federated Learning (FL), Split Learning (SL), and edge-adapted Large AI Models (LAMs)—and their role in enabling intelligent orchestration, resource optimization, and context-aware services. The comparative analysis demonstrates that edge computing architectures reduce end-to-end latency by 85–95% relative to cloud-centric deployments (under conditions of MEC servers within 1 km and 5G NR fronthaul), while federated learning with gradient compression achieves communication overhead reductions of up to 99% under IID data distributions and stable channel conditions. The results indicate that the tight integration of distributed computing and edge AI enhances network responsiveness, scalability, and adaptability, while also revealing persistent challenges related to orchestration complexity, resource constraints, security, and interoperability. The study concludes that holistic computational architectures and AI-native design principles are essential for the effective realization of 6G networks and for guiding future research and standardization efforts.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15030043

Authors: Jules Bekoka Botomba Akhlaqur Rahman Daniel T. H. Lai Vishal Sharma

The rise of Industry 4.0 has accelerated the adoption of intelligent automation in high-throughput manufacturing environments. Automated guided vehicles (AGVs) rely heavily on magnetic guidance tracks, which are susceptible to wear, contamination, and structural degradation. These defects frequently cause AGV misalignment, emergency stops, and production downtime. This paper presents a lightweight, embedded, vision-based framework for real-time monitoring of AGV magnetic tracks using Raspberry Pi 4 cameras and Python-based computer vision algorithms. The system integrates grayscale intensity modeling, histogram-based MeanShift tracking, contour continuity analysis, and machine learning-assisted classification to detect missing segments, wear, and foreign object interference. Experimental validation on a 30 m test track and five years of industrial data (>3000 samples) demonstrate robust tracking, reliable anomaly detection, and zero false positives under nominal conditions. The proposed hybrid deterministic, ML architecture supports predictive maintenance, reduces downtime risk, and contributes to resilient Industry 4.0 material-handling systems.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15030042

Authors: Rishin Patra Hilary Scott Nkimbeng Cho Jin W. Choi

This paper presents the design of a batteryless near-field communication (NFC) multi-sensor node with an integrated adaptive power-management system for sensing applications. The work focuses on harvesting energy from a 13.56 MHz NFC field to power an ultra-low power sensing platform. The design consists of the TI RF430FRL152H, an integrated NFC transponder with an embedded MSP430 microcontroller core and ferroelectric random-access memory (FRAM) non-volatile memory. The system combines an ISO/IEC 15693 NFC front end, a tuned loop antenna for optimized power harvesting, and multiple analog and digital sensor interfaces, and a firmware architecture for intermittent harvested energy operation. The aforementioned design performs on-demand data acquisition, logs measurements in the FRAM, and communicates the measured results through an ISO15693 compliant NFC link while powered entirely by the reader’s radio-frequency (RF) field. Since NFC provides only limited harvested power, efficient energy management is critical. The proposed scheme continuously monitors the storage capacitor voltage and activates each sensor only when sufficient energy is available. After every measurement, the system reassesses the stored charge before triggering the next acquisition, ensuring stable multi-sensor operation. A BMP390 temperature and pressure sensor and the on-chip temperature sensor demonstrate the platform’s capability. Experimental results show that the system harvests 1.064 mW (1.85 V, 560 µA), achieves a wireless operating range of up to 40 mm, and delivers a response time of 800 ms, demonstrating its suitability for low-power temperature and pressure sensing applications.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15030041

Authors: Isuru Munasinghe Asanka Perera Sreenatha Anavatti Matt Garratt

This study proposes a modular path optimization framework for uncrewed ground vehicles (UGVs) in uncrewed aerial vehicle (UAV)-assisted navigation environments to improve the efficiency, smoothness, and executability of paths generated by classical grid-based path planning algorithms. The principal innovation of this work is the Visibility and Line-of-Sight Path Simplification (VLoSPS) algorithm, an algorithm-independent post-processing method that removes redundant waypoints through long-range axis-aligned visibility analysis while preserving path feasibility. VLoSPS is integrated with the Direction-Aware Path Planning Approach (DAPPA) to reduce angular deviations and improve directional continuity. The proposed framework is applicable to standard algorithms, including A*, Dijkstra, Breadth-First Search (BFS), and Depth-First Search (DFS), without modifying their internal search mechanisms. The main academic contributions comprise the formulation of a generalized post-processing architecture for UAV-derived occupancy maps, the introduction of a visibility-aware waypoint reduction strategy, and extensive validation using two synthetic maze datasets and three UAV-derived semantically segmented real-world datasets. On the Göttingen Maze Dataset, the VLoSPS and DAPPA pipeline reduced the average path lengths of A*, Dijkstra, BFS, and DFS by 5.42%, 9.46%, 10.44%, and 86.00%, respectively. The consistent improvements across real-world datasets demonstrate the effectiveness, computational feasibility, and general applicability of the proposed framework for UAV-assisted UGV path planning. The implementation code and benchmark resources developed in this study are publicly released to promote reproducibility and facilitate future research.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15030040

Authors: Md. Mehedi Rahman Rana Md. Anisur Rahman Kamrul Hasan Talukder Syed Md. Galib Nazmul Siddique

The widespread manipulation of digital images on social media has significantly undermined public trust in visual content and created major challenges for automated forgery detection. These challenges are further intensified by platform-induced degradations such as compression, resizing, and filtering, which often obscure forensic traces. This work develops FIDD-6000, a large-scale benchmark dataset for image forgery detection and localization, containing 6000 social media images, including 1000 authentic and 5000 manipulated samples, with pixel-level ground-truth masks annotated across three forgery categories, splicing, copy-move, and retouching, all created under realistic post-processing conditions. Each manipulated image is accompanied by a pixel-level ground-truth mask indicating the tampered regions. To assess the challenges posed by social media-based image manipulation, we evaluate 15 state-of-the-art image forgery localization methods on FIDD-6000, including approaches based on JPEG compression artifacts, sensor-noise analysis, and error level analysis. Experimental results show that these methods perform poorly on the proposed dataset, revealing their limited effectiveness in detecting forged images that have undergone social media-specific compression and transformation. This performance gap highlights the need for more robust and advanced machine learning and deep learning approaches capable of handling the complexity of modern image manipulations. Therefore, FIDD-6000 provides a valuable resource for researchers by offering a rigorous benchmark for developing, evaluating, and comparing next-generation forgery detection and localization methods.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15030039

Authors: Kyrmyzy Taissariyeva Zhuldyz Kalpeyeva Yerlan Tashtay Yermek Bekenov Zhansaya Ayapbergen

A pressing challenge of modern wireless networks is ensuring stable radio coverage inside buildings, where radio signal propagation is significantly complicated by the influence of building structures. Reinforced concrete walls, floor slabs, internal partitions, and energy-efficient windows with metallized coatings create substantial obstacles to the propagation of electromagnetic waves, causing reflection, absorption, and scattering. As a result, areas with weakened coverage are formed inside buildings, leading to deterioration in mobile communication quality and reduced data transmission rates. This study presents an experimental investigation of the received signal strength of mobile operators inside a multi-storey residential complex. An analysis was conducted to evaluate the impact of building height, architectural features, and construction materials on radio signal propagation. In addition, the frequency bands used in 4G LTE and 5G networks by mobile operators were examined. It was found that LTE networks mainly operate in the 1.8–2.1 GHz frequency range, whereas 5G networks operate in the n77 band (3.6–3.7 GHz), which provides higher data throughput but is characterized by greater signal attenuation when propagating inside buildings. To address this issue, a Distributed Antenna System (DAS) based on GPON technology was implemented in the studied building. The placement of antenna equipment on the roof enabled the efficient reception of the signal from the base station and its subsequent distribution inside the building through an internal antenna network. The measurement results demonstrated that the deployment of a GPON-based DAS significantly improves the received signal level and ensures more uniform radio coverage inside indoor environments. The obtained results confirm that the use of distributed antenna systems is an effective solution for compensating signal losses caused by the shielding effect of building structures and can significantly improve the quality of mobile communications in dense urban environments. The results show that the RSRP level in indoor environments without DAS decreases to approximately −100 to −110 dBm, while after deployment of the GPON-based DAS, it improves to −45 to −75 dBm. This corresponds to a signal gain of up to 40–50 dB, ensuring stable connectivity and significantly improved data transmission performance.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15030038

Authors: Nurzhigit Smailov Sauletbek Koshkinbayev Kydyrali Yssyraiyl Ainur Kuttybayeva Gulbahar Yussupova Askhat Batyrgaliyev Akezhan Sabibolda

The increasing complexity and extended operational lifetimes of modern space infrastructure have significantly intensified the demand for reliable structural health monitoring (SHM) systems. However, the extreme space environment, characterized by radiation exposure, microgravity, ultra-high vacuum, and severe thermal cycling, imposes critical limitations on conventional electrical sensing technologies, leading to reduced measurement accuracy, instability, and long-term degradation. This review presents a comprehensive analysis of fiber Bragg grating (FBG)-based sensing technologies as a promising solution for deformation monitoring in space infrastructure. The study investigates the fundamental operating principles of FBG sensors under space conditions and systematically classifies existing FBG-based SHM architectures, including point-based, multiplexed, long-distance, and hybrid sensing systems. Furthermore, the advantages of FBG sensors—such as immunity to electromagnetic interference, passive operation, and high-resolution multipoint sensing—are critically evaluated in comparison with traditional electrical sensors. In addition, key challenges affecting the performance of FBG systems in space environments are analyzed, including radiation-induced wavelength drift, temperature–strain cross-sensitivity, signal attenuation, and long-term stability issues. The paper also highlights recent advances in interrogation techniques and network architectures that enable reliable in situ and real-time deformation monitoring of space structures. The results demonstrate that FBG-based sensing systems provide a scalable and robust framework for SHM in extreme environments while also revealing existing limitations and open research challenges. This work establishes a structured foundation for the development of next-generation intelligent monitoring systems for space infrastructure.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15030037

Authors: Devarajan Kaliyannan Kadhiravan M J Shree Vignesh Khumar Alampalayam Tamilselvan Kughan S A Hari Krishnan Babu Mohanraj Thangamuthu

Vibration energy harvesting has emerged as a sustainable solution for powering low-energy devices such as wireless sensors and wearable electronics. However, conventional vibration energy harvesters often suffer from narrow operational bandwidth and limited output performance under ultra-low excitation conditions. To overcome these limitations, this study proposes an asymmetric tristable vibration energy harvester integrated with an elastic magnifier (EM), hereafter referred to as the asymmetric TVEH with EM, to enhance energy conversion efficiency under weak excitation. A nonlinear two-degree-of-freedom electromechanical model is developed to describe the coupled dynamics between the cantilever beam and the EM, incorporating nonlinear restoring forces and electromechanical coupling effects. The system performance is investigated using the harmonic balance method (HBM) and time-domain numerical simulations. In addition, parametric studies are conducted to examine the influence of the EM mass and stiffness ratios on the dynamic response and energy harvesting performance. The numerical results demonstrate that the inclusion of the EM significantly amplifies the system response under ultra-low excitation (f=0.055), enabling improved inter-well motion and enhancing energy conversion efficiency by up to 45%. To validate the analytical and numerical findings, an experimental prototype is fabricated and tested. The experimental results confirm the effectiveness of the proposed design, achieving a root mean square voltage of Vrms=5V across a load resistance of RL=100kΩ under a base acceleration of 1.4m/s2 at 14 Hz, measured over a 30 s window with a low-pass filter cut-off frequency of 100 Hz. The proposed asymmetric TVEH with EM consistently outperforms both the symmetric TVEH with EM and the asymmetric configuration without EM. Overall, the results highlight the pivotal role of the elastic magnifier in enhancing the dynamic response and harvesting performance under weak excitations, demonstrating strong potential for powering low-power electronic devices in practical applications. Furthermore, this work supports the United Nations Sustainable Development Goal SDG 7 (Affordable and Clean Energy) by promoting decentralized and renewable vibration-based energy harvesting technologies.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15030036

Authors: Abdullah Alhasanat Ahed Aleid Abdelrahman Abushattal Amal Alhasanat Umar Raza

Optical Wireless Sensor Networks (OWSNs) have emerged as a promising solution for energy-efficient and secure data collection in free-space optical (FSO) environments. A key challenge in such networks is minimizing the decision error rate (DER) during decision aggregation at the central entity (CE). Building on earlier Time-Difference-of-Arrival (TDoA) reporting methods, this paper introduces an Angle-of-Arrival (AoA) framework for decision gathering. In the proposed scheme, sensor nodes equipped with Corner Cube Retro-reflectors (CCRs) passively communicate their local decisions, while the CE identifies such decisions based on AoA estimation. A closed-form expression for the DER is derived, incorporating false-alarm and missed-detection probabilities, and is validated through Monte Carlo simulations. Comparative evaluation against TDoA, Single Wavelength Parallel (SWP), and Multiple Wavelength Series (MWS) schemes shows that the AoA-based approach achieves consistently lower DERs, particularly in high-SNR regimes and larger node counts, closely approaching the theoretical lower bound. These results highlight AoA as a practical and scalable alternative to conventional decision-gathering methods in OWSNs.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15030035

Authors: Aline dos Santos Silva Miguel Velhote Correia Andreia Gonçalves da Costa Rui J. Cerqueira Hugo Plácido da Silva

Previous studies on healthy controls suggest the added value of thigh-based Electrocardiography (ECG), which collects data using sensors embedded in a toilet seat for unobtrusive signal acquisition. However, further evidence regarding its clinical feasibility is needed; with this work, we investigated three complementary aspects: signal quality, morphological correlation with standard ECG leads, and the system’s potential for heart rate variability (HRV) analysis in patients undergoing aortic valve replacement. This work was divided into two main phases. In the first, 32 healthy volunteers underwent simultaneous ECG recordings using both a standard 12-lead ECG system and the thigh-based system. Signal Quality Index (SQI) analysis revealed that 56.25% of the experimental signals were classified as excellent, and over 62.5% of recordings showed a strong correlation with Lead I of the clinical ECG. These findings extend the state of the art by further characterising the quality and relevance of the captured signals. In the second phase, two patients with severe aortic stenosis were monitored before and after surgical valve replacement. HRV metrics derived from the thigh-based ECG captured distinct autonomic responses: one patient showed significant postoperative improvement in global and parasympathetic modulation (increased SDNN, RMSSD, and Sample Entropy), while the other exhibited reduced variability and complexity, potentially indicating impaired autonomic recovery. These results highlight the feasibility of thigh-based ECG data acquisition for passive, longitudinal cardiac health monitoring in everyday environments and its applicability for pre- and postoperative autonomic assessment.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15020034

Authors: Nikola Gavric Guru Bhandari Andrii Shalaginov

Slowloris is a well-known application-layer Denial of Service (DoS) attack that is challenging to detect due to its low-rate nature, allowing it to blend with legitimate traffic and remain unnoticed. Our hypothesis is that deliberate prolongation of the pre-authentication stage in stateful protocols induces unnecessary CPU utilization. In this study, we repurpose Slowloris as an energy-oriented (E-DoS) attack that exploits pre-authentication statefulness of the most prevalent remote access protocols, the Secure Shell Protocol (SSH) and File Transfer Protocol (FTP). We employ a Raspberry Pi-based experimental setup with different software implementations of the mentioned protocols to validate our hypothesis. Our experiments confirm the susceptibility of SSH and FTP to Slowloris E-DoS attacks, and we quantify the consequential impact on power consumption. We find that the Slowloris E-DoS attack exhibits an asymmetrical nature, causing a disproportionate computational demand on victim systems compared to the resources invested by the attacker. The results of this study indicate that battery-powered single-board computers (SBCs) are critically affected by these attacks due to their limited power availability. This research demonstrates the importance of understanding and mitigating Slowloris E-DoS vulnerabilities in the SSH and FTP protocols, offering valuable insights for enhancing security measures. Our findings show that millions of SBCs worldwide may be at risk and highlight a deeper structural weakness: the stateful design of widely deployed protocols can turn service availability into an energy liability. This systemic risk extends beyond SSH and FTP, with implications for IoT devices and backends that depend on stateful communication protocols.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15020033

Authors: Mohammad Saadatseresht Hossein Arefi Fatemeh Torkamandi

The accurate interpretation of structural edges requires distinguishing geometry-driven discontinuities from reflectance- and illumination-induced variations. Conventional photogrammetric pipelines rely primarily on radiometric and geometric cues, which often lack physical interpretability under complex material and lighting conditions. This study proposes a photogrammetry–polarimetry fusion framework for physics-guided semantic classification of 3D structural edges. Radiometric, geometric, and polarimetric features are integrated within a noise-normalized representation to enable modality-independent interpretation. A rule-based classification scheme is introduced to assign edges to physically meaningful categories, including geometric, material, specular, illumination, and polarization-driven phenomena. The method is evaluated on a calibrated geometric object and a cultural heritage statue. Results show that polarization provides complementary information that reduces ambiguity between geometry-driven and reflectance-driven edge responses while preserving the underlying reconstructed geometry. On the calibrated dataset, edge detection achieves 88.4% precision, 95.5% recall, and an F1-score of approximately 0.92. Multi-view integration further improves the completeness of geometry-dominant 3D edges. The proposed framework introduces a physics-guided semantic sensing layer for multi-modal 3D perception, enabling more robust and interpretable structural analysis in photogrammetric workflows.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15020032

Authors: Chia-Hong Chou Arjun Sudheer Younghee Park

Traditional intrusion detection systems for IoT networks achieve high classification accuracy but lack interpretability and actionable incident-response capabilities, limiting their operational value in security-critical environments. This paper presents a graph-based multi-agent framework that integrates ensemble machine learning with Large Language Model (LLM)-powered incident report generation via Retrieval-Augmented Generation (RAG). The system employs a three-phase architecture: (1) a lightweight Random Forest binary pre-detection, achieving 99.49% accuracy with a 6 MB model size for edge deployment; (2) ensemble classification combining Multi-Layer Perceptron, Random Forest, and XGBoost with soft voting and SHAP-based feature attribution for explainability; and (3) a ReAct-based summary agent that synthesizes classification results with external threat intelligence from Web search and scholarly databases to generate evidence-grounded incident reports. To address the challenge of evaluating non-deterministic LLM outputs, we introduce custom RAG evaluation metrics—faithfulness and groundedness implemented via the LLM-as-Judge framework. Experimental validation on the ACI IoT Network Dataset 2023 demonstrates ensemble accuracy exceeding 99.8% across 11 attack classes; perfect groundedness scores (1.0), indicating all generated claims derive from the retrieved context; and moderate faithfulness (0.64), reflecting appropriate analytical synthesis. The ensemble approach mitigates individual model weaknesses, improving the UDP Flood F1 score from 48% (MLP alone) to 95% through soft voting. This work bridges the gap between high-accuracy detection and trustworthy, actionable security analysis for automated incident-response systems.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15020031

Authors: Michele Paoletti Giovanni Paragliola Carmelo Mineo

This study presents a structured methodology for optimizing the placement and selection of accelerometer sensors for structural health monitoring in civil infrastructures. The approach integrates both ambient and forced vibration testing data, followed by a unified analysis of sensor energy distribution through singular value decomposition of the cross power spectral density. The energy associated with each sensor is normalized and decomposed into its vertical, longitudinal, and transversal components, allowing for detailed ranking and visualization across different structural elements such as the deck and supporting piers. A comparative analysis between the energy distributions obtained from ambient and forced vibrations is conducted to identify consistent sensor locations. The sensor configuration is then iteratively refined using a combination of global dynamic criteria and local spatial constraints to ensure both stability and optimal spatial distribution. The resulting framework enables the systematic design of sensor layouts that combine energy-based robustness with optimal spatial distribution across all three spatial components, while significantly reducing the number of required sensors, ensuring the preservation of damage detection capability and long-term structural health monitoring.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15020030

Authors: Konstantinos F. Kantelis Vassilis Asteriou Aliki Papadimitriou-Tsantarliotou Olga Tsave Christos Liaskos Christos A. Ouzounis Lefteris Angelis Ioannis S. Vizirianakis Petros Nicopolitidis Georgios I. Papadimitriou

Nanotechnology continues to advance rapidly, revealing previously unexplored directions in nanoscale communications. Biological and electromagnetic nanonetworks—established communication paradigms at the nanoscale—have shifted interest toward the middle and higher levels of the nanonetworking protocol stack. Motivated by the discovery of Cable Bacteria (CB) and their unique properties, we propose a theoretical model and framework for a new category of nanonetworks: bioelectrical nanonetworks (BioEN). This proposed framework combines the biocompatibility, sustainability and inherent nanodimensions of biological organisms with the networking performance of electromagnetic systems. Large-scale formations (e.g., 10,000 cells spanning nearly 2 cm), together with the electrical characteristics of CB, suggest the feasibility of guided electron-based transport that could complement diffusion-dominated nanonetworks, subject to resistive-capacitive (RC) constraints that remain to be quantified. Furthermore, we present a set of basic network architectures—such as star, ring, and tree—introducing a conceptual bio-multiplexer component, which utilizes CB to form a bioelectrical nanonetwork and illustrate core functionalities primarily at the network layer. Within this theoretical framework, BioEN is positioned as a potential enabler for diverse scientific, environmental, and technological applications, including health and ecosystem biosensing and bioremediation-oriented bioengineering. This work is conceptual and does not experimentally validate a deployed nanonetwork; instead, it establishes the design principles, abstractions, and architectural foundations intended to guide future implementation and experimental verification of bioelectrical nanonetworks.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15020029

Authors: Rasool Seyghaly Jordi Garcia Xavi Masip-Bruin

As social networks continue to expand, smart advertising increasingly depends on machine learning to deliver personalized and effective advertisements. Federated Learning (FL) is a distributed learning paradigm that supports privacy-preserving advertising by training models locally while avoiding direct sharing of raw user data. However, ensuring the correctness, reliability, and operational robustness of FL-driven smart advertising systems remains a significant challenge, particularly in distributed and user-facing environments. In this study, we investigate the use of model checking as a formal verification technique for validating key properties of an FL-based smart advertising workflow in social networks. We combine a structured finite-state modeling approach with Linear Temporal Logic (LTL) specifications and model-checking tools to assess correctness, availability, and baseline privacy requirements. Using controlled simulation-based configurations, we show that, for a setup with 100 users and 20 edge servers, the system delivers advertisements to all users and the global model successfully processes 200 out of 200 requests. We further analyze verification overhead through detection-time measurements, observing an increase in average detection time from 10.05 s to 11.98 s as the number of users rises from 20 to 100. These results indicate that the proposed framework can provide practical assurance for FL-enabled smart advertising workflows, support more reliable deployment in distributed intelligent systems, and improve trustworthiness in real advertising applications.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15020028

Authors: Askar Abdykadyrov Gulzada Mussapirova Nurzhigit Smailov Zhanna Seissenbiyeva Gulbakhar Yussupova Ainur Tasieva Ainur Kuttybayeva Altyngul Turebekova Rizat Kenzhegaliyev Nurlan Kystaubayev

The object of this research is resource management and energy consumption processes in optical fiber communication networks with access–metro–core architectures. The study addresses the problem that conventional static and semi-dynamic control methods are unable to simultaneously ensure energy efficiency and QoS stability under conditions of exponentially growing and highly variable traffic. To solve this problem, an AI-based integrated control model was developed that combines traffic prediction, dynamic resource allocation, spectrum management, and power optimization within a unified framework. Traffic prediction is performed using LSTM–BiRNN neural networks (1.2–1.8 million parameters, 300–500 thousand records), while control decisions are generated by an Actor–Critic reinforcement learning algorithm. Simulation results obtained in the Python 3.12 and OptiSystem 17.0 environments demonstrate that, in the Access segment (1–10 Gb/s), latency is stabilized within 1–10 ms; in the Metro segment (40–120 Gb/s), energy consumption is reduced by 18–27%; and in the Core segment (400–1000 Gb/s), the efficiency of RSA algorithms increases by 22–35%. When the EDFA output power is maintained within +17 to +23 dBm, amplifier power consumption decreases by 10–15%, resulting in overall network energy savings of 20–40%. The obtained results are explained by the synergy of accurate traffic prediction provided by the LSTM–BiRNN model and proactive real-time decision-making enabled by the Actor–Critic algorithm. The distinctive feature of the proposed approach is the simultaneous optimization of energy efficiency and QoS across all access, metro, and core segments within a single integrated architecture. The results can be practically applied in the design and modernization of optical fiber communication networks, as well as in the deployment of energy-efficient intelligent network management systems.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15020027

Authors: Bahareh Lashkari Javad Rezazadeh Reza Farahbakhsh

Crowdsensing has been recently investigated as an incorporation of Human-Machine intelligence in which contribution of users is crucial. Indoor localization is one of the significant applications among divers applications that have been introduced in this area. Considering the slight infiltration of GPS signals in indoor environments crowdsensing and its promising indoor localization schemes have been utilized for providing precise localization services. Precision of crowdsensing indoor localization schemes and elimination of erroneous data collection is strongly dependent on the underlying task allocation mechanism. In this work, we have approached the localization precision as a consequence of task allocation mechanism of crowd-powered indoor localization schemes. Hence, we have proposed to tackle this issue by applying GWO (Gray Wolf Optimizer) algorithm on participants of crowdsensing scheme. It is expected that the GWO algorithm implicitly performs the task allocation procedure in account of its crowd-powered nature. Accordingly, we have applied GWO algorithm on a proposed indoor localization scenario to undertake the requirements for discrete task allocation mechanism. Implementation results demonstrated that the population-centric structure of the GWO algorithm significantly increments the accuracy of fingerprint collection mechanism which maintains an exceptional localization precision.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15020026

Authors: Askar Abdykadyrov Dina Ermanova Maxat Mamadiyarov Seidulla Abdullayev Nurzhigit Smailov Nurlan Kystaubayev

This paper presents the development and investigation of an intelligent control system for a high-frequency ozone generator integrated into an IoT-based and telecommunication environment. A cyber-physical nonlinear mathematical model combining the electrical, thermal, gas-dynamic, and chemical subsystems of the ozone generation process is proposed. The model was implemented in discrete-time form and experimentally validated using the corona–discharge-based high-frequency ozonator ETRO-02. The deviation between simulation and experimental results did not exceed 5.3% for settling time, 6.7% for overshoot, 1.6% for steady-state ozone concentration, and 0.9% for gas temperature, confirming the adequacy of the proposed model. Based on this model, a hierarchical two-level intelligent control architecture is synthesized, consisting of a fast local control loop with a cycle time of 1–5 ms and a supervisory monitoring layer. The proposed adaptive state-feedback control law with online gain adjustment ensures stable real-time operation under nonlinear dynamics, ±20% parameter variations, network delays of 1–10 ms, and packet loss probabilities of up to 5%. As a result, the settling time is reduced from 420 ms to 160 ms, the overshoot from 12.5% to 3.1%, and the steady-state error from 6.5% to 1.6%, while the specific energy consumption decreases from 11.8 to 6.2 Wh/m3. The obtained results demonstrate that the integration of a cyber-physical model with a millisecond-level intelligent control system significantly improves the dynamic performance, robustness, and energy efficiency of high-frequency ozone generators compared to classical control and monitoring-oriented IoT systems. Unlike cloud-centric IoT monitoring architectures that operate at second-level update cycles, the proposed system closes the control loop locally at the millisecond scale, enabling stabilization of fast nonlinear electro-plasma dynamics. The results demonstrate that edge-intelligent adaptive control significantly enhances both dynamic performance and energy efficiency, confirming the feasibility of millisecond-level cyber-physical regulation for industrial ozone generation systems.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15020025

Authors: Ayoob Ayoob Mohd Faizal Ab Razak Ghaith Khalil Muammer Aksoy

Vehicle networking is a new paradigm in wireless technology that facilitates communication between vehicles in close proximity and in-vehicle internet access. This technology paves the way for a variety of safety, convenience and entertainment applications, including safety message exchange, real-time traffic information sharing and public internet access. The overall goal of vehicular networks is to create an efficient, safe and convenient environment for vehicles on the road. This paper presents a Sensitive Node Election (SNE) algorithm adapted to routing protocols in certain opportunistic network environments. The algorithm focuses on selecting the best agent for communication using an innovative approach for message forwarding. Quality of Service (QoS) metrics targeted for optimization include network end-to-end throughput and packet delivery, with the aim of improving the overall performance of the network. Our algorithm includes a stochastic rebroadcasting scheme that takes into account parameters, such as vehicle density, distance between vehicles and transmission distance, and adapts to various network conditions. Furthermore, the SNE algorithm uses a metric based on transmission distance and can dynamically adapt to application requirements, such as prioritization. It provides high throughput and minimizes delay. The results demonstrate the effectiveness of this approach in improving QoS in various vehicular ad hoc network (VANET) simulations and influencing the neural network ensemble (NNE Algorithm).

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15020024

Authors: Taeyoon Kim Minseo Lee Sanghyun Cheong Chunghwa Song Han-Cheol Ryu

Soymilk solid content (%) is a critical quality indicator that is directly related to product classification and regulatory compliance in food manufacturing. However, conventional optical refractometer-based measurements often suffer from blurred scale boundaries and subjective reading errors, leading to poor reproducibility under varying illumination conditions. This study proposes an image-based signal analysis framework that quantitatively interprets blurred liquid-scale boundaries by analyzing pixel intensity profiles, their gradients, and effective boundary widths. Instead of relying on human visual judgment, the proposed method characterizes boundary uncertainty using Gaussian-smoothed intensity signals and derivative-based feature extraction. Quantitative validation against ground-truth concentration values over 150 images demonstrates an overall mean absolute error (MAE) of 1.90 and a root mean squared error (RMSE) of 3.85. Illumination conditions yielding stable, single-peak derivative responses achieve an overall MAE of 0.23, whereas severe illumination conditions associated with unstable or distorted derivative patterns result in substantially higher errors (MAE = 8.57, RMSE = 8.60). These results quantitatively confirm that derivative-based boundary signal stability is directly linked to measurement accuracy. By transforming visual ambiguity into quantifiable signal features, this work provides a practical and reproducible alternative to subjective refractometer readings and offers a foundation for reliability-aware optical concentration measurement systems in industrial environments.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15010023

Authors: Wei Zhang Yimin Shen Hang Zhou Bo Zhou Xianju Zheng Xiang Chen

Systemic risk propagation in modern financial markets is characterized by non-linear contagion and rapid topological evolution, rendering traditional static monitoring methods ineffective. Existing Graph Neural Networks (GNNs) often struggle to capture “structural breaks” during crises due to their reliance on static adjacency assumptions and isotropic aggregation. To address these challenges, this study proposes the Temporal Attentive Graph Networks (TAGN), a dynamic framework designed for extreme volatility prediction and financial surveillance. TAGN constructs an incremental multi-scale graph by fusing high-frequency trading data, supply chain linkages, and institutional co-holdings to model heterogeneous risk transmission channels. Technically, it employs a deeply coupled GAT-GRU architecture, where the Graph Attention Network (GAT) dynamically assigns weights to contagion sources, and the Gated Recurrent Unit (GRU) memorizes the trajectory of structural evolution. Extensive experiments on the S&P 500 dataset (2018–2024) demonstrate that TAGN significantly outperforms state-of-the-art baselines, including WinGNN and PatchTST, achieving an AUC of 0.890 and a Precision at 50 of 61.5%. Notably, a risk early-warning index derived from TAGN exhibits a 1–2 week lead time over the VIX index during major market stress events, such as the Silicon Valley Bank collapse. This research facilitates a paradigm shift from historical statistical estimation to dynamic network-aware sensing, offering interpretable tools for RegTech applications.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15010022

Authors: Ferdaous Kamoun-Abid Amel Meddeb-Makhlouf

Big data has significantly transformed data processing and analytics across various domains. However, ensuring security and data confidentiality in distributed platforms such as Hadoop remains a challenging task. Distributed environments face major security issues, particularly in the management and protection of large-scale data. In this article, we focus on the cost of secure information transmission, implementation complexity, and scalability. Furthermore, we address the confidentiality of information stored in Hadoop by analyzing different AES encryption modes and examining their potential to enhance Hadoop security. At the application layer, we operate within our Hadoop environment using an extended, secure, and widely used MQTT protocol for large-scale data communication. This approach is based on implementing MQTT with TLS, and before connecting, we add a hash verification of the data nodes’ identities and send the JWT. This protocol uses TCP at the transport layer for underlying transmission. The advantage of TCP lies in its reliability and small header size, making it particularly suitable for big data environments. This work proposes a triple-layer protection framework. The first layer is the assessment of the performance of existing AES encryption modes (CTR, CBC, and GCM) with different key sizes to optimize data confidentiality and processing efficiency in large-scale Hadoop deployments. Afterwards, we propose evaluating the integrity of DataNodes using a novel verification mechanism that employs SHA-3-256 hashing to authenticate nodes and prevent unauthorized access during cluster initialization. At the third tier, the integrity of data blocks within Hadoop is ensured using SHA-3-256. Through extensive performance testing and security validation, we demonstrate integration.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15010021

Authors: Bhagya Lakshmi Polavarapu V. Dinesh Reddy Mahesh Kumar Morampudi Md Muzakkir Hussain Ashu Abdul

Autism Spectrum Disorder (ASD) is a complex neurodevelopmental condition characterized by a wide range of symptoms and severity, posing significant challenges for accurate diagnosis. Approaches that rely on a single data source, or unimodal data, often fail to capture the disorder’s inherent heterogeneity. A multimodal approach, which integrates diverse data types, can create a more holistic and precise understanding of ASD. This paper introduces the Multimodal ASD (MMASD) framework, a novel predictive model for ASD. The MMASD framework is built upon two distinct input modalities: structural magnetic resonance imaging (sMRI) and corresponding phenotype data. The sMRI data provides detailed neuroanatomical metrics, including brain tissue segmentation, volumetric measurements, and cortical thickness. Complementing this, the phenotype data encompasses the clinical and behavioral characteristics of each individual. In the proposed framework, latent features are independently extracted from both modalities and then fused to generate a comprehensive representation of the multimodal information. These fused features are then used to predict ASD by leveraging the outputs of various classifiers. A majority voting ensemble is employed to determine the final prediction. The MMASD framework achieves a high accuracy of 97.27%, surpassing the performance of current state-of-the-art approaches and demonstrating the efficacy of integrating neuroimaging and clinical data for ASD prediction.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15010020

Authors: Muhammad Irfan Minhas Imran Shah Yasir Ali Fawaz Nashmi M Alhusayni

The high rate of bike commuting around the globe has greatly transformed the mode of transportation in cities, but the high speeds of motorized cycling have contributed to a high rate of serious road trauma. Although conventional helmets offer necessary passive structural protection, they do not consider the most important aspect of the emergency response, which is the Golden Hour the time frame during which medical intervention can have the most significant impact. This paper is a development and validation of an autonomous, low-cost smart helmet architecture that is programmed to operate in real-time to detect accidents and autonomously inform the operator of accidents. The system is built up of an ESP32 microcontroller with a multi-modal sensor package, which comprises an inertial measurement unit (IMU), force-impact sensors, and MQ-3 alcohol sensors to conduct proactive safety screening. To overcome the single threshold limitation of unreliable systems, a time-windowed sensor-fusion algorithm was applied in order to distinguish between normal riding dynamics and bona fide collisions. This reasoning involves concurrent cues of high-G inertial rotations and physical impacting features over a time window of 500 ms to reduce spurious activations. The architecture of the system is completely self-sufficient and employs an in-built GPS-GSM module to send the geographical location through SMS without the need to have a smartphone connection. The prototype was also put through 150 experimental tests, with some conducted in laboratories, and real-world running tests in diverse terrains. The findings reveal an accuracy in detection of 93.7, a false positive rate (FPR) of 2.6 and a mean emergency alert latency of 2.8 s. In addition, it was found that structural integrity was confirmed at ECE 22.05 impact conditions using Finite Element Analysis (FEA), with a safety factor of 1.38. These quantitative results mean that the proposed system is an effective way to address a cultural shift between passive structural protection and active rescue intervention as a statistical and computationally efficient safety measure of modern micro-mobility.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15010019

Authors: Vittalis Ayu Milena Radenkovic

Indonesia is a country of vast geographical and cultural diversity, hosting numerous cultural festivals annually, such as Sekaten, Labuhan, and the Lembah Baliem Festival. However, as the world’s largest archipelago country, Indonesia faces geographical challenges in terms of ensuring the reliability of communication networks, particularly in maintaining user experience in high-density, short-duration traffic burst environments, such as festivals. The nation’s network connectivity relies heavily on satellite networks and Palapa Ring, a national fibre-optic backbone network that comprises a combination of inland and underwater networks, connecting major and remote islands to the global internet. Although this solution can provide a baseline for broadband connectivity, an adaptive intelligent mobile edge-based solution is needed to complement the existing network infrastructure in order to meet the dynamic demands of localised and transient traffic surges across multiple temporary, geographically dispersed festival sites in both urban and rural areas. In this paper, we present a multimodal study that combines network connectivity measurements during a festival with an extensive user analysis of festival participants and organisers to investigate reliability gaps in user experience regarding network connectivity. Our findings show that internet connectivity was intermittently disrupted during the festival, and our user analysis revealed a gap between customer expectations and perceptions of network service quality and the provision of application services in a heterogeneous festival environment. To address this challenge, we propose a novel next-generation intelligent festival mobile edge framework, MobiFest, which integrates the multi-layer Cognitive Cache which has geospatial–temporal edge intelligence for localised service provisioning to improve the delivery of application services in both urban and rural festival environments. In our extensive experiments, we employ smart garbage as our use case and demonstrate how our complex, multimodal intelligent network protocol SmartGarbiC, designed based on MobiFest for garbage management services, outperforms state-of-the-art and benchmark protocols.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15010018

Authors: Miha Pipan Marko Šimic Niko Herakovič

This paper presents test results of the performance comparison of 5G standalone (SA) and non-standalone (NSA) networks in the context of gathering data of remote sensors and machines. The study evaluates key network characteristics such as latency, throughput, jitter and packet loss (for UDP protocol only) using standardized tests to gain insights into the impact of these factors on real-time and data-intensive communication. In addition, a range of communication protocols including OPC UA, Modbus, MQTT, AMQP, CoAP, EtherCAT and gRPC were tested to assess their efficiency, scalability and suitability with different send data sizes. By conducting experiments in a controlled hardware environment, we have analyzed the impact of the 5G architecture on protocol behavior and measured the transmission performance at different data sizes and connection configurations. Particular attention is paid to protocol overhead, data transfer rates and responsiveness, which are crucial for industrial automation and IoT deployments. The results show that SA networks consistently offer lower latency and more stable performance, where robust and low-latency data transfer is essential. In contrast, lightweight IoT protocols such as MQTT and CoAP demonstrate reliable operation in both SA and NSA environments due to their low overhead and adaptability. These insights are equally important for time-critical industrial protocols such as EtherCAT and OPC UA, where stability and responsiveness are crucial for automation and control. The study highlights current limitations of 5G networks in supporting both remote sensing and industrial use cases, while providing guidance for selecting the most suitable communication protocols depending on network infrastructure and application requirements. Moreover, the results indicate directions for configuring and optimizing future 5G networks to better meet the demands of remote sensing systems and Industry 4.0 environments.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15010017

Authors: Sushank Chaudhary

Underwater wireless optical communication (UWOC) has emerged as a key enabler for Internet of Underwater Things (IoUT) and autonomous sensing networks, but its reliability is severely affected by salinity-induced attenuation, scattering, and turbulence. This work presents a high-speed and salinity-resilient UWOC architecture that jointly exploits Polarization Division Multiplexing (PDM) and Multiple-Input Multiple-Output (MIMO) diversity to enhance link capacity and robustness in realistic oceanic conditions. Two 1 Gbps NRZ data channels at 1550 nm were transmitted using continuous-wave lasers and evaluated using a hybrid OptiSystem–MATLAB simulation framework with full channel modeling of absorption, scattering, turbulence, and salinity (32–36 ppt). Results reveal that the proposed PDM-MIMO system achieves more than an order-of-magnitude bit-error-rate (BER) reduction compared with non-MIMO or single-polarization baselines, maintaining acceptable BER levels up to 20 m. Performance degradation with increasing salinity is quantified, and results confirm that combined PDM and spatial diversity effectively mitigate salinity-induced losses. The presented design demonstrates a viable and scalable solution for next-generation underwater sensing and communication networks in coastal and deep-sea ecosystems.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15010016

Authors: Jianbin Xiong Jing Wang Qi Wang Jianxiang Yang Xiangjun Dong Weikun Dai Qianguang Zhang

The high-quality droplet formation in continuous inkjet printing (CIJ) is crucial for precise character deposition on product surfaces. This process, where a piezoelectric transducer perturbs a high-speed ink stream to generate micro-droplets, is highly sensitive to parameters like ink pressure and transducer amplitude. Suboptimal conditions lead to satellite droplet formation and charge transfer issues, adversely affecting print quality and necessitating reliable monitoring. Replacing inefficient manual inspection, this study develops MBSim-YOLO, a deep learning-based method for automated droplet detection. The proposed model enhances the YOLOv8 architecture by integrating MobileNetv3 to reduce computational complexity, a Bidirectional Feature Pyramid Network (BiFPN) for effective multi-scale feature fusion, and a Simple Attention Module (SimAM) to enhance feature representation robustness. A dataset was constructed using images captured by a CCD camera during the droplet ejection process. Experimental results demonstrate that MBSim-YOLO reduces the parameter count by 78.81% compared to the original YOLOv8. At an Intersection over Union (IoU) threshold of 0.5, the model achieved a precision of 98.2%, a recall of 99.1%, and a mean average precision (mAP) of 98.9%. These findings confirm that MBSim-YOLO achieves an optimal balance between high detection accuracy and lightweight performance, offering a viable and efficient solution for real-time, automated quality monitoring in industrial continuous inkjet printing applications.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15010015

Authors: Nattawat Pattarawetwong Charuay Savithi Arisaphat Suttidee

Large sports stadiums require robust real-time monitoring due to high crowd density, complex spatial configurations, and limited network infrastructure. This research evaluates a hybrid edge–cloud architecture implemented in a national stadium in Thailand. The proposed framework integrates diverse surveillance subsystems, including automatic number plate recognition, face recognition, and panoramic cameras, with edge-based processing to enable real-time situational awareness during high-attendance events. A simulation based on the stadium’s physical layout and operational characteristics is used to analyze coverage patterns, processing locations, and network performance under realistic event scenarios. The results show that geometry-informed sensor deployment ensures continuous visual coverage and minimizes blind zones without increasing camera density. Furthermore, relocating selected video processing tasks from the cloud to the edge reduces uplink bandwidth requirements by approximately 50–75%, depending on the processing configuration, and stabilizes data transmission during peak network loads. These findings suggest that processing location should be considered a primary architectural design factor in smart stadium systems. The combination of edge-based processing with centralized cloud coordination offers a practical model for scalable, safety-oriented monitoring solutions in high-density public venues.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15010014

Authors: Chang Meng Lei Shu Leijing Bai

The rapid growth of precision agriculture has accelerated the deployment of plant protection unmanned aerial vehicles (UAVs). However, reliable data resources for vision-based intelligent supervision of operational states, such as whether a UAV is currently spraying, remain limited. Most publicly available UAV detection datasets target urban security and surveillance scenarios, where annotations emphasize object localization rather than agricultural operation state recognition, making them insufficient for farmland spraying supervision. Therefore, agricultural-oriented data resources are needed to cover diverse backgrounds and include operation state labels, thereby supporting both academic research and practical deployment. In this study, we construct and release the first multi-background dataset dedicated to agricultural UAV spraying behavior recognition. The dataset contains 9548 high-quality annotated images spanning the following six typical backgrounds: green cropland, bare farmland, orchard, woodland, mountainous terrain, and sky. For each UAV instance, we provide both a bounding box and a binary operation state label, namely spraying and flying without spraying. We further conduct systematic benchmark evaluations of mainstream object detection algorithms on this dataset. The dataset captures agriculture-specific challenges, including a high proportion of small objects, substantial scale variation, motion blur, and complex dynamic backgrounds, and can be used to assess algorithm robustness in real-world agricultural settings. Benchmark results show that YOLOv5n achieves the best overall performance, with an accuracy of 97.86% and an mAP@50 of 98.30%. This dataset provides critical data support for automated supervision of plant protection UAV spraying operations and precision agriculture monitoring platforms.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15010013

Authors: Hafid Elfahimi Rachid Harba Asma Aferhane Hassan Douzi Ikram Damoune

Prevention of complications related to diabetic foot (DF) can now be performed using smartphone-connected thermal cameras. However, the absolute error associated with these devices remains particularly high, compromising measurement reliability, especially under variable environmental conditions. To address this, we introduce a physiologically motivated two-region segmentation task (forehead + plantar foot) to enable stable temperature correction. First, we developed a fully automated joint method for this task, building upon a new multimodal thermal–RGB dataset constructed with detailed annotation procedures. Five deep learning methods (U-Net, U-Net++, SegNet, DE-ResUnet, and DE-ResUnet++) were evaluated and compared to traditional baselines (Adaptive Thresholding and Region Growing), demonstrating the clear advantage of data-driven approaches. The best performance was achieved by the DE-ResUnet++ architecture (Dice score: 98.46%). Second, we validated the correction approach through a clinical study. Results showed that the variance of corrected temperatures was reduced by half compared to absolute values (p < 0.01), highlighting the effectiveness of the correction approach. Furthermore, corrected temperatures successfully distinguished DF patients from healthy controls (p < 0.01), unlike absolute temperatures. These findings suggest that our approach could enhance the performance of smartphone-connected thermal devices and contribute to the early prevention of DF complications.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15010012

Authors: Walid Mchara Giovanni Cicceri Lazhar Manai Monia Raissi Hezam Albaqami

Accurate global irradiance (GI) forecasting is essential for improving photovoltaic (PV) energy management, stabilizing renewable power systems, and enabling intelligent control in solar-powered applications, including electric vehicles and smart grids. The highly stochastic and non-stationary nature of solar radiation, influenced by rapid atmospheric fluctuations and seasonal variability, makes short-term GI prediction a challenging task. To overcome these limitations, this work introduces a new hybrid forecasting architecture referred to as WTX–CBO, which integrates a Wavelet Transform (WT)-based decomposition module, an encoder–decoder Transformer model, and an XGBoost regressor, optimized using the Chaotic Billiards Optimizer (CBO) combined with the Adam optimization algorithm. In the proposed architecture, WT decomposes solar irradiance data into multi-scale components, capturing both high-frequency transients and long-term seasonal patterns. The Transformer module effectively models complex temporal and spatio-temporal dependencies, while XGBoost enhances nonlinear learning capability and mitigates overfitting. The CBO ensures efficient hyperparameter tuning and accelerated convergence, outperforming traditional meta-heuristics such as Particle Swarm Optimization (PSO) and Genetic Algorithms (GA). Comprehensive experiments conducted on real-world GI datasets from diverse climatic conditions demonstrate the outperformance of the proposed model. The WTX–CBO ensemble consistently outperformed benchmark models, including LSTM, SVR, standalone Transformer, and XGBoost, achieving improved accuracy, stability, and generalization capability. The proposed WTX–CBO framework is designed as a high-accuracy decision-support forecasting tool that provides short-term global irradiance predictions to enable intelligent energy management, predictive charging, and adaptive control strategies in solar-powered applications, including solar electric vehicles (SEVs), rather than performing end-to-end vehicle or photovoltaic power simulations. Overall, the proposed hybrid framework provides a robust and scalable solution for short-term global irradiance forecasting, supporting reliable PV integration, smart charging control, and sustainable energy management in next-generation solar systems.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15010011

Authors: Xing Yang Zhengjie Wang Lei Shu Fan Yang Xuanchen Guo Xiaoyuan Jing

Ensuring food security requires innovative, sustainable pest management solutions. The Solar Insecticidal Lamp Internet of Things (SIL-IoT) represents such an advancement, yet its reliability in harsh, variable outdoor environments is compromised by frequent component and sensor faults, threatening effective pest control and data integrity. This paper presents a comprehensive survey on fault detection (FD) for SIL-IoT systems, systematically analyzing their unique challenges, including electromagnetic interference, resource constraints, data scarcity, and network instability. To address these challenges, we investigate countermeasures, including blind source separation for signal decomposition under interference, lightweight model techniques for edge deployment, and transfer/self-supervised learning for low-cost fault modeling across diverse agricultural scenarios. A dedicated case study, utilizing sensor fault data of SIL-IoT, demonstrates the efficacy of these approaches: an empirical mode decomposition-enhanced model achieved 97.89% accuracy, while a depthwise separable-based convolutional neural network variant reduced computational cost by 88.7% with comparable performance. This survey not only synthesizes the state of the art but also provides a structured framework and actionable insights for developing robust, efficient, and scalable FD solutions, thereby enhancing the operational reliability and sustainability of SIL-IoT systems.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15010010

Authors: Rachel Kufakunesu Herman C. Myburgh Allan De Freitas

The Internet of Military Things (IoMT) relies on Long-Range Wide Area Networks (LoRaWAN) for low-power, long-range communication in critical applications like border security and soldier health monitoring. However, conventional priority-based flow control mechanisms, which rely on static classification thresholds, lack the adaptability to handle the nuanced, continuous nature of physiological data and dynamic network states. To overcome this rigidity, this paper introduces a novel, domain-adaptive Fuzzy Logic Flow Control (FFC) protocol specifically tailored for LoRaWAN-based IoMT. While employing established Mamdani inference, the FFC system innovatively fuses multi-parameter physiological data (body temperature, blood pressure, oxygen saturation, and heart rate) into a continuous Health Score, which is then mapped via a context-optimised sigmoid function to dynamic transmission intervals. This represents a novel application-layer semantic integration with LoRaWAN’s constrained MAC and PHY layers, enabling cross-layer flow optimisation without protocol modification. Simulation results confirm that FFC significantly enhances reliability and energy efficiency while reducing latency relative to traditional static priority architectures. Seamlessly integrated into the NS-3 LoRaWAN simulation framework, the FFC protocol demonstrates superior performance in IoMT communications. Simulation results confirm that FFC significantly enhances reliability and energy efficiency while reducing latency compared with traditional static priority-based architectures. It achieves this by prioritising high-priority health telemetry, proactively mitigating network congestion, and optimising energy utilisation, thereby offering a robust solution for emergent, health-critical scenarios in resource-constrained environments.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15010009

Authors: Khaled Osmani Marc Florian Meyer Detlef Schulz

This paper presents a pre-industrial, laboratory-stage version of an innovative sensor box designed to enable remote measurement of electrical currents. The proposed prototype functions as a drone-mounted payload that can be deployed onto overhead transmission lines. Utilizing Hall-effect sensors, electronic signal processing through filtering, and digital data transmission via Arduino and Bluetooth, the instantaneous line currents are visualized in MATLAB (R2023a) as time-based curves. The sensor box can also be remotely released from the transmission line once measurements are complete, allowing a fully autonomous mode of operation. Laboratory tests demonstrated promising results for real-world applications, with measurement efficiencies ranging from 92% to 98% under various test conditions, including stress tests involving harmonics and total harmonic distortion up to 40%. Future work will focus on implementing effective shielding against high electric fields to further enhance reliability and advance the sensor’s industrialization as a novel solution for power grid digitalization.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15010008

Authors: Ihtisham Ul Haq Francesco Felicetti Francesco Lamonaca

Upper-limb motor impairment is a major consequence of stroke and neuromuscular disorders, imposing a sustained clinical and socioeconomic burden worldwide. Quantitative assessment of limb positioning and motion accuracy is fundamental to rehabilitation, guiding therapy evaluation and robotic assistance. The evolution of upper-limb positioning systems has progressed from optical motion capture to wearable inertial measurement units (IMUs) and, more recently, to data-driven estimators integrated with rehabilitation robots. Each generation has aimed to balance spatial accuracy, portability, latency, and metrological reliability under ecological conditions. This review presents a systematic synthesis of the state of measurement uncertainty, calibration, and traceability in upper-limb rehabilitation robotics. Studies are categorised across four layers, i.e., sensing, fusion, cognitive, and metrological, according to their role in data acquisition, estimation, adaptation, and verification. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) protocol was followed to ensure transparent identification, screening, and inclusion of relevant works. Comparative evaluation highlights how modern sensor-fusion and learning-based pipelines achieve near-optical angular accuracy while maintaining clinical usability. Persistent challenges include non-standard calibration procedures, magnetometer vulnerability, limited uncertainty propagation, and absence of unified traceability frameworks. The synthesis indicates a gradual transition toward cognitive and uncertainty-aware rehabilitation robotics in which metrology, artificial intelligence, and control co-evolve. Traceable measurement chains, explainable estimators, and energy-efficient embedded deployment emerge as essential prerequisites for regulatory and clinical translation. The review concludes that future upper-limb systems must integrate calibration transparency, quantified uncertainty, and interpretable learning to enable reproducible, patient-centred rehabilitation by 2030.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15010007

Authors: Christos Tsallis Panagiotis Papageorgas Dimitrios Piromalis Radu Adrian Munteanu

Industrial wireless sensor and actuator networks (IWSANs) are central to Industry 4.0, supporting distributed sensing, actuation, and communication in cyber-physical production systems. Unlike previous studies, which focus on isolated constraints, this review synthesises recent work across eight coupled dimensions. These span reliability and fault tolerance, security and trust, time synchronisation, energy harvesting and power management, media access control (MAC) and scheduling, interoperability, routing and topology control, and real-world validation, within a unified comparative framework. Following Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines, a Scopus search identified 60 primary publications published between 2022 and 2025. The analysis shows a clear shift from reactive designs to predictive approaches that incorporate learning methods and energy considerations. Fault detection now relies on deep learning (DL) and statistical modelling, security incorporates trust and intrusion detection, and new synchronisation and MAC schemes approach wired levels of determinism. Regarding applied contributions, the analysis notes that routing and energy harvesting advances extend network lifetime. However, gaps remain in mobility support, interoperability across protocol layers, and field validation. The present work outlines these open issues and highlights research directions needed to mature IWSANs into robust infrastructure for Industry 4.0 and the emerging Industry 5.0 vision.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15010006

Authors: Ilyas Potamitis

Seconds count differently for people in danger. We present a real-time streaming pipeline for audio-based detection of hazardous life events affecting life and property. The system operates online rather than as a retrospective analysis tool. Its objective is to reduce the latency between the occurrence of a crime, conflict, or accident and the corresponding response by authorities. The key idea is to map reality as perceived by audio into a written story and question the text via a large language model. The method integrates streaming, zero-shot algorithms in an online decoding mode that convert sound into short, interpretable tokens, which are processed by a lightweight language model. CLAP text–audio prompting identifies agitation, panic, and distress cues, combined with conversational dynamics derived from speaker diarization. Lexical information is obtained through streaming automatic speech recognition, while general audio events are detected by a streaming version of Audio Spectrogram Transformer tagger. Prosodic features are incorporated using pitch- and energy-based rules derived from robust F0 tracking and periodicity measures. The system uses a large language model configured for online decoding and outputs binary (YES/NO) life-threatening risk decisions every two seconds, along with a brief justification and a final session-level verdict. The system emphasizes interpretability and accountability. We evaluate it on a subset of the X-Violence dataset, comprising only real-world videos. We release code, prompts, decision policies, evaluation splits, and example logs to enable the community to replicate, critique, and extend our blueprint.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15010005

Authors: Josip Lorincz Marko Kusačić Edin Čusto Zoran Blažević

The rapid expansion of Long Range (LoRa) and Long Range Wide Area Network (LoRaWAN) protocol technologies in large-scale Internet of Things (IoT) deployments highlights the need for precise and analytically grounded energy consumption (EC) estimation of battery-powered LoRa end devices (DVs). Since LoRa DV instantaneous EC strongly depends on key transmission parameters, primarily including spreading factor (SF), transmit (Tx) power, and LoRa message packet size (PS), accurate modelling of their combined influence is essential for optimizing LoRa end DV lifetime, ensuring energy-efficient network operation, and supporting transmission parameter-adaptive communication strategies. Motivated by these needs, this paper presents a comprehensive multiple linear regression modelling framework for quantifying LoRa end DV EC during one transmission and reception LoRa end DV Class A communication cycle. The study is based on extensive high-resolution electric-current measurements collected over 69 measurement sets spanning different combinations of SFs, Tx power levels, and PS values. Based on measurement results, a total of 14 multiple linear regression models are developed, each capturing the joint impact of two transmission parameters while holding the third fixed. The developed regression models are mathematically formulated using linear, interaction, and polynomial terms to accurately express nonlinear EC behavior. Detailed statistical accuracy assessments demonstrate excellent goodness of fit of the developed EC multiple linear regression models. Complementary numerical analyses of regression models EC data distribution further validate regression models’ reliability, and highlight transmission parameter-driven variability of Lora end DV EC. The results of numerical analyses for LoRa end DV EC data distribution show that specific combinations of SF, Tx power, and PS transmit parameters amplify or mitigate EC differences, demonstrating that their joint variability patterns can significantly alter instantaneous energy demand across operating conditions. These interactions underscore the importance of modelling parameters together, rather than in isolation. The developed regression models provide interpretable mathematical formulations of instantaneous LoRa end DV EC prediction for transmission at different combinations of transmission parameters, and offer practical value for energy-aware configuration, battery-lifetime planning, and optimization of LoRa network-based IoT systems.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15010004

Authors: Gang Wei Lei Shu Wei Lin Xing Yang Ru Han Kailiang Li Kai Huang

The camera is a core device for modern surveillance and data collection, widely used in various fields including security, transportation, and healthcare. However, their widespread deployment has proportionally escalated associated security risks. This paper initially examines the current state of research on attack methods targeting camera systems, providing a comprehensive review of various attack techniques and their security implications. Subsequently, we focus on a specific attack method against universal serial bus (USB) cameras, known as electromagnetic pulse (EMP) attacks, which utilize EMP to prevent the system from detecting the cameras. We simulated EMP attacks using a solar insecticidal lamp (which generates EMP by releasing high-voltage pulses) and a commercially available EMP generator. The performance of the cameras under various conditions was evaluated by adjusting the number of filtering magnetic rings on the USB cable and the distance between the camera and the interference source. The results demonstrate that some USB cameras are vulnerable to EMP attacks. Although EMP attacks might not invariably cause image distortion or permanent damage, their covert nature can lead to false detection of system failures, data security, and system maintenance. Based on these findings, it is recommended to determine the optimal number of shielding rings for cameras or their safe distance from EMP sources through the experimental approach outlined in this study, thereby enhancing the security and resilience of USB camera enabled systems in specific scenarios.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15010003

Authors: Yerlan Tashtay Nurzhigit Smailov Daulet Naubetov Akezhan Sabibolda Yerzhan Nussupov Nurzhamal Kashkimbayeva Yersaiyn Mailybayev Askhat Batyrgaliyev

Fiber-optic gyroscopes (FOGs) have become one of the most important elements of modern inertial navigation systems due to their high accuracy, reliability, and independence from external signals such as satellite navigation. This review analyzes and discusses the key FOG architectures: interferometric (IFOG), resonant (RFOG), digital (DFOG), and hybrid (HFOG). The concepts of their functioning, structural features, and the main advantages and limitations of each architecture are examined. Particular focus is placed on advanced signal-processing and error-compensation algorithms, including filtering techniques, noise suppression, mitigation of thermal and mechanical drifts, and emerging machine learning (ML) based approaches. The analysis of these architectures is carried out in terms of major parameters that determine accuracy, robustness, and miniaturization potential. Various applications of FOGs in space systems, ground platforms, marine and underwater navigation, aviation, and scientific research are also being considered. Finally, the latest development trends are summarized, with a particular focus on miniaturization, integration with additional sensors, and the introduction of digital and AI-driven solutions, aimed at achieving higher accuracy, long-term stability, and resilience to real-world disturbances.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15010002

Authors: Lorenzo Mario Amorosa Stefano Caputo Lorenzo Mucchi Gianni Pasolini

This paper addresses the confidentiality of wireless communications in industrial internet-of-things environments by investigating the feasibility of secret key generation for link-layer encryption using ultra wideband (UWB) signals. Taking advantage of the nanosecond-level temporal resolution offered by ultra wideband, we exploit channel reciprocity to extract highly detailed, noise-like channel measurements, in line with the physical-layer security paradigm. Three key generation algorithms, operating in both the time and frequency domains, are evaluated using real-world data collected through a dedicated measurement campaign in an industrial setting. The analysis, conducted under realistic conditions, examines the impact of practical impairments, such as imperfect channel reciprocity and timing misalignments, on the key agreement rate and the length of the generated keys. The results confirm the strong potential of ultra wideband technology to enable robust physical-layer security, offering a viable and efficient solution for securing wireless communications in complex and dynamic industrial internet-of-things environments.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan15010001

Authors: Adriano Alves Pereira Daniel Hilário da Silva Caio Tonus Ribeiro Caroline Valentini de Queiroz Luanne Cardoso Mendes Leandro Rodrigues da Silva Souza Selma Terezinha Milagre Adriano de Oliveira Andrade Carlos Dias Maciel

Background: Rigidity is a cardinal symptom of Parkinson’s Disease (PD), yet its clinical evaluation remains largely subjective and susceptible to errors. This study introduces an innovative method for objectively classifying individuals with PD by combining an active wrist orthosis with Machine Learning (ML) models. Methods: The orthosis, equipped with current and force sensors, recorded biomechanical signals during passive wrist flexion and extension, from which twelve quantitative features were extracted. Data were collected from 30 participants (15 with PD and 15 Healthy Controls). Nineteen supervised ML algorithms were systematically evaluated through feature selection, cross-validation, and hyperparameter tuning. Results: Using all twelve features, QDA achieved an accuracy of 0.889 and sensitivity of 1.000, followed by GPC (0.778) and LDA (0.778). After applying feature selection with the Correlation-based Feature Subset to reduce redundancy, Extra Trees reached 0.833 accuracy, while both QDA and GPC maintained accuracies of 0.778. This consistency across models, even with a reduced feature set, highlights the robustness of the extracted biomarkers. Conclusions: These findings confirm that wrist rigidity signals provide discriminative quantitative information between PD patients and HC and are able to support PD classification, combining engineering innovation with clinical practice that highlights the potential of integrating wearable devices and ML as a personalized healthcare in PD.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan14060119

Authors: Khalid A. Darabkh Oswa M. Amro Feras B. Al-Qatanani

The Global Positioning System (GPS) and Received Signal Strength Indicator (RSSI) usage for location provenance often fails in obstructed, noisy, or densely populated urban environments. This study proposes a passive location provenance method that uses the location’s acoustics and the device’s acoustic side channel to address these limitations. With the smartphone’s internal microphone, we can effectively capture the subtle vibrations produced by the capacitors within the voltage-regulating circuit during wireless transmissions. Subsequently, we extract key features from the resulting audio signals. Meanwhile, we record the RSSI values of the WiFi access points received by the smartphone in the exact location of the audio recordings. Our analysis reveals a strong correlation between acoustic features and RSSI values, indicating that passive acoustic emissions can effectively represent the strength of WiFi signals. Hence, the audio recordings can serve as proxies for Radio-Frequency (RF)-based location signals. We propose a location-provenance framework that utilizes sound features alone, particularly the Mel-Frequency Cepstral Coefficients (MFCCs), achieving coarse localization within approximately four kilometers. This method requires no specialized hardware, works in signal-degraded environments, and introduces a previously overlooked privacy concern: that internal device sounds can unintentionally leak spatial information. Our findings highlight a novel passive side-channel with implications for both privacy and security in mobile systems.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan14060117

Authors: Jefferson Hora Gene Fe Palencia Rochelle Sabarillo Johnny Tugahan Yichuang Sun Xi Zhu

In rectifier design, the key parameters are the voltage–conversion ratio and the power conversion efficiency. A new circuit design approach is presented in which a capacitor-based, cross-coupled, differential-driven topology is used to boost the voltage–conversion ratio. The scheme also integrates an auxiliary current path to raise the power conversion efficiency. To demonstrate its practicality, two three-stage rectifiers were designed and fabricated using standard 65 nm CMOS technology. The designs were tested under various conditions to assess their performance. The first rectifier targets indoor light energy harvesting applications. It achieves a peak voltage conversion ratio of 3.94 and a maximum power conversion efficiency of 58.7% when driving a 600 Ω load, while supplying over 2 mA of output current. The second rectifier is optimized for RF energy harvesting at 2.4 GHz. Experimental results indicate that it can deliver 70 µA to a 50 kΩ load, with a peak voltage conversion ratio of 5 and a power conversion efficiency of 17.5%.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan14060118

Authors: Francesco Di Rienzo Giustino Claudio Miglionico Pietro Ducange Francesco Marcelloni Nicolò Salti Carlo Vallati

Industry 4.0 advanced technologies are increasingly used to monitor workers and reduce accident risks to ensure workplace safety. In this paper, we present an on-premise, rule-based safety management system that exploits the fusion of data from an Ultra-Wideband (UWB) Real-Time Locating System (RTLS) and AI-based video analytics to enforce context-aware safety policies. Data fusion from heterogeneous sources is exploited to broaden the set of safety rules that can be enforced and to improve resiliency. Unlike prior work that addresses PPE detection or indoor localization in isolation, the proposed system integrates an UWB-based RTLS with AI-based PPE detection through a rule-based aggregation engine, enabling context-aware safety policies that neither technology can enforce alone. In order to demonstrate the feasibility of the proposed approach and showcase its potential, a proof-of-concept implementation is developed. The implementation is exploited to validate the system, showing sufficient capabilities to process video streams on edge devices and track workers’ positions with sufficient accuracy using a commercial solution. The efficacy of the system is assessed through a set of seven safety rules implemented in a controlled laboratory scenario, showing that the proposed approach enhances situational awareness and robustness, compared with a single-source approach. An extended validation is further employed to confirm practical reliability under more challenging operational conditions, including varying camera perspectives, diverse worker clothing, and real-world outdoor conditions.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan14060116

Authors: Filomena Pietrantonio Alessandro Signorini Anna Rosa Bussi Francesco Rosiello Fabio Vinci Michela Delli Castelli Matteo Pascucci Elena Alessi Luca Moriconi Antonio Vinci Andrea Moriconi Roberto D’Amico

Background: Wireless Vital Parameter Continuous Monitoring (WVPCM) allows the continuous tracking of patient physiological parameters, facilitating the earlier detection of clinical deterioration, especially in low-intensity care settings. The aim of this study is to evaluate the effectiveness of using WVPCM compared to the usual monitoring of critically ill patients hospitalized in Internal Medicine wards. An investigation of the attitude of health professionals towards the use of new technologies in daily practice to improve patient management was also carried out. Methods: The LIght Monitor Study (LIMS) is a prospective, open-label, randomized, multi-center pilot trial comparing WVPCM and conventional nurse monitoring during the first 72 h of hospitalization. A central randomization unit used computer-generated tables to allocate patients to two different types of monitoring. The main outcome was the occurrence of major complications. The study planned to enroll 296 critically ill patients with a Modified Early Warning Score (MEWS) ≥ 3 and/or National Early Warning Score (NEWS) ≥ 5 across two Internal Medicine (IM) Units in Italy. The investigation of the attitude of nurses towards the use of WVPCM was carried out by using a questionnaire and a qualitative survey. Results: Due to the COVID-19 outbreak, the study was interrupted early and only 135 patients (WVPCM = 68; standard care = 67) were randomized. One patient in the control group was excluded from analysis because of drop-out, leaving 134 patients for intention to treat analysis. No statistically significant differences between standard care and WVPCM were observed in terms of major complications (37.5%, vs. 31.2% p = 0.475), in-hospital mortality (17.5% vs. 11.1%, p = 0.309), and median hospital length of stay (9 vs. 10 days, p = 0.463). WVPCM decreased nursing workload compared to the control, as the average time spent by nurses on the detection of vital signs per patient was 0 min per patient per day compared to 24.4 min (p < 0.001) observed in the control group. Twenty-two percent of patients in the WVPCM group (15/68) experienced discomfort with the device, resulting in its removal. The investigation of nurses involved 16 out of 18 people participating in the study. Opinions on the wireless device for patient monitoring were particularly favorable; most of them considered remote monitoring clearly superior to traditional in-person visits and easy to use after a brief practice period. All participants recognized the safety benefits of the system. Conclusions: The reduced sample size of this pilot study does not allow us to draw any conclusions on the superiority of WVPCM compared to standard care in terms of clinical outcomes. However, we observed a positive trend in the reduction of major complications.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan14060115

Authors: Salah Fakhoury Karim Ismail

Traffic safety analysis has traditionally relied on historical road collision data. However, this approach has many limitations due to well-known challenges with the availability and quality of collision data. Moreover, collecting sufficient crash data to develop statistical models for traffic safety analysis is only possible after the societal damage due to collisions has been sustained. Those problems are more likely when studying pedestrian safety. To address these constraints, researchers utilize traffic conflict indicators to identify the severity of conflicts and develop strategies to enhance road safety. This study evaluates Ultra-Wideband (UWB) technology for estimating the post-encroachment time (PET) indicator, a commonly used measure in pedestrian safety. Indoor experiments were conducted to explore potential multipath issues commonly encountered in wireless-based localization systems. The time-division multiple access (TDMA) scheme was utilized by assigning 20 ms time slots for stable communication between a tag and an anchor. To address the different clocks in UWB anchors and tags, the master–slave technique was employed for time synchronization between the devices. The experiments also examined the storage of UWB measurements using a cloud-based global clock for time synchronization. The study found that the mean absolute error (MAE) in PET is 4.92 s under interference conditions and 0.148 s with the TDMA technique between the ground truth and the UWB measurements. The findings offer valuable insights for future studies aimed at enhancing UWB accuracy.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan14060114

Authors: David Kalina Ryan O’Neill Elisa Pevere Raul Fernandez Rojas

This paper presents the design, development, and field testing of an Operational Fire Management System (OFMS) aimed at enhancing situational awareness and improving the safety and efficiency of firefighting operations. The system integrates real-time intelligence and remote monitoring to provide emergency management personnel and first responders with accurate information on vehicle location, communication status, and water level monitoring. Developed in collaboration with the Australian Capital Territory Rural Fire Service (ACT RFS), the OFMS prototype encompasses three core subsystems: the Monitoring and Environmental Sensing Subsystem (MESS), the Communication and Vital Monitoring Subsystem (CVMS), and the Command-and-Control Interface Subsystem (CCIS). MESS introduces a tilt-compensated ultrasonic algorithm for accurate water level estimation in moving fire trucks, CVMS leverages an open-source smartwatch with LoRa communication for real-time physiological tracking, and CCIS offers a cloud-based interface for live visualisation and coordination. Together, these subsystems form a practical and scalable framework for supporting frontline operations, particularly in rural firefighting contexts where vehicles are required to operate off-road and deliver large volumes of water to isolated locations. By providing real-time visibility of resource availability and crew status, the system strengthens operational coordination and decision-making in environments where connectivity is often limited. This paper discusses the design and implementation of the prototype, highlights key performance results, and outlines opportunities for future development, including improved environmental resilience, expanded sensor integration, and multi-agency interoperability. The findings confirm that the OFMS represents a novel and field-ready approach to fireground management, empowering firefighting teams to respond more effectively to emergencies and better protect lives, property, and the environment.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan14060113

Authors: Arash Mohammadzadeh Gonabadi Nathaniel H. Hunt Farahnaz Fallahtafti

Exoskeletons offer promising solutions for enhancing human mobility; however, personalizing assistance parameters to optimize physiological outcomes remains challenging. Human-in-the-loop (HIL) optimization has emerged as an effective strategy for tailoring device control, often using electromyography (EMG) as a real-time proxy for metabolic cost. This study simulates HIL optimization using surrogate models built from the average root mean square of the muscles’ activations (EMG-RMS) derived from treadmill walking trials with a robotic waist tether. Nine surrogate models were evaluated for prediction accuracy, including gradient boosting (GB), random forest, support vector regression, and Gaussian process variants. Seven global optimization algorithms were compared based on convergence time, EMG-RMS at optimum, and efficiency metrics. GB achieved the highest predictive accuracy (1.57% RAEP). Among optimizers, the gravitational search algorithm (GSA) produced the lowest EMG-RMS value (0.17 normalized units) and the fastest convergence (0.32 s), while particle swarm optimization (PSO) achieved 0.36 EMG-RMS in 1.61 s. These findings demonstrate the value of EMG-based simulation frameworks in guiding algorithm selection for HIL optimization, ultimately reducing the experimental burden in developing personalized exoskeleton assistance strategies.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan14060112

Authors: Suvish Mehrdad Ghamari Senthilarasu Sundaram

The global increase in dementia cases, which is predicted to exceed 152 million by 2050, poses substantial challenges to healthcare systems and caregiving structures. Concurrently, the expansion of mobile health (mHealth) technologies offers scalable, cost-effective opportunities for dementia care. This study systematically reviews 100 publicly available dementia-related mobile applications on the Apple App Store (iOS) and the Google Play Store (Android), categorised using the Mobile App Rating Scale (MARS), as well as the targeted end-users, Internet of Things (IoT) integration, data protection, and cost burden. Applications were evaluated for their utility in cognitive training, memory support, carer education, clinical decision-making, and emotional well-being. Findings indicate a predominance of carer resources and support tools, while clinically integrated platforms, cognitive assessments, and adaptive memory aids remain underrepresented. Most apps lack empirical validation, inclusive design, and integration with electronic health records, raising ethical concerns around data privacy, transparency, and informed consent. In parallel, the study identifies promising pathways for energy-optimised IoT systems, Artificial Intelligence (AI), and Ambient Assisted Living (AAL) technologies in fostering dementia-friendly, sustainable environments. Key gaps include limited use of low-power wearables, energy-efficient sensors, and smart infrastructure tailored to therapeutic needs. Application domains such as cognitive training (19 apps) and carer resources (28 apps) show early potential, while emerging innovations in neuroadaptive architecture and emotional computing remain underexplored. The findings emphasize the need for co-designed, evidence-based digital solutions that align with the evolving needs of people with dementia, carers, and clinicians. Future innovations must integrate sustainability principles, promote interoperability, and support global aging populations through ecologically responsible, person-centred dementia care ecosystems.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan14060111

Authors: Josip Lorincz Krešimir Levarda Mario Čagalj Amar Kukuruzović

This paper investigates how key Long-Range (LoRa) sensor network transmission parameters and the number and material composition of physical obstacles on the signal propagation path impact wireless signal transmission quality in indoor propagation environments. A dedicated test platform was developed to assess how different combinations of the LoRa transmission parameters, which include spreading factor, transmit power, transmit duty cycle, message payload size, and the quantity and material composition of physical obstacles, with the signal propagation path length influence critical signal quality indicators, specifically the signal-to-noise ratio (SNR) and the received signal strength indicator (RSSI). The developed experimental test platform was implemented for a real-world indoor LoRa network composed of LoRa end devices (DVs) and gateways (GWs), utilizing technologies such as Node-RED for service orchestration, InfluxDB for data storage, The Things Network (TTN) for LoRa wide-area network connectivity, and Grafana for data visualization. The results of the performed analyses reveal how different combinations of LoRa transmission parameters, specifically the number and material composition of physical obstacles encountered during signal transmission among the LoRa end DVs and GWs, affect wireless signal quality indicators, namely RSSI and SNR, in indoor propagation environments of LoRa sensor networks. The obtained findings contribute to the optimization of LoRa transmission parameter selection for reliable and efficient signal transmission in LoRa indoor sensor network deployment, such as in urban environments with obstacles of varying structural composition and density encountered on the communication paths of different lengths between the LoRa end DVs and GWs.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan14060110

Authors: William O’Brien Adam Dooley Mihai Penica Sean McGrath Eoin O’Connell

Wireless connectivity plays a pivotal role in enabling real-time telemetry, sensor feedback, and autonomous navigation within Industry 4.0 environments. This paper presents a ROS 2-based mobile robotic platform designed to perform real-time network diagnostics across both private 5G and Wi-Fi technologies in a live smart manufacturing testbed. The system integrates high-frequency telemetry acquisition with spatial localization, multi-protocol connection analysis, and detailed performance monitoring. Metrics such as latency, packet loss, bandwidth, and IIoT (Industrial Internet of Things) data stream health are continuously logged and analysed. Telemetry is captured during motion and synchronously stored in an InfluxDB time-series database, enabling live visualization through Grafana dashboards. A key feature of the platform is its dual-path transmission architecture, which provides communication redundancy and allows side-by-side evaluation of network behaviour under identical physical conditions. Experimental trials demonstrate the platform’s ability to detect roaming events, characterize packet loss, and reveal latency differences between Wi-Fi and 5G networks. Results show that Wi-Fi suffered from roaming-induced instability and packet loss, whereas 5G maintained stable and uninterrupted connectivity throughout the test area. This work introduces a modular, extensible framework for mobile network evaluation in industrial settings and provides practical insights for infrastructure tuning, protocol selection, and wireless fault detection.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan14060109

Authors: Akeem Abimbola Raji Thomas O. Olwal

The proliferation of Internet of Things (IoT) devices due to remarkable developments in mobile connectivity has caused a tremendous increase in the consumption of broadband spectrums in fifth generation (5G) mobile access. In order to secure the continued growth of IoT, there is a need for efficient management of communication resources in the 5G wireless access. Cognitive radio (CR) is advanced to maximally utilize bandwidth spectrums in the radio communication network. The integration of CR into IoT networks is a promising technology that is aimed at productive utilization of the spectrum, with a view to making more spectral bands available to IoT devices for communication. An important function of CR is spectrum sensing (SS), which enables maximum utilization of the spectrum in the radio networks. Existing SS techniques demonstrate poor performance in noisy channel states and are not immune from the dynamic effects of wireless channels. This article presents a comprehensive review of various approaches commonly used for SS. Furthermore, multi-agent deep reinforcement learning (MADRL) is proposed for enhancing the accuracy of spectrum detection in erratic wireless channels. Finally, we highlight challenges that currently exist in SS in CRIoT networks and further state future research directions in this regard.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan14060108

Authors: Grigorios Kotsakis Christos Papaioannou Thanassis Souflas Dimitris Tsolkas Alex Kakyris Panagiotis Gounas Panagiotis Stavropoulos

Cloud monitoring systems combine physical sensors with cloud computing capabilities. Modern manufacturing techniques and smart factories under Industry 4.0 and Industry 5.0 call for the integration of monitoring systems as part of the broader digitization process. Digitization typically occurs by integrating external sensors onto existing legacy machines. Data obtained can be utilized in digital twins, simulations, machine learning models, and Industrial Internet Of Things (IIoT) applications. The adaptation of these new technologies usually stalls due to the reluctance of end users to make modifications to already existing equipment, the legacy equipment that is in use and does not provide the information needed, and the substantial costs of integrating new measuring systems that typically require additional IT infrastructure. Having identified the need for easily scalable affordable measurement systems, new disseminated systems that utilize cloud solutions and use 5G as an enabler for real-time communication are on the rise. This publication proposes a methodology, and tests and demonstrates a relevant manufacturing use case for integrating a non-invasive-to-IT-infrastructure, cloud-based and artificial intelligence-powered monitoring system focused on high performance applications. The proposed methodology has been evaluated in a real industrial environment.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan14060107

Authors: Jeremiah O. Abolade Dominic B. O. Konditi Pradeep Kumar Grace Olaleru

A compact bio-inspired terahertz wideband antenna is presented in this work. The proposed antenna is based on Viburnum tinus leaf shape, a defective ground plane, a folded-ring slot, and parasitic elements. The footprint of the proposed antenna is 0.46 × 0.18 λg2 at 0.18 THz. A bandwidth of 0.536 THz (0.18–0.72 THz) is achieved with a band notch at 0.35 THz (0.3–0.36 THz). The proposed antenna has a peak gain of 5 dBi and the stable radiation patterns. The proposed antenna is validated through a finite difference time domain simulator and the equivalent circuit analysis. The results from show a good correlation. Also, an extensive parametric analysis is performed, and the comparative analysis of the proposed antenna with the existing antennas shows that the proposed antenna is compact with competitive performance metrics such as gain, efficiency, and notch-band characteristics. Therefore, the proposed antenna (hereafter referred to as VTB-A) is a promising candidate for future terahertz wireless communications (5G, 6G, and beyond) and terahertz imaging.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan14060106

Authors: Azhar A. Hamdi Asmaa A. Eyssa Mahmoud I. Abdalla Mohammed ElAffendi Ali Abdullah S. AlQahtani Abdelhamied A. Ateya Rania A. Elsayed

Ensuring the security and privacy of confidential data during transmission is a critical challenge, necessitating advanced techniques to protect against unwarranted disclosures. Steganography, a concealment technique, enables secret information to be embedded in seemingly harmless carriers such as images, audio, and video. This work proposes two secure audio steganography models based on the least significant bit (LSB) and discrete wavelet transform (DWT) techniques for concealing different types of multimedia data (i.e., text, image, and audio) in audio files, representing an enhancement of current research that tends to focus on embedding a single type of multimedia data. The first model (secured model (1)) focuses on high embedding capacity, while the second model (secured model (2)) focuses on improved security. The performance of the two proposed secure models was tested under various conditions. The models’ robustness was greatly enhanced using convolutional encoding with binary phase shift keying (BPSK). Experimental results indicated that the correlation coefficient (Cr) of the extracted secret audio in secured model (1) increased by 18.88% and by 16.18% in secured model (2) compared to existing methods. In addition, the Cr of the extracted secret image in secured model (1) was improved by 0.1% compared to existing methods. The peak signal-to-noise ratio (PSNR) of the steganography audio of secured model (1) was improved by 49.95% and 14.44% compared to secured model (2) and previous work, respectively. Furthermore, both models were evaluated in an orthogonal frequency division multiplexing (OFDM) system over various wireless channels, i.e., Additive White Gaussian Noise (AWGN), fading, and SUI-6 channels. In order to enhance the system performance, OFDM was combined with differential phase shift keying (DPSK) modulation and convolutional coding. The results demonstrate that secured model (1) is highly immune to noise generated by wireless channels and is the optimum technique for secure audio steganography on noisy communication channels.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan14060105

Authors: Saket Sarkar Redwan Alqasemi

The integration of neural interfaces with assistive robotics has transformed the field of prosthetics, rehabilitation, and brain–computer interfaces (BCIs). From brain-controlled wheelchairs to Artificial Intelligence (AI)-synchronized robotic arms, the innovations offer autonomy and improved quality of life for people with mobility disorders. This article discusses recent trends in brain–computer interfaces and their application in robotic assistive devices, such as wheelchair-mounted arms, drone control systems, and robotic limbs for activities of daily living (ADLs). It also discusses the incorporation of AI systems, including ChatGPT-4, into BCIs, with an emphasis on new innovations in shared autonomy, cognitive assistance, and ethical considerations.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan14060104

Authors: Giovanni Cicceri Fabrizio De Vita

The rise of the Internet of Things (IoT) has revolutionized the way industrial, structural, and environmental systems are monitored and maintained [...]

Journal of Sensor and Actuator Networks doi: 10.3390/jsan14050103

Authors: Nasreddine Makni Riccardo Collu Massimo Barbaro

Monitoring plant water status is vital for optimizing irrigation in precision agriculture. This study explores the use of two simple, affordable, and non-invasive sensor systems, electrical impedance spectroscopy (EIS) and infrared (IR) spectroscopy, to assess plant water status directly from leaf tissues. This approach is well-suited for the realization of large networks of distributed sensors wirelessly connected to a central hub. An outdoor experiment was conducted over two phases of 20 day-experiment involving six Hydrangea macrophylla plants subjected to two irrigation treatments: a control group (well-irrigated) and a test group (poorly irrigated) designed to induce water stress. The standard relative water content (RWC) method validated the treatment effects on the plants, and both EIS and IR sensors effectively distinguished between the two groups. Impedance-derived parameters, particularly the normalized intracellular resistance (R0) and the cell membrane capacitance (C0), exhibited statistically significant differences between the treatments. In addition, the IR measurements showed moderate correlations with RWC, with determination coefficients of R2 = 0.56 and R2 = 0.51 for first and second phases of the experiment, respectively. Despite some limitations concerning the electrode–leaf conformity and external sunlight interference, the results point to the advantages of these methods for real-time plant monitoring and decision-making in smart irrigation systems.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan14050102

Authors: Elia Henrichs Dana Jox Pia Schweizer Christian Krupitzer

Monitoring systems are essential in many fields, such as food production, storage, and supply, to collect information about applications or their environments to enable decision-making. However, these systems generate massive amounts of data that require substantial processing. To improve data analysis efficiency and reduce data collectors’ energy demand, adaptive monitoring is a promising approach to reduce the gathered data while ensuring the monitoring of critical events. Adaptive monitoring is a system’s ability to adjust its monitoring activity during runtime in response to internal and external changes. This work investigates the application of adaptive monitoring—especially, the adaptation of the sensor sampling rate—in dynamic and unstable environments. This work evaluates 11 distinct approaches, based on threshold determination, statistical analysis techniques, and optimization methods, encompassing 33 customized implementations, regarding their data reduction extent and identification of critical events. Furthermore, analyses of Shannon’s entropy and the oscillation behavior allow for estimating the efficiency of the adaptation algorithms. The results demonstrate the applicability of adaptive monitoring in food storage environments, such as cold storage rooms and transportation containers, but also reveal differences in the approaches’ performance. Generally, some approaches achieve high observation accuracies while significantly reducing the data collected by adapting efficiently.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan14050101

Authors: Zitong Shao Pengfei Zhang Xiaofang Wang Pengfei Lu

Molecular communication (MC) has emerged as a promising paradigm for nanoscale information exchange in Internet of Bio-Nano Things (IoBNT) environments, offering intrinsic biocompatibility and potential for real-time in vivo monitoring. This study proposes a cascaded MC channel framework for vascular stenosis detection, which integrates non-Newtonian blood rheology, bell-shaped constriction geometry, and adsorption–desorption dynamics. Path delay and path loss are introduced as quantitative metrics to characterize how structural narrowing and molecular interactions jointly affect signal propagation. On this basis, a peak response time-based delay inversion method is developed to estimate both the location and severity of stenosis. COMSOL 6.2 simulations demonstrate high spatial resolution and resilience to measurement noise across diverse vascular configurations. By linking nanoscale transport dynamics with system-level detection, the approach establishes a tractable pathway for the early identification of vascular anomalies. Beyond theoretical modeling, the framework underscores the translational potential of MC-based diagnostics. It provides a foundation for non-invasive vascular health monitoring in IoT-enabled biomedical systems with direct relevance to continuous screening and preventive cardiovascular care. Future in vitro and in vivo studies will be essential to validate feasibility and support integration with implantable or wearable biosensing devices, enabling real-time, personalized health management.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan14050100

Authors: Nayera Youness Ahmad Mostafa Mohamed A. Sobh Ayman M. Bahaa Khaled Nagaty

Ensuring secure and reliable communication in Vehicular Ad hoc Networks (VANETs) is critical for safe transportation systems. This paper presents Vehicular Misbehavior Network (VeMisNet), a deep learning framework for detecting misbehaving vehicles, with primary contributions in systematic feature engineering and scalability analysis. VeMisNet introduces domain-informed spatiotemporal features—including DSRC neighborhood density, inter-message timing patterns, and communication frequency analysis—derived from the publicly available VeReMi Extension Dataset. The framework evaluates Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Bidirectional LSTM architectures across dataset scales from 100 K to 2 M samples, encompassing all 20 attack categories. To address severe class imbalance (59.6% legitimate vehicles), VeMisNet applies SMOTE post train–test split, preventing data leakage while enabling balanced evaluation. Bidirectional LSTM with engineered features achieves 99.81% accuracy and F1-score on 500 K samples, with remarkable scalability maintaining >99.5% accuracy at 2 M samples. Critical metrics include 0.19% missed attack rates, under 0.05% false alarms, and 41.76 ms inference latency. The study acknowledges important limitations, including reliance on simulated data, single-split evaluation, and potential adversarial vulnerability. Domain-informed feature engineering provides 27.5% relative improvement over dimensionality reduction and 22-fold better scalability than basic features. These results establish new VANET misbehavior detection benchmarks while providing honest assessment of deployment readiness and research constraints.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan14050099

Authors: Damilola D. Olatinwo Herman C. Myburgh Allan De Freitas Adnan M. Abu-Mahfouz

Smart crop technologies offer promising solutions for enhancing agricultural productivity and sustainability, particularly in the face of global challenges such as resource scarcity and climate variability. However, their deployment in infrastructure-limited regions, especially across Africa, faces persistent barriers, including unreliable power supply, intermittent internet connectivity, and limited access to technical expertise. This study presents a PRISMA-guided systematic review of literature published between 2015 and 2025, sourced from the Scopus database including indexed content from ScienceDirect and IEEE Xplore. It focuses on key technological components including multimodal sensing, data fusion, IoT resource management, edge-cloud integration, and adaptive network design. The analysis of these references reveals a clear trend of increasing research volume and a major shift in focus from foundational unimodal sensing and cloud computing to more complex solutions involving machine learning post-2019. This review identifies critical gaps in existing research, particularly the lack of integrated frameworks for effective multimodal sensing, data fusion, and real-time decision support in low-resource agricultural contexts. To address this, we categorize multimodal sensing approaches and then provide a structured taxonomy of multimodal data fusion approaches for real-time monitoring and decision support. The review also evaluates the role of IoT virtualization as a pathway to scalable, adaptive sensing systems, and analyzes strategies for overcoming infrastructure constraints. This study contributes a comprehensive overview of smart crop technologies suited to infrastructure-limited agricultural contexts and offers strategic recommendations for deploying resilient smart agriculture solutions under connectivity and power constraints. These findings provide actionable insights for researchers, technologists, and policymakers aiming to develop sustainable and context-aware agricultural innovations in underserved regions.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan14050098

Authors: Siripan Rattanaamporn Asanka Perera Andy Nguyen Thanh Binh Ngo Javaan Chahl

Situation awareness is essential for ensuring safety in hazardous environments, where timely and accurate information is critical for decision-making. Unmanned Aerial Vehicles (UAVs) have emerged as valuable tools in enhancing situation awareness by providing real-time data and monitoring capabilities in high-risk areas. This study explores the integration of advanced technologies, focusing on imaging and sensor technologies such as thermal, spectral, and multispectral cameras, deployed in critical zones. By merging these technologies into UAV platforms, responders gain access to essential real-time information while reducing human exposure to hazardous conditions. This study presents case studies and practical applications, highlighting the effectiveness of these technologies in a range of hazardous situations.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan14050097

Authors: Tharuka Govinda Waduge Yang Yang Boon-Chong Seet

Underwater wireless communication (UWC) is an emerging technology crucial for automating marine industries, such as offshore aquaculture and energy production, and military applications. It is a key part of the 6G vision of creating a hyperconnected world for extending connectivity to the underwater environment. Of the three main practicable UWC technologies (acoustic, optical, and radiofrequency), acoustic methods are best for far-reaching links, while optical is best for high-bandwidth communication. Recently, utilizing reconfigurable intelligent surfaces (RISs) has become a hot topic in terrestrial applications, underscoring significant benefits for extending coverage, providing connectivity to blind spots, wireless power transmission, and more. However, the potential for further research works in underwater RIS is vast. Here, for the first time, we conduct an extensive survey of state-of-the-art of RIS and metasurfaces with a focus on underwater applications. Within a holistic perspective, this survey systematically evaluates acoustic, optical, and hybrid RIS, showing that environment-aware channel switching and joint communication architectures could deliver holistic gains over single-domain RIS in the distance–bandwidth trade-off, congestion mitigation, security, and energy efficiency. Additional focus is placed on the current challenges from research and realization perspectives. We discuss recent advances and suggest design considerations for coupling hybrid RIS with optical energy and piezoelectric acoustic energy harvesting, which along with distributed relaying, could realize self-sustainable underwater networks that are highly reliable, long-range, and high throughput. The most impactful future directions seem to be in applying RIS for enhancing underwater links in inhomogeneous environments and overcoming time-varying effects, realizing RIS hardware suitable for the underwater conditions, and achieving simultaneous transmission and reflection (STAR-RIS), and, particularly, in optical links—integrating the latest developments in metasurfaces.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan14050096

Authors: Kuburat Oyeranti Adefemi Murimo Bethel Mutanga Oyeniyi Akeem Alimi

Internet of Things (IoT) networks are constantly exposed to various security challenges and vulnerabilities, including manipulative data injections and cyberattacks. Traditional security measures are often inadequate, overburdened, and unreliable in adapting to the heterogeneous yet diverse nature of IoT networks. This emphasizes the need for intelligent and effective methodologies. In recent times, deep learning models have been extensively used to monitor and detect intrusions in complex applications. The models can effectively learn and understand the dynamic characteristics of voluminous IoT datasets to prompt efficient decision-making predictions. This study proposes a hybrid Convolutional Neural Network and Gated Recurrent Unit (CNN-GRU) algorithm to enhance intrusion detection in IoT environments. The proposed CNN-GRU model is validated using two benchmark datasets: the IoTID20 and BoT-IoT intrusion detection datasets. The proposed model incorporates an effective technique to handle the class imbalance issues that are peculiar to voluminous datasets. The results demonstrate superior accuracy, precision, recall, F1-score, and area under the curve, with a reduced false positive rate compared to similar models in the literature. Specifically, the proposed CNN–GRU achieved up to 99.83% and 99.01% accuracy, surpassing baseline models by a margin of 2–3% across both datasets. These findings highlight the model’s potential for real-time cybersecurity applications in IoT networks and general industrial control systems.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan14050095

Authors: Peng Lin Jinzhao She Xiang Chen

In complex testing scenarios of large-scale information systems, communication networks, and the Internet of Things, exhaustive testing is always prohibitively expensive and time-consuming. T-way combinatorial testing has emerged as a cost-effective solution. To address the problem of generating test suites for t-way combinatorial testing, a Logical Combination Index Table (LCIT) is proposed. Utilizing the LCIT, the t-way combinatorial coverage model (t-wCCM) is constructed to guide the test case generation process. Multi-start Construction Procedure (MsCP) algorithm is employed to generate an initial solution set, and then local optimization is performed using a low-complexity Balanced Local Search (BLS) algorithm. Further, Evolutionary Path Relinking combined with the BLS (EvPR + BLS) algorithm is proposed to accelerate the convergence process. Experiments show that the proposed Refined Evolutionary Heuristic (REH) algorithm performs best on 50% of the classic test instances, and performs superior to the average on 66% of the test instances, with a relative improvement in the maximum computation time of approximately 33.33%.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan14050094

Authors: Tingting Cao Fan Yang Chensiyu Fan Ru Han Xing Yang Lei Shu

Three-dimensional (3D) wireless sensor networks (WSNs) are gaining increasing significance in applications across complex environments, including underwater monitoring, mountainous terrains, and smart cities. Compared to two-dimensional (2D) WSNs, 3D WSNs introduce unique challenges in coverage, connectivity, map construction, and blind area detection. This paper provides a comprehensive survey of node deployment strategies in 3D WSNs. We summarize several key design aspects: sensing models, occlusion detection, coverage and connectivity, sensor mobility, signal and protocol effects, and simulation map construction. Deployment algorithms are categorized into six main types: classical algorithms, computational geometry algorithms, virtual force algorithms, evolutionary algorithms, swarm intelligence algorithms, and approximation algorithms. For each category, we review representative works, analyze their design principles, and evaluate their advantages and limitations. Comparative summaries are included to facilitate algorithm selection based on specific deployment requirements. Recent advancements in these strategies have led to significant improvements in network performance, with some algorithms achieving up to 12.5% lower cost and 30% higher coverage compared to earlier methods, and even reaching 100% coverage in certain cases. Thus, this survey aims to present the current research status and highlight practical improvements, offering a reference for understanding existing approaches and selecting appropriate algorithms for diverse deployment scenarios.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan14050093

Authors: Kenia Elizabeth Sabando-Bravo Marlon Navia Jorge Luis Zambrano-Martinez

In the present work, a sensor network design for monitoring carbon dioxide (CO2) pollution in Portoviejo City, Ecuador, is evaluated through a methodology that combines simulation and physical implementation. This methodology involves the development and evaluation of two scenarios: an initial scenario (A), developed through both physical implementation and simulation, and another simulation scenario (B). Both simulated scenarios are created using CupCarbon version 6.51 software. In these scenarios, the functionality of Wireless Sensor Networks (WSNs) is analyzed by implementing the LoRaWAN communication technology. Furthermore, the MQ-135 sensor is used to obtaining data on the PPM of (CO2) in order to examine the areas that concentrate the most significant amount of this atmospheric pollutant. The proposed networks are evaluated using the packet loss metric during data transmission. After implementation, analysis, and respective evaluation, it can be concluded that the network simulated in Scenario B is suitable for monitoring (CO2) and other pollutants that can be analyzed within the urban environment.

Journal of Sensor and Actuator Networks doi: 10.3390/jsan14050092

Authors: Riccardo Collu Cinzia Salis Elena Ferrazzano Massimo Barbaro

Implantable medical devices present several technological challenges, one of the most critical being how to provide power supply and communication capabilities to a device hermetically sealed within the body. Using a battery as a power source represents a potential harm for the individual’s health because of possible toxic chemical release or overheating, and it requires periodic surgery for replacement. This paper proposes a batteryless implantable device powered by an inductive link and equipped with bidirectional wireless communication channels. The device, designed in a 180 nm CMOS process, is based on two different pairs of mutually coupled inductors that provide, respectively, power and a low-bitrate bidirectional communication link and a separate, high-bitrate, one-directional upstream connection. The main link is based on a 13.56 MHz carrier and allows power transmission and a half-duplex two-way communication at 106 kbps (downlink) and 30 kbps (uplink). The secondary link is based on a 27 MHz carrier, which provides one-way communication at 2.25 Mbps only in uplink. The low-bitrate links are needed to send commands and monitor the implanted system, while the high-bitrate link is required to receive a continuous stream of information from the implanted sensing devices. The microchip acts as a hub for power and data wireless transmission capable of managing up to four different neural recording and stimulation front ends, making the device employable in a complex, distributed, bidirectional neural prosthetic system.