IoT doi: 10.3390/iot7040087

Authors: Michail Alexandros Kourtis Achilleas Economopoulos George Xilouris Evangelos Markakis Ricard Vilalta

The proliferation of Internet of Things (IoT) devices operating in swarm-like formations—from autonomous device fleets to federated service networks—demands a computing continuum that spans edge nodes, fog gateways, and cloud back-ends. Service meshes such as Istio provide transparent traffic management, observability, and policy enforcement for the microservice fabrics that underpin these continuums, yet their scalability behaviour under diverse coordination patterns and increasing load intensity remains poorly characterised. This paper introduces a two-axis taxonomy for benchmarking service-mesh scalability in IoT-to-cloud microservice continuums: Axis A captures four scaling tiers (Baseline, Moderate, High, Extreme) derived from offered load and concurrency, while Axis B is measured by the coordination-amplification factor φ, the number of service-to-service calls that one request triggers, and groups the scenarios into federated patterns, in which services call only distinct downstream services, and peer-to-peer patterns, in which services also call peer instances of themselves. We instantiate the taxonomy across six representative IoT scenarios, each exercised through multi-phase Fortio load campaigns over an Istio-meshed Kubernetes cluster. Analysing 51 benchmark runs, we report percentile latency distributions (P50, P90, P99), load fidelity, and throughput–tail coupling. Because every scenario is driven with fixed-size payloads, per-request application processing is held constant, which lets us separate the effect of coordination structure from that of application weight. At matched application weight and offered load, peer-to-peer coordination adds only a modest tail premium over federated rollout (a factor of ≈1.2–1.8 at 100–200 RPS); the severe effects—up to an order-of-magnitude P99 growth from a scenario’s own baseline to saturation, and achieved throughput collapsing to roughly half the requested rate—emerge specifically for heavy-compute peer-exchange workloads driven toward saturation. This interaction of load, coordination structure, and application weight is what the two-axis grid is designed to expose, and negligible-compute acknowledgement endpoints additionally provide a direct per-hop mesh-overhead measurement. We deliberately scope the study to the cloud-side segment of the continuum—the layer on which the service mesh runs—and within it to the single-node data plane, where mesh overhead can be measured in isolation from cross-node network variability; device and edge tiers enter only as offered load, and no claim is made about inter-tier transport. The A×B grid exposes otherwise hidden interaction effects between coordination topology and scale, providing actionable design guidance for service-mesh capacity planning and auto-scaling in IoT microservice deployments.

IoT doi: 10.3390/iot7040086

Authors: Wenchao Yang Zhiguo Hu Xinyang Wang Run Wang Rongchang Li Guofu Luo Yuyan Zhang Yuanji Liang

The accurate prediction of the power of High-Pressure Grinding Rolls (HPGR) is considered essential for evaluating equipment operating conditions and optimizing energy consumption. Existing power prediction methods, however, are considered to have notable limitations: mechanistic models exhibit limited adaptability under dynamic conditions, and purely data-driven models lack physical logic constraints, often resulting in physically inconsistent predictions during extreme conditions such as shutdowns. To address these problems, proposed in this paper is a power prediction method that combines Long Short-Term Memory (LSTM) networks with Physics-Informed Neural Networks (PINN) under a sliding-window rolling prediction framework, termed LSTM-PINN. This method takes HPGR as the research object and integrates the LSTM-PINN framework with the physical mechanism of high-pressure roller mills for power prediction. Specifically, based on the physical operating mechanism of HPGR, four constraint relationships-monotonicity, linear prior, thermodynamic, and energy conservation-are introduced and embedded into the loss function of LSTM-PINN. While LSTM-PINN has been applied in other domains, its combination with the HPGR physical mechanism for power prediction has not been previously reported. The LSTM network extracts dynamic temporal features of power evolution, while the four mechanism-driven physical constraints guide the model toward physically consistent predictions. Experiments using actual operational data from a mining company demonstrate that: (1) the pure LSTM model outputs non-zero power during shutdown, whereas LSTM-PINN brings predictions to zero; (2) compared with pure LSTM, LSTM-PINN reduces RMSE by 23.13%, 13.02%, and 11.86%, and reduces MAE by 21.67%, 13.70%, and 10.85% under the single-feature, multi-feature, and all-feature input combinations, respectively. Among all configurations, the multi-feature combination achieves the lowest absolute errors with the smallest variance, representing the optimal trade-off between accuracy and stability. Overall, the proposed method substantially improves prediction accuracy, interpretability, and reliability, providing a trustworthy basis for energy optimization and intelligent control of HPGRs.

IoT doi: 10.3390/iot7040085

Authors: Liana Luminița Boca Elisabeta Mihaela Ciortea Vasile Teodor Dădârlat

This paper proposes a formally analyzable Cloud-IoT architecture for educational environments, connecting learners, teachers, and institutional administrators to a shared cloud infrastructure through an intermediate IoT layer. The architecture is instantiated in a business-language learning scenario, with four cloud subsystems: a Domain Terminology Repository, an Adaptive Learning Engine, a Monitoring and Assessment Module, and an Administrative and Reporting Module. Its dynamic behavior is formally represented using a timed Petri net incorporating state evolution, transition-delay parameters, feedback, and formal behavioral conditions. The complete model is simulated using Visual Object Net++, and the results are analyzed across the Cloud, IoT, and Client subnets to examine state evolution and marking variation. Additional controlled experiments examine the model under timing variations and increased concurrent Client workloads. A reduced Generalized Stochastic Petri Net (GSPN), representing a Cloud-IoT processing and feedback cycle, is subsequently analyzed using GreatSPN. State-space analysis establishes boundedness, absence of dead markings, and reachability of the response state for the reduced model. Steady-state analysis further shows that reducing an exponentially timed transition rate increases the occupancy of its preceding place. The combined approach provides behavioral evidence for the complete architecture and complementary formal and quantitative results for the reduced model, without extending these results to the complete Petri net.

IoT doi: 10.3390/iot7040084

Authors: Abdullah Abbasi Dil Nawaz Hakro Akhtar Hussain Osama Alrahbi Mohammed Izaan Kari Suad Mohammed Al Qassabi Muhammad Hafidz Fazli Bin Md Fauadi

Internet of Things (IoT) malware and intrusions generate network-observable flow patterns, but high benchmark accuracy does not by itself establish transfer to new environments. This study presents Protocol-conditioned Analysis with Behavioral Threat Identification (PA-BTI) as an evidence-bounded framework combining dataset-specific Random Forest/XGBoost detection, protocol-conditioned direction-invariant CorrAUC (dCorrAUC) diagnostics, a River streaming diagnostic, and context-aware alert prioritization. Across the primary evaluations, selected operating points reached 99.77% accuracy with 0.48% false-positive rate (FPR) on ToN-IoT and 99.44% accuracy with 0.08% FPR on a balanced Bot-IoT holdout, whereas the official NSL-KDD split reached 79.55% accuracy and 66.20% attack recall. To address testbed-artifact sensitivity, a new official UNSW-NB15 train/test ablation obtained 87.67% accuracy, 98.59% attack recall, and 25.70% FPR with all features; removing TTL/state variables changed accuracy to 87.22%, and additionally removing the ct_* windowed features changed it to 86.31%, showing no collapse but a persistently high official-split FPR. A new integrated common-flow replay propagated real UNSW detector outputs and training-only protocol evidence through the contextual layer using explicitly synthetic CTI/asset context. On a disjoint 41,166-record evaluation half, calibrated fusion did not improve context-graded nDCG@100 over confidence alone (0.610 versus 0.627), demonstrating component interaction while bounding any claim of prioritization benefit. The River diagnostic also exposed a minority-class failure mode (91.56% accuracy but attack-class F1 = 0.003). PA-BTI is therefore presented as a reproducible, bounded evaluation framework rather than evidence of cross-dataset generalization or robust portability.

IoT doi: 10.3390/iot7040083

Authors: Ashwin Tyagi Dharani Murugan Manimaran Sivasamy Rayappa David Amar Raj Christian Napoli Cristian Randieri

Deepfake manipulation has become increasingly difficult to detect as generative models continue to produce highly realistic facial content. This work presents the Frequency-Aware Lightweight Hybrid Network (FALH-Net Lite), a compact deepfake classification framework that combines spatial- and frequency-domain representations for resource-constrained edge deployment. The proposed framework integrates grayscale intensity with three high-frequency Discrete Wavelet Transform (DWT) sub-bands (LH, HL, and HH) to form a four-channel input, which is processed using an adapted YOLO11n-cls backbone. A Frequency-Aware Squeeze-and-Excitation (FreqSE) module is incorporated to recalibrate channel responses, while Focal Loss is employed during training to address class imbalance. The Celeb-DF-v2 dataset is partitioned at the video level before frame extraction to reduce the risk of near-duplicate leakage between training and validation data. Under the corrected video-level evaluation, FALH-Net Lite achieves an accuracy of 87.7%, with a balanced accuracy of 62.1%, an ROC-AUC of 73.6%, an F1-score of 93.2%, and an MCC of 36.7%. The model contains approximately 1.26 million parameters and requires 0.4885 GFLOPs, providing a compact computational profile for edge inference. Deployment experiments on the NVIDIA Jetson Orin Nano and Raspberry Pi 5 further evaluate the feasibility of executing the proposed classification pipeline on resource-constrained hardware. Cross-dataset validation and broader multi-run statistical evaluation remain directions for future work.

IoT doi: 10.3390/iot7040082

Authors: Habib Idmouida Khalid Minaoui

Severe conditions in hard-to-reach regions, where terrestrial networks are limited, make data backhaul from these areas challenging. In this context, advances in the Space-IoT have created new opportunities for data collection and monitoring using LEO satellites. To address this issue, this paper presents an orbit-aware S&F architecture for data collection from an intelligent ground terminal located in remote areas using a 3U CubeSat orbiting at 500 km altitude in a Sun-synchronous orbit. The designed ground terminal integrates an ESP32 microcontroller and a 433 MHz LoRa module and is enhanced with an embedded satellite pass prediction, Doppler pre-correction, and an adaptive LoRa strategy. The CubeSat utilizes a TOTEM SDR receiver, onboard data buffering, and an S-band downlink with variable coding for throughput enhancement. The orbital model for satellite prediction is validated using Ansys STK software version 12, while UHF and S-band links are evaluated using time-varying link-budget analysis. The adaptive transmission is compared with fixed configurations in terms of usable contact time and data delivered per pass. Results indicate that the proposed system demonstrates the feasibility of a Store-and-Forward mission co-design that combines precise orbit prediction, Doppler compensation, and adaptive transmission for future Space-IoT applications.

IoT doi: 10.3390/iot7030081

Authors: Zijia Hu Qichao Wang Yadong Huang Yanliang Ji

For Internet of Underwater Things (IoUT)−oriented condition monitoring of underwater propulsion systems, continuous visual observations can provide rich information on the spatial distribution and temporal evolution of cavitation, while the direct transmission of complete image sequences may impose a substantial data burden on underwater communication networks. To provide compact and physically interpretable visual monitoring information, this study develops an image-derived multi-domain feature−extraction method for hydrofoil cavitation monitoring. Cavitation image sequences of an original NACA0009 hydrofoil and a hydrofoil with hole−pit structures were analyzed as two experimental configurations exhibiting different cavitation behaviors. Static−background subtraction, RGB−channel−response processing, Canny edge detection, morphological processing, and threshold-based focusing were applied to extract cavitation regions. The normalized cavitation−area time series of the tip leakage vortex (TLV), tip separation vortex (TSV), and six local regions were then constructed from consecutive images and treated as image-derived monitoring signals. Time−domain and spatial features were used to characterize the overall cavitation level and regional distribution, while Fast Fourier Transform (FFT) and Discrete Wavelet Transform (DWT) were further employed to describe spectral fluctuations and multi-scale transient variations. The extracted monitoring features showed clear responses to changes in hydrofoil configuration and operating conditions. Under the baseline condition, the mean TLV and TSV cavitation−area features of the hydrofoil with hole−pit structures were approximately 40.0% and 85.0% lower than those of the original hydrofoil, respectively. Differences were also observed in the regional, frequency−domain, and time−frequency characteristics and remained observable under the two changed operating conditions. These results indicate that continuous cavitation images can be transformed into complementary multi-domain descriptors for characterizing variations in cavitation behavior. The proposed approach therefore provides a potential visual sensing and feature−extraction component for future IoUT-based condition monitoring of underwater propulsion systems, while reducing reliance on the transmission of complete image sequences.

IoT doi: 10.3390/iot7030080

Authors: Luyao Wang Jiahao Xie Hao Hao Huiling Shi

Early-exit deep neural networks (DNNs) can reduce edge-inference latency, but abrupt variations in wireless and computing resources can destabilize split-inference policies. This paper proposes a meta-learning-driven adaptive control framework for joint backbone splitting and early-exit routing in MobileViT. The framework formulates multi-exit splitting as a constrained Markov decision process (CMDP) and introduces splitting-aware multi-dimensional adaptive proximal policy optimization (SMAPPO). SMAPPO combines nonlinear quality-of-service (QoS) penalties with topology-aware action masking, while cross-environment meta-initialization supports edge-local adaptation after resource disturbances. Under the stated simulation assumptions, SMAPPO reached the highest performance-index plateau among six methods in a representative 500-episode stationary trace and achieved the lowest normalized total cost across three latency–energy preference settings. Across ten seeds and nine stationary or disturbed scenarios, online SMAPPO achieved a 77.20% measured accuracy and 22.40 mJ of system energy. With an adaptation horizon of K=14, SMAPPO yielded a post-disturbance mean latency of 37.68 ms, a QoS-violation rate of 2.24%, and an on-time completion rate of 98.69%. These results indicate that combining meta-initialization, nonlinear constraint shaping, and topology-aware action masking improves stationary optimization and disturbance recovery within the controlled simulator.

IoT doi: 10.3390/iot7030079

Authors: Damiano Vincenzo Coppola Miriana Russo Corrado Santoro Federico Fausto Santoro Angelo Spadola Alessio Tudisco

This paper presents a maritime Internet of Things anti-theft architecture based on an ESP32 onboard node, local motion analysis, and LoRa mesh communication. The proposed detection pipeline uses a one-dimensional convolutional autoencoder trained on stationary vessel data and applied to sliding windows of X- and Z-axis angular velocity measurements. During deployment, a calibration phase estimates the reconstruction-error threshold from the local motion profile of the moored vessel, reducing the dependence on labelled theft examples. The communication layer combines an Elliptic Curve Cryptography setup phase with symmetric payload encryption for alert packets, while ESP32 hardware security features are used to protect firmware and stored credentials. The mesh network uses controlled flooding. A Godot-based simulation environment was used to generate stationary and towing scenarios under different wave configurations. In the current simulation campaign, towing windows produced a higher mean reconstruction error than stationary windows. The results support the feasibility of the architecture and also show that event-level alert logic is required to aggregate window-level anomaly scores into reliable alarms.

IoT doi: 10.3390/iot7030078

Authors: Mohammad Alja’afreh Ali Karime Aziz Oukaira

Internet of Things (IoT) botnet detection requires high predictive performance, low client-side resource demands, and limited exposure of raw traffic data. This paper presents a traffic-constrained multi-client split-learning (TC-SL) intrusion-detection system evaluated on BoT-IoT, N-BaIoT, and CIC-IDS2017 using eight clients and one edge server. TC-SL is positioned as a resource-constrained engineering adaptation of standard split learning: it profiles candidate cut layers, selects the highest-performing feasible cut under an explicit communication budget, and trains by exchanging cut-layer activations and gradients while raw records remain local. Centralized, federated, split-learning, and SplitFed-v1 models were compared with matched partitions and optimization budgets. Split learning achieved macro F1 scores of 98.88%, 98.42%, and 97.51% on the three datasets, respectively, with a mean macro F1 of 98.27%, compared with 98.52% for centralized learning, 97.84% for federated learning, and 98.39% for SplitFed. Its pooled ROC-AUC and average precision were 0.985 and 0.980. Within the fixed 10-epoch systems workload, the selected L4 cut logged 95 MB of bidirectional communication per epoch and 0.95 GB in total, versus 405 MB per epoch and 4.05 GB for the configured federated-learning baseline; these byte totals are fixed-workload measurements rather than communication-to-target-accuracy claims. The early split minimized cumulative client energy at 248 J, whereas the middle split minimized total-system energy at 780 J. Across L1–L6, reconstruction NRMSE increased from 0.18 to 0.71, membership-inference AUC decreased from 0.71 to 0.53, label- and attribute-inference success decreased from 0.84 and 0.76 to 0.55 and 0.54, inversion success decreased from 75% to 20%, and poisoning-induced macro-F1 degradation decreased from 6.8 to 3.9 percentage points. The results identify a practical accuracy–communication–energy–privacy operating point for constrained IoT clients.

IoT doi: 10.3390/iot7030077

Authors: Matheus Campos Bruno Augusto Pereira Moisés Freitas Adriano C. Pinto Alison de Oliveira Moraes Renan Sarmento Arthur H. C. Miranda Evandro Nohara

Automated surface defect detection in hot-rolled steel is a prerequisite for real-time quality control, yet most deployed inspection systems operate in isolation from Industrial Internet of Things (IIoT) infrastructure. This paper reports a laboratory-scale proof of concept with two contributions. The first is a segmentation study on the Severstal dataset using a leakage-free, defect-stratified split of 1886 test images. Because a trivial all-background predictor already attains 96.66% pixel accuracy, performance is reported through Dice, IoU, precision, recall, and F1 with 95% confidence intervals. A compact from-scratch U-Net (0.49 M parameters) reaches a Dice of 0.416 at 38.6 ms per image, an ImageNet-pretrained DeepLabV3+ model reaches 0.677 at 46.3 ms and 37 times the parameters, and a classical Otsu baseline reaches 0.060, bracketing an explicit accuracy-versus-footprint design space rather than a single recommended model. The second contribution is architectural: a three-layer IIoT architecture whose messaging layer is empirically characterized on a Raspberry Pi broker over 158,500 messages. A factorial experiment isolates the transport configuration of the broker, rather than that of the publisher, as the determinant of end-to-end latency, yielding a seventeen-fold reduction. The layer sustains 1920 messages per second without loss, and a deliberate broker outage shows that MQTT delivery guarantees are semantic rather than temporal, motivating an application-level message-expiry policy. Embedded inference deployment is identified as the primary next step.

IoT doi: 10.3390/iot7030076

Authors: Xuefeng Liu Rui Tang Qindong Sun Sichen Zou

Passive acoustic monitoring of ocean surface wind speed and rainfall faces severe degradation in shallow waters due to multipath propagation and non-meteorological noise interference. To address these challenges within the Internet of Underwater Things (IoUT), this study proposes a sequential acoustic sensing framework for vertical linear array (VLA) nodes to enhance meteorological inversion accuracy. First, an incoherent averaging method is introduced to mitigate acoustic field fluctuations by accumulating vertical spatial information across the sensing channels. Second, the Correlation Matrix of Energy Spectrum (CMES) and the higher-order bispectrum are analyzed to decouple cross-frequency characteristics and identify the dominant frequency bands of the acoustic sources. On this basis, a Principal Component Analysis (PCA)-assisted bispectral entropy method is implemented after spectral reconstruction, enabling accurate environmental scenario classification and interference suppression at the sensor level. Experimental validation using ambient noise data recorded by an IoUT VLA node in the South China Sea demonstrates that the proposed framework effectively stabilizes the acoustic field, reducing continuous spectrum fluctuations by 7–8 dB. Consequently, the applicability and robustness of empirical wind speed inversion models are significantly improved, providing a resilient and high-fidelity sensing solution for interference-prone shallow sea IoUT applications.

IoT doi: 10.3390/iot7030075

Authors: Prithvi Raju Mekala Yonas Kassa Sushma Mishra

The convergence of Large Language Models (LLMs) with the Internet of Things (IoT) is driving a transformative shift toward a continuous, context-aware smart healthcare ecosystem. Due to its novelty, existing research in this domain remains fragmented, leaving a critical gap in unified frameworks that synthesize domain applications, functional AI deployment roles, network architectures, and security boundaries. Following PRISMA 2020 guidelines, this paper presents a systematic literature review and quantitative analysis evaluating a selected corpus of 61 peer-reviewed and 14 preprint papers in this domain. Methodologically, we assess a novel hybrid article discovery strategy, finding that an AI-powered prompt-based literature search strategy achieves higher precision than traditional keyword-based Boolean queries (86% vs. 42%) on the evaluated search sample, which may reduce screening workloads. We found that the major limitation of AI-based literature search is non-determinism, which is also an inherent property of LLM-powered applications. To address this, we propose methodological guidelines for using an AI-assisted hybrid literature search strategy. Based on the selected literature, we establish a multi-layer taxonomy organizing the IoT-LLM advances in the healthcare domain across four pillars: application domain, LLM role, IoT device type, and architectural deployment pattern. Quantitative synthesis reveals a heavy research concentration in remote patient monitoring and personal health management (representing 59% of the corpus combined), primarily driven by the data accessibility of wearable sensors (64%). Cross-tabulation uncovers a distinct capability–constraint spectrum: cloud-based deployments lean on heavyweight state-of-the-art models (mainly GPT-family models) for complex semantic reasoning, whereas edge, federated, and blockchain-based hybrid systems leverage localized models (BERT and LLaMA families). Patient data privacy and reduced communication overhead were among the main reasons for choosing localized models. Crucially, our assessment reveals a pervasive neglect of LLM-specific vulnerabilities such as prompt injection and jailbreak attacks and a tendency to treat regulatory frameworks (e.g., HIPAA, GDPR) as design features rather than empirically validated compliance metrics. Finally, we propose an actionable future research agenda prioritizing multi-device system orchestration, emergency care integration, privacy-preserving LLMs, and deployment-scale clinical validation.

IoT doi: 10.3390/iot7030074

Authors: Ashraf Alkhresheh

Task offloading in vehicular edge networks must satisfy strict latency limits. At the same time, it must resist security threats such as replay attacks. Existing offloading models treat cryptographic settings as fixed, separate from the scheduling decision. This is a gap, and it exists in part because jointly choosing the best node and the best cryptographic curve for each task is computationally hard. We prove that this joint problem reduces to a generalized assignment problem, a well-known NP-hard problem, once curve-selection variables are fixed. Because of this hardness, we design a polynomial-time greedy heuristic as a practical approximation. Our model treats Elliptic Curve Cryptography (ECC) curve selection as an adaptive decision, and jointly optimizes it together with latency, CPU load, and bandwidth, using one unified scoring function. Results: Task success rate (TSR) with dynamic ECC is within 0.3 percentage points of latency-only scheduling (85.26% vs. 85.58%), while replay success falls from 100% to 8.93%, more than a 10-fold reduction. A single fixed curve that never refreshes (static ECC) performs far worse on both counts (40.29% TSR, 84.54% replay success), since it cannot serve tasks needing stronger security and accumulates staleness without bound. Measured cryptographic overhead is 0.35–1.54 ms per task depending on curve, and the heuristic runs within roughly 2.34% of an exact ILP bound at full scale. These results, from an openly available Python (version 3.9 or later) simulation, confirm real-time feasibility for IoT-enabled vehicular deployments.

IoT doi: 10.3390/iot7030073

Authors: Abu Saleh Molla Antara Chowdhury Syed Shariar Alam Shuvo Afia Tasnim Supty Shahriar Siddique Ayon Md Habibur Rahman

Patient recovery prediction and hospital length of stay estimation remain critical challenges in healthcare resource allocation and clinical decision-making. Inaccurate discharge planning drives substantial avoidable hospital costs, while existing machine learning models remain limited by narrow, single-domain data that fail to capture the multimodal complexity of modern smart ward environments. This study proposes IoT-ClinXAI, an explainable multimodal framework that fuses IoT environmental data, wearable physiological signals, and clinical records for accurate and transparent patient recovery prediction in smart hospital wards. A Multi-domain Hierarchical Consensus Feature-Selection method groups features into structured domains, applies Borda–Kemeny weighted consensus within each domain, and reduces cross-domain redundancy while preserving complementary information. A Snake Optimization–tuned Random Forest Regressor optimizes predictive performance through adaptive hyperparameter search, while a multi-scale SHAP framework provides global and patient-level explanations for transparent clinical inference. Experiments were conducted on a real-world IoT-enabled smart ward dataset comprising patient data and recovery duration. The proposed framework achieved strong predictive performance on the held-out test set, with R2 of 0.964, RMSE of 0.476 days, MAE of 0.342 days, and MAPE of 3.13%, yielding a 23.3% RMSE reduction over the unselected baseline and outperforming all feature-selection methods by 10.9–17.6% in RMSE. Statistical superiority was consistently confirmed across all pairwise comparisons using Wilcoxon signed-rank tests with Bonferroni correction (p<0.001). SHAP analysis identified ward allocation, respiratory rate, and oxygen saturation as the dominant recovery predictors, while environmental IoT variables showed minimal predictive contribution. These results highlight IoT-ClinXAI as a reliable and useful framework for supporting bed management, discharge planning, and hospital resource optimization in resource-constrained healthcare settings.

IoT doi: 10.3390/iot7030072

Authors: José André Galván Diego Mandujano Lenin Canchos Walter Lujerio Mario Chauca

Environmental conditions such as inadequate lighting, excessive noise, and poor indoor air quality can negatively affect students’ health, comfort, and academic performance. Although recent Internet of Things (IoT) technologies have enabled low-cost environmental monitoring systems, most studies provide limited validation of the embedded firmware responsible for deterministic multi-sensor acquisition and real-time operation. This paper proposes and virtually validates an energy-efficient embedded firmware architecture for a low-cost IoT environmental monitoring node for smart classrooms. The system integrates ESP32-based firmware with MQ-135, LDR, and KY-037 sensors, local alarm management, LCD visualization, and HTTP-based wireless communication. Hardware–software co-simulation was performed in Proteus Virtual System Modeling (VSM) before physical implementation. Ten experimental scenarios evaluated firmware execution, sensor integration, alarm coordination, fault handling, IoT communication, and power consumption. The proposed architecture maintained stable deterministic execution under all scenarios, with instantaneous current consumption ranging from 100 mA to 280 mA, 100% successful HTTP transmissions (HTTP status code 200), and an average communication latency of 378 ms. These results demonstrate that virtual prototyping provides an effective framework for early firmware verification, reducing development risks while supporting the deployment of reliable and scalable IoT environmental monitoring systems for smart classroom applications.

IoT doi: 10.3390/iot7030071

Authors: Jingping Duan Nan Wang Yongquan Chen

Transformer lifecycle data across organizations are typically vertically partitioned among material suppliers, manufacturers, logistics service providers, testing agencies, and operation and maintenance units. This study presents a reproducible multi-layer vertical federated learning (VFL) prototype that integrates salted-hash identifier matching, additive sharing of local score vectors over finite fields, and a local public key infrastructure with a signature-based audit verification mechanism. A deterministic synthetic dataset is first constructed, comprising 5200 aligned records and 31 predictor variables, which are partitioned among five participants with varying numbers of features per participant. Second, across five validation runs, the VFL models under both the standard block-wise and score-sharing paths achieved an AUC of 0.8825 ± 0.0119, an F1 score of 0.7367 ± 0.0249, and an accuracy of 0.8102 ± 0.0183 on the test set. The classification results of both paths were fully consistent with the centralized gradient-descent logistic regression baseline. Notably, the score-sharing path exhibited a maximum log-odds deviation of only 2.22 × 10−8 on the test set, with no prediction discrepancies observed. Third, across 10 independently generated synthetic populations, the nonlinear output mechanism highlights the limitations of linear models: the AUC of vertical federated learning (VFL) drops to 0.6457 ± 0.0171, while Extra Trees and HistGradientBoosting achieve 0.7731 ± 0.0149 and 0.7743 ± 0.0139, respectively. Finally, in a separate residual-sharing diagnostic test, when 1 to 4 participants jointly shared the residuals, the label inference AUC remained around 0.499–0.500; however, when all five participants shared or plaintext residuals were used, the labels could be fully recovered. Both simple membership inference diagnostic tests yielded results close to random. The local signature log verifier rejected all 700 injected faults and accepted the 400 clean control log events. These results validate the feasibility of numerical reproducibility and local audit functionality under synthetic data and single-process conditions, yet they are insufficient to demonstrate end-to-end label privacy protection, malicious security, effectiveness on real data, or real-time ledger performance.

IoT doi: 10.3390/iot7030070

Authors: Jesús Mendoza Padilla Eugenio Escalante Otero Ximena Vargas-Ramirez Lina Esquea Arroyo Daniel Fernando Forero Meriño

Continuous monitoring of water quality is essential for supporting environmental management and enabling timely decision-making in wastewater treatment facilities. Although numerous Internet of Things (IoT) solutions have been proposed for environmental monitoring, many rely on proprietary cloud platforms or commercial gateways that limit flexibility, scalability, and integration with customized applications. This paper presents the design, implementation, and field validation of a modular IoT architecture for real-time water quality monitoring based on distributed sensor nodes, long-range LoRa communication, and a self-hosted web platform. The proposed architecture integrates sensor nodes equipped with calibrated pH, dissolved oxygen, and turbidity sensors, a hybrid LoRa/Wi-Fi Main Controller implementing a custom master–slave communication protocol, and a Python-based back-end with a PostgreSQL database for data acquisition, storage, visualization, and historical analysis. The complete system was deployed and experimentally validated in a real coupled constructed wetland located at the Universidad del Atlántico, Colombia, where three monitoring stations continuously acquired and transmitted water quality measurements over a one-month evaluation period. During the experimental deployment, the system generated more than 4.5 million measurement records (297 MB) while recording average RSSI values between −55.7 and −58.1 dBm (standard deviation: 1.6–2.2 dB). The developed web platform successfully supported real-time visualization and historical analysis of all acquired measurements. These results demonstrate the feasibility of the proposed architecture as a practical, scalable, and modular solution for continuous environmental monitoring that can be readily adapted to other distributed water quality monitoring applications.

IoT doi: 10.3390/iot7030069

Authors: Thit Tun Hakilo Sabit

This paper presents a comprehensive review of the integration of Intelligent Transportation Systems (ITS) and Digital Twin (DT) technologies for intelligent traffic management. It examines the role of key enabling technologies, including the Internet of Things (IoT), machine learning (ML), deep learning (DL), reinforcement learning (RL), Graph Neural Networks (GNNs), vehicle-to-everything (V2X) communication, and edge computing. These technologies support real-time traffic monitoring, traffic prediction, and adaptive control in ITS. The review synthesizes recent research on conventional traffic control methods, optimization-based approaches, learning-based techniques, and DT-enabled traffic management solutions. Particular attention is given to the integration of DTs with intelligent traffic signal control, real-time synchronization, multi-intersection coordination, communication latency, sensing uncertainty, and scalability. The reviewed literature demonstrates the potential of DT-enabled ITS to improve traffic efficiency, reduce congestion, enhance transportation safety, and support sustainable mobility through data-driven decision-making. However, significant challenges remain regarding communication delays, sensor and data uncertainty, computational complexity, scalability, and validation under realistic urban conditions. Based on the reviewed literature, this paper identifies key research gaps and outlines future research directions toward scalable, reliable, adaptive, and real-time DT-enabled ITS architectures for next-generation smart cities.

IoT doi: 10.3390/iot7030068

Authors: Oudarja Barman Tanmoy Sakib Hasan Adnan Anwar Md. Al Mamun A B M Mehedi Hasan Akhlaqur Rahman

While federated learning offers a decentralized approach to model training, ensuring the integrity of the information from each IoT client remains a challenge. This work delves into the dynamics of multi-stage federated learning, its susceptibility to information integrity attacks, and how to defend against such threats. A comprehensive understanding of data uncertainty and the challenges of poisoning attacks is discussed, laying a solid groundwork for the proposed defense mechanisms. At its core, this paper introduces a novel multi-stage federated learning model that segments the federated learning process into distinct phases with a novel approach of inertial momentum-aware Inexact Augmented Lagrange Multiplier Robust PCA with constant momentum factor and unaltered norm of the traditional one, each tailored to optimize for both efficiency and security. This robust framework is then tested against data injection-based poisoning attacks, using sparse noise, and demonstrates the effectiveness of the proposed recovery techniques like Robust PCA. Performance results highlight the resilience and efficiency of the introduced model with novel reconstruction algorithm, emphasizing the importance of this approach in real-world IoT settings. Data analysis, model summaries, and impacts of adversarial attacks further reinforce the findings, which are evaluated using rigorous statistical metrics and machine learning algorithms. The paper concludes by acknowledging its efficiency in detection and recovery from data poisoning attacks, improving robustness and data reconstruction in IoT environments while highlighting opportunities for further security enhancements.

IoT doi: 10.3390/iot7030067

Authors: Mohammed Al Saleh Joseph Azar

Federated, semi-supervised novelty detection is well suited for intrusion detection on resource-constrained Internet of Things (IoT) nodes: each device learns a model of benign traffic, shares only summary statistics, and does not transmit raw traffic samples. A previously published cross-layer federated detector, Baseline K-Means, showed that periodically merging worker statistics through a coordinator raises the detection rate, but it also exhibited a systematic side effect: after every merge, the precision decays, and the false-positive rate (FPR) climbs because the coordinator recomputes its threshold from streaming distances filtered by the closest observed anomaly, so tightens after every merge, flagging progressively more benign traffic; the threshold was also hand-tuned. We present AF-BKM, an Adaptive Federated Baseline K-Means that repairs the federated mechanism with two label-free, statistics-only enhancements, denoted as E1 and E2: (i) an adaptive decision threshold read from the benign Mahalanobis-distance distribution, requiring no manual percentile search and no attack labels (E1), and (ii) a robust, benignly anchored aggregation that blends worker means under quality weighting and outlier-worker filtering and recalibrates the threshold on a trusted benign anchor to a stable, anchor-referenced false-positive level, which a target-FPR rule can make operator-selectable instead of tightening it toward the nearest anomaly (E2). With MinMax scaling fit only on benign baseline data and non-IID federated streams on NSL-KDD, UNSW-NB15 and the N-BaIoT corpus of real traffic from commercial IoT devices, AF-BKM removes the merge-induced precision decay (the first-to-last-epoch precision change improves from −0.134 to −0.002 on NSL-KDD, from −0.121 to −0.014 on UNSW-NB15, and from −0.170 to −0.009 on N-BaIoT) and reduces the mean FPR by 30–64%, depending on the dataset; all central improvements are significant across 10 seeds (Wilcoxon p=0.002, large effect sizes). AF-BKM preserves recall on NSL-KDD and N-BaIoT and, on the harder UNSW-NB15, exposes an explicit precision–recall trade-off through a benign target-FPR knob. In fp32, the deployed model serializes to 5.5–52 KB, a packet is classified in 11–27 µs on a desktop CPU, and each merge round uploads a d+3-value summary (160–472 B) 94.6–98.3% smaller than the same summary extended with the covariance upper triangle. A robustness study covering selected faulty-worker updates, contamination of the commissioning anchor, and detector-level white-box evasion reports the measured degradation patterns: fabricated threshold candidates have no direct path to the threshold, although a fabricated mean still reaches it indirectly through the blended centroid, and the anchor-referenced false-positive level remains stable under percent-level anchor contamination, while recall sensitivity is dataset-dependent and the evasion budget tracks the benign–attack margin of each dataset. We frame the contribution with a focused taxonomy that identifies merge-induced precision decay under non-IID workers as an open gap. Code is released for reproducibility.

IoT doi: 10.3390/iot7030066

Authors: Murilo Táparo Jonatas Galvão Luiz Xavier Paulo Zimpel Bianca Dantas Ricardo Santos

The Multi-Node Allocation (MNA) problem in Internet of Things (IoT) networks arises when application requirements exceed the capacity of a single node, requiring job distribution across multiple devices. This problem is challenging in large-scale heterogeneous environments once it involves optimizing resource utilization, bandwidth consumption, and latency within a rapidly expanding search space. This paper proposes two scalable approaches: a greedy heuristic called Demand Index Multi-Node Allocation (DI-MNA) and a hybrid evolutionary algorithm (NSGA-Hyb) that combines DI-MNA with NSGA-III. Both methods use bounded combinatorial exploration and a normalized demand index to guide the search efficiently. The approaches are evaluated on IoT networks ranging from 10 to 1000 nodes under different workload conditions and compared with an optimal Branch and Bound (B&B) algorithm for small instances. Results show that DI-MNA achieves near-optimal solutions in small networks while maintaining low computational cost as network size grows. In large-scale scenarios, DI-MNA consistently matches or outperforms the evolutionary methods and sustains runtime speedups of up to 51× over NSGA-Hyb and more than 7.8×106 over B&B. These findings demonstrate that DI-MNA provides an effective balance between solution quality, scalability, and computational efficiency for resource allocation in large-scale IoT networks.

IoT doi: 10.3390/iot7030065

Authors: Ruth Escobedo-Carranza Juan Aguilera-Alvarez Adriana Guzmán-López Sergio Olmos-Temois Micael Bravo-Sánchez Víctor Sámano-Ortega

Cardiovascular diseases are among the leading causes of mortality worldwide, making continuous electrocardiographic (ECG) monitoring essential for the early detection and follow-up of cardiac abnormalities. This study presents an Internet of Things (IoT) platform for continuous remote monitoring of three-lead ECG signals using LTE-M cellular connectivity. The proposed system integrates an ADS1293 analog front-end for ECG acquisition, a Walter IoT Module for MQTT-based data transmission, and a cloud infrastructure for secure data reception, storage, and visualization. A dual-core implementation on the ESP32 separates ECG acquisition from MQTT communication, preventing sample loss during continuous monitoring. Experimental results demonstrated reliable transmission of raw three-lead ECG signals, with no packet loss observed during a continuous 12 h LTE-M transmission test involving approximately 250,000 packets. The monitoring mechanism also automatically detected packet losses and device restarts. At the same time, server performance evaluation showed low CPU and memory utilization during simultaneous communication with five data sources under the evaluated conditions. These results validate the proposed IoT communication platform and establish a foundation for future work, including intelligent ECG analysis, improvements in signal acquisition and conditioning, and the continued development of the portable Holter device.

IoT doi: 10.3390/iot7030064

Authors: Mostafa Kamel Abdelrahman Ahmed Yahya Mahmoud Hussein

The Message Queuing Telemetry Transport (MQTT) protocol has become one of the most widely used messaging protocols for IoT and Industrial Internet of Things (IIoT) applications because of its lightweight publish–subscribe architecture. However, the standard MQTT PUBLISH message supports only a single topic–payload pair, requiring multiple protocol transactions and acknowledgment exchanges when several related measurements need to be transmitted together. This limitation increases communication overhead and latency, particularly in data-intensive IoT and IIoT environments. To address this limitation, this paper proposes M_PUBLISH, a protocol-level extension that aggregates multiple topic–payload pairs into a single MQTT control packet. At the broker, the aggregated packet is transparently decomposed into standard MQTT PUBLISH messages before being forwarded to subscribers, preserving native topic-based routing and compatibility with existing MQTT subscribers. The proposed protocol is analytically and experimentally evaluated in terms of latency, protocol overhead, frame size, and goodput across all MQTT QoS levels. The protocol is implemented in the aMQTT broker and validated under representative IoT/IIoT scenarios, including packet loss, network latency, bandwidth limitation, and selective subscribers. The results show up to 95% lower end-to-end latency, up to 20× higher goodput, and significantly lower protocol overhead while remaining compatible with existing MQTT subscribers and require modifications to publishers and brokers.

IoT doi: 10.3390/iot7030063

Authors: Marco Grossi Martin Omaña

Cyberattacks represent a serious threat for the security of network-based systems and are responsible for large economic losses every year. In this context, physical unclonable function (PUF)-based authentication can provide access to the network resources to legitimate users only, thus preventing unauthorized accesses. On the other hand, transient disturbances (e.g., noise, temperature and power supply variations) and permanent faults can lead to erroneous PUF responses, resulting in failed authentication and reduced network availability for legitimate users. Error-correcting codes have been proposed in the literature to improve PUF reliability. However, they typically require significant costs in terms of processing power and area overhead, meaning they are often unsuitable for resource-constrained devices, such as low-cost microcontrollers and FPGAs. In this paper, we have investigated strategies based on the use of different kinds of error-detecting and error-correcting codes, as well as their possible combination, with limited requirements in terms of processing power and no need for helper data. These strategies have been evaluated using both a synthetic PUF dataset and a real PUF dataset. The results show that the strategy based on a checksum error-detecting code achieves a good performance in terms of network availability, i.e., an error probability in the order of 10−3 (3.69 × 10−2) when the error on the PUF response (without any ECC) is 12.89% (55.04%), with a low data overhead (1.56% of the PUF challenge size), but it is effective only in the presence of transient disturbances. Instead, the strategy combining the checksum and the Hamming codes provides even higher network availability, i.e., an error probability in the order of 10−4 (1.6 × 10−3) when the error on the PUF response (without any ECC) is 12.89% (55.04%), at the cost of a slightly higher data overhead (7.81% of the PUF challenge size), while also enabling the capability to correct erroneous PUF responses caused by both disturbances and permanent faults.

IoT doi: 10.3390/iot7030062

Authors: Luis Alberto López-González Juan José Martínez-Nolasco Mauro Santoyo-Mora Mauricio Erazo-Barradas Víctor Sámano-Ortega Coral Martínez-Nolasco

The Internet of Plants (IoP) represents the convergence of Artificial Intelligence (AI), Big Data analytics, and the Internet of Things (IoT) within protected agricultural systems. This study presents an IoP platform designed to collect, process, and analyze real-time environmental data using specialized IoT sensors capable of monitoring critical variables, including carbon dioxide concentration (CO2), pH, air temperature, and relative humidity in hydroponic production systems. The proposed framework integrates advanced machine-learning algorithms, including Random Forest Regressor and Long Short-Term Memory (LSTM) neural networks, to process large volumes of environmental data and support crop management. In addition, the platform incorporates Vapor Pressure Deficit (VPD) and Growing Degree Days (GDD) analyses to provide crop-specific recommendations and support informed decision-making. This platform establishes a benchmark for smart agriculture in Mexico’s Laja–Bajío region, facilitating informed decision-making and maximizing the sustainability of food systems. Experimental validation was conducted under both controlled and semi-controlled environments using Swiss chard (Beta vulgaris subsp. cicla L.) and lettuce (Lactuca sativa L.) cultivated in hydroponic systems. These environments represented contrasting climatic conditions, allowing evaluation of platform stability and forecasting performance under varying thermal regimes. The Random Forest Regressor model, trained using growth chamber data consisting of 19,836 valid observations, reproduced the deterministic VPD relationship with a coefficient of determination (R2) of 0.90 and a root mean square error (RMSE) of 0.08 kPa, confirming internal consistency and identifying temperature as the dominant contributing variable rather than predicting an independent outcome. The dynamic alarm system, integrated with crop phenological stages, demonstrated greater effectiveness than conventional static-threshold approaches by generating alerts according to crop developmental requirements. Furthermore, the web-based visualization platform enabled users to interpret environmental conditions through intuitive graphical representations, facilitating decision-making without requiring specialized technical expertise. The results demonstrate the feasibility of the IoP platform as a comprehensive environmental management tool for protected agricultural systems. The proposed framework provides a scalable solution for precision agriculture applications in the Laja–Bajío region of Mexico and in other regions with similar production systems.

IoT doi: 10.3390/iot7030061

Authors: D. Di Capua R. Pacheco-Blazquez J. García-Espinosa A. Pastor

This paper presents Open Source Integration for Internet of Things (OSI4IOT), an open-source software platform designed to support the integration of sensor-driven Internet of Things (IoT), Asset Information Modelling (AIM), Geographical Information Systems (GIS), and data-driven analysis within a Digital Twin (DT) framework. The platform provides a modular architecture for connecting heterogeneous data sources and enabling the coupling between physical assets and numerical models. In particular, it supports the integration of Finite Element Method (FEM)-based structural models for simulation and comparison with monitored responses. A case study involving a structural frame is used to demonstrate the platform workflow, including data acquisition, model execution, and result visualisation. The results are used to assess the consistency between analytical, numerical, and monitored responses under varying loading conditions. The paper focuses on the system architecture and the coupling strategy between data acquisition and simulation components within an open-source environment.

IoT doi: 10.3390/iot7030060

Authors: Shensheng Tang

IoT gateway–cloud systems support large-scale sensing, monitoring, and control applications, but must operate under finite buffering, dynamic traffic demands, and service interruptions caused by gateway and cloud failures. These challenges can lead to backlog accumulation, congestion, and degraded service performance, making admission-threshold selection an important reliability-management problem. This paper investigates reliability-aware admission-threshold selection for finite-buffer systems with service interruptions, motivated by IoT gateway–cloud architectures. A finite level-dependent quasi-birth-and-death (LD-QBD) model is developed to jointly capture probabilistic admission control, finite buffering, and gateway–cloud failures. Exact stationary analysis yields a multidimensional performance-characterization framework based on effective service deliverability, congestion-regime probability, saturation probability, and soft normalized headroom. The admission threshold is shown to govern the trade-off between service deliverability and congestion protection under failure-induced backlog dynamics. To address this trade-off, two complementary threshold-selection paradigms are developed: a trade-off-driven weighted optimization approach and a constraint-based feasibility-enforcement approach. Numerical results show that the weighted formulation exhibits a well-defined knee point, whereas the constraint-based method produces reliability-aware threshold adjustments when operational constraints become active. The results further indicate that increasing traffic load or failure intensity generally requires more conservative admission policies. Although motivated by IoT gateway–cloud systems, the proposed framework is applicable to a broader class of finite-buffer service systems with unreliable resources.

IoT doi: 10.3390/iot7030059

Authors: Yassine Ayat Ali El Moussati Oumayma Rachdi Maryem Dinar Abdelaziz El Aouni Hajar Karkri Mohammed Benzaouia Wiame Benzekri Ismail Mir Aumeur El Amrani Abdelmalek Mimouni

Efficient irrigation management requires complementary information on atmospheric demand, soil conditions, and crop water stress. This study presents a low-power Internet of Things (IoT)-based irrigation system that integrates these components within a unified monitoring and control framework. The system combines LoRa communication, ESP32-based sensor nodes, soil and meteorological sensing, FAO-56 reference evapotranspiration (ET0), and canopy-temperature-based Crop Water Stress Index (CWSI). Irrigation decisions rely on the complementary use of ET0, in situ soil measurements, and CWSI rather than on a single indicator. A hybrid time-, event-, and query-driven acquisition strategy was implemented to adapt node activity and limit communication overhead. The system was deployed under outdoor conditions in Oujda, Morocco, demonstrating integrated sensing, wireless data transmission, crop-stress monitoring, and automated irrigation control. Energy characterization further showed distinct consumption profiles across sensing, communication, actuation, and low-power operating states, supporting the use of duty cycling to limit active node operation. The results demonstrate the feasibility of integrating environmental, soil, and crop-level information within a low-power IoT framework for adaptive irrigation management.

IoT doi: 10.3390/iot7030058

Authors: Marios Koniaris Danae Spentzou Max Friedemann Helmut Mischo John Soldatos Georgios Kouzas

Mining operations generate continuous sensor data across heterogeneous repositories with no unified access layer. Existing integration platforms either require centralizing data into new infrastructure or demand extensive pipeline reconfiguration when sources change. We present a metadata-driven execution model in which integration behavior is resolved at runtime from executable metadata rather than encoded in static workflows, preserving existing infrastructure while enabling unified access across heterogeneous repositories. An Asset Cataloging registry stores executable specifications, including connector identifiers, connection parameters, and routing rules, which select and invoke the appropriate connector at runtime without workflow coding or redeployment. Evaluation on large-scale real mining sensor datasets spanning heterogeneous formats (JSON, CSV, Parquet) and repositories (Kafka, MongoDB, external REST APIs) confirmed zero message loss and bit-exact binary reconstruction across all scenarios under at-least-once delivery with idempotent writes. Connector dispatch overhead fell below the 1 ms measurement resolution, confirming that integration latency is dominated by storage I/O rather than orchestration cost. Following evaluation, four pilot sites deployed the platform in production, spanning from active underground operations to post-mining waste management, under the EU Horizon Europe MINE.IO project, demonstrating viability at industrial scale.

IoT doi: 10.3390/iot7030057

Authors: Trien Phat Tran Fareed Ud Din Ljiljana Brankovic Cesar Sanin Susan M. Hester

Smartphone-based plant identification increasingly serves as the edge tier of agricultural Internet of Things (IoT) systems, where models must adapt to crowdsourced data under bandwidth, memory, and energy constraints. No prior work, to our knowledge, has systematically investigated continual learning at the scale of thousands of fine-grained medicinal plant species from crowdsourced images, nor how retraining frequency affects the cost–performance trade-off in an IoT model-lifecycle setting. We evaluate three continual learning strategies, naïve fine-tuning, experience replay, and Learning without Forgetting, under periodic retraining schedules (updating every K increments), tested on 2719 species (≥25 images each) from the Viet Medi Species 2026 dataset (310,647 images; 4799 species total). All three strategies exhibit negative forgetting (performance improvement rather than degradation) in the instance-incremental setting, with naïve fine-tuning and LwF showing the strongest gains. Periodic retraining with K=2 halves retraining operations while maintaining comparable performance. A baseline MobileNetV2 model achieves 54.07% top-10 accuracy across 2719 species and has been deployed via TensorFlow Lite (FP16, ∼11.5 MB) in the Med Herb Lens Android application. In this regime, naïve fine-tuning offers a favourable cost–performance trade-off and is a reasonable default for instance-incremental agricultural IoT deployments.

IoT doi: 10.3390/iot7030056

Authors: Najem N. Sirhan Riyad Alrousan Hussam N. Fakhouri

Internet of Things (IoT) devices are increasingly targeted by rapidly evolving malware, yet collaborative detection remains challenged by privacy leakage, noisy and imbalanced training data, and weak integrity guarantees when sharing model updates. This paper presents Mal-Fedchain, a secure and privacy-preserving framework for image-based IoT malware detection and prevention that couples federated learning with blockchain and honeypot-assisted behavioral monitoring, targeting Linux-capable IoT gateway devices. Portable Executable (PE) binaries are transformed into grayscale images using a corrected fixed-width byte-mapping pipeline stabilized by an information-maximizing GAN (IMGAN). A bi-level preprocessing pipeline applies two-sided weighted sparse representation (T-WSR) denoising—designed to selectively suppress zero-padding artifacts, high-entropy packed regions, and sparse opcode noise while preserving discriminative section-boundary texture—followed by geometric augmentation to mitigate class imbalance. Malware detection and family attribution are performed using a residual capsule-based network (RBCN) that fuses discriminative visual representations with PE-header features via concatenation, improving robustness against polymorphism and obfuscation. A formal threat model governs three adversary classes: a semi-honest aggregation server, a bounded fraction of malicious clients (up to 30%), and a passive eavesdropper. To enable collaboration without exposing raw data, clients train locally and share only MemCbar-encrypted updates; a permissioned Hyperledger Fabric blockchain ledger records hashed updates and security events to provide integrity, traceability, and tamper resistance. A file-system-integrated honeypot captures evasive behaviors and logs auditable evidence to strengthen prevention. Experiments on the Malimg dataset across five ablation configurations demonstrate that the corrected RBCN pipeline achieves 93.52% accuracy, 92.40% precision, 93.52% recall, 92.52% F-measure, MCC of 0.9245, and AUC of 0.9976 in its centralized configuration, and 65.62% accuracy with AUC of 0.9840 in the full federated configuration with five clients and eight communication rounds, substantially outperforming all baselines across all reported metrics.

IoT doi: 10.3390/iot7030055

Authors: Yassine El Yamani Youssef Baddi Najib El Kamoun

Federated learning (FL) is a promising paradigm for privacy-preserving IoT intrusion detection, but its effectiveness can be substantially degraded by the combination of heterogeneous non-IID client distributions and severe multi-class imbalance. Under such conditions, conventional size-based aggregation may overemphasize large yet highly skewed clients, limiting the representation of minority attack classes in the global model. To address this issue, we propose Mean/Std, a lightweight distribution-aware aggregation strategy that combines a client-size proxy with two complementary statistics of local label distributions, namely the standard deviation and the dominance gap of class proportions, while preserving a communication footprint comparable to FedAvg. Experiments on the N-BaIoT benchmark, comprising seven heterogeneous IoT clients and eleven traffic classes, are conducted under a privacy-oriented update-perturbation setting inspired by secure aggregation workflows. The results show that Mean/Std consistently provides the strongest imbalance-aware performance among the evaluated FL baselines, achieving a Macro-F1 score of 0.8418 and a Balanced Accuracy of 0.8722 while improving the representation of minority attack classes. Additional experiments across five independent random seeds and a comprehensive hyperparameter sensitivity analysis further confirm the robustness and stability of the proposed aggregation mechanism. Overall, the results demonstrate that lightweight distribution-aware aggregation offers an effective, robust, and practically deployable solution for mitigating aggregation bias under simultaneous non-IID heterogeneity and severe multi-class imbalance in FL-based IoT botnet detection.

IoT doi: 10.3390/iot7030054

Authors: Kittiwat Srivilas Chaiyod Pirak

Narrowband Internet of Things (NB-IoT) is a 3GPP-standardised low-power wide-area network (LPWAN) technology designed for massive machine-type communications in challenging propagation environments. Despite its growing deployment, empirical channel data for Thailand’s diverse terrain—urban dense, urban outdoor, suburban, rural, and forest/mountain—remains limited in the open literature. This paper presents a composite channel characterisation study encompassing sixteen measurement sites across five environment classes in central and western Thailand. A composite channel model combining log-distance path loss, log-normal shadowing, and Nakagami-m fast fading is applied across all sites, yielding 8000 reference signal received power (RSRP) samples. Path loss exponents range from n = 2.2 (rural) to n = 4.0 (forest/mountain), back-calculated Nakagami-m parameters from m = 0.44 to m = 3.51, and shadowing standard deviations from σsh = 4.16 to 8.38 dB; ECL distributions are derived for all five environment classes. The back-calculated Nakagami-m parameters reveal a coherence gradient from sub-Rayleigh forest terrain (m < 1) through urban Rayleigh (m = 1.00) to near-Rician rural conditions (m > 2)—a fading hierarchy not previously reported for NB-IoT in Thailand. Results confirm that the composite channel model accurately characterises RSRP distributions and provides actionable network planning parameters for NB-IoT deployment in varied Thai terrain.

IoT doi: 10.3390/iot7030053

Authors: Christos Goumopoulos Antonios Pliatsios

The Social Internet of Things (SIoT) has emerged as a promising paradigm for addressing interoperability, adaptability, and intelligent collaboration challenges in smart city environments. However, existing solutions often provide only partial support for semantic interoperability, dynamic social relationships, and context-aware service coordination across heterogeneous IoT ecosystems. This paper presents SEMIWARE, a semantic social network-oriented middleware designed to support collaborative, interoperable, and context-aware SIoT applications. SEMIWARE adopts a layered architecture that combines a FIWARE-based middleware backbone with modular services for context management, semantic annotation, semantic reasoning, service discovery, social relationship management, profiling, security, and ontology alignment. Its semantic backbone is provided by an OWL2 ontology that models IoT entities, users, services, contextual information, and trust-aware social relationships. The middleware is validated through two representative applications in distinct domains: smart mobility, where semantic reasoning supports adaptive eco-friendly route computation, and healthcare, where semantically integrated wearable and environmental data support health-event detection for people with dementia. Experimental evaluation further examines the performance of semantic annotation, semantic reasoning, and context management services under increasing workloads. The results provide prototype-level evidence that SEMIWARE supports semantic interoperability, cross-domain adaptability, and graph-based processing under controlled workloads, indicating its potential suitability for complex, data-intensive SIoT applications.

IoT doi: 10.3390/iot7030052

Authors: Saddam K. Alwane Shereen S. Jumaa Muna H. Saleh Aymen D. Salman Ayad Q. Al-Dujaili Amjad J. Humaidi

The rapid proliferation of Internet of Things (IoT) devices within 5G-enabled smart city environments has introduced unprecedented challenges in communication protocol management across heterogeneous network architectures. With connected IoT devices projected to reach 21.1 billion by the end of 2025 and approximately 39 billion by 2030, existing static protocol selection mechanisms are unable to accommodate the dynamic Quality of Service (QoS) requirements of different smart city applications, such as enhanced Mobile Broadband (eMBB), Ultra-Reliable Low-Latency Communication (URLLC), and massive Machine-Type Communication (mMTC). This paper presents APO-DRL (Adaptive Protocol Optimization using Deep Reinforcement Learning), a framework that utilizes a Dueling Double Deep Q-Network (D3QN) combined with a Prioritized Experience Replay mechanism for intelligent, real-time communication protocol selection and parameter optimization in heterogeneous IoT networks. The proposed framework formulates the protocol optimization problem as a Markov Decision Process (MDP), wherein the DRL agent dynamically selects the optimal communication protocol (NB-IoT, LTE-M, LTE Cat-1, or 5G NR) and adaptively tunes transmission parameters based on real-time network conditions. Experimental evaluation in a 3GPP TR 38.901 Urban Macro simulation environment with N = 30 devices demonstrates that APO-DRL achieves a 138.9% improvement in average throughput compared to Static Allocation (60.00 vs. 25.12 Mbps), while simultaneously achieving the highest QoS satisfaction (83.38%) across all methods, albeit with higher energy consumption and packet loss than Static Allocation. Relative to D3QN+PER, APO-DRL exhibits substantially lower cross-seed throughput variance (±0.88 vs. ±11.03 Mbps), confirming that QA-PER produces a more stable and reproducible learned policy.

IoT doi: 10.3390/iot7030051

Authors: Mikiyas Alemayehu Mohamed Chahine Ghanem Hamza Kheddar Dipo Dunsin Marcio J. Lacerda

Distributed Denial of Service (DDoS) attacks pose significant threats to Industrial Internet of Things (IIoT) environments, exacerbated by the resource constraints of IoT devices and the disruptive impact of such attacks. Conventional detection and prevention methods fall short of ensuring the availability and operational continuity required in industrial deployments. This article systematically analyses artificial intelligence (AI) techniques for detecting, preventing, and mitigating DDoS attacks in IIoT systems. We examine diverse AI-driven solutions, including machine learning (ML) and deep learning (DL) models, alongside hybrid approaches that enhance real-time threat identification, adaptive defence mechanisms, and decentralised trust management, addressing the evolving sophistication of DDoS attacks. This study highlights AI’s potential to strengthen IIoT security and resilience, particularly in critical national infrastructure (CNI), where uninterrupted operations are paramount. However, challenges such as computational overhead, model interpretability, and dataset scarcity in industrial settings remain critical barriers. Additionally, the dynamic IIoT topology and heterogeneous device ecosystems necessitate context-aware AI solutions. This analysis underscores the need for lightweight, explainable AI frameworks and collaborative defence strategies tailored to the IIoT’s unique constraints. It emphasises the integration of AI with emerging technologies like edge computing and federated learning to advance proactive, scalable DDoS defence mechanisms in industrial ecosystems.

IoT doi: 10.3390/iot7030050

Authors: Yahia Hasan Jazyah Luai Al-Shalabi

A new era in wireless communication has been witnessed by the emergence of fifth generation (5G) technology, characterized by high data rates, ultra-low latency, and massive device connectivity. To address the growing demand for efficient spectrum utilization, Non-Orthogonal Multiple Access (NOMA) has been introduced as a promising multiple access scheme. This study investigates the energy efficiency (EE) and spectral efficiency (SE) performance of NOMA in comparison with Orthogonal Multiple Access (OMA) under varying bandwidth conditions. In addition to conventional analytical and simulation-based evaluations, artificial intelligence (AI) techniques, including Deep Learning (DL), Decision Tree (DT), K-Nearest Neighbours (KNN), and Logistic Regression (LR), are employed to model and predict system performance. The AI models are trained using simulation-generated datasets to capture complex relationships between bandwidth, transmit power, and user distribution. Simulation results demonstrate improvement in SE and EE of NOMA across different bandwidth scenarios. Furthermore, DL and DT models achieve higher prediction accuracy. The consistency between AI predictions and simulation outcomes confirms the robustness of the proposed framework. These findings highlight the superiority of NOMA over OMA and demonstrate the effectiveness of integrating AI techniques for performance optimization in 5G and beyond wireless networks.

IoT doi: 10.3390/iot7030049

Authors: Sudeshna Das Abhishek Majumder Sudipta Roy

The application of Internet of Things-based ecosystems is growing rapidly. Cyber attacks are also increasing at a similar pace. Intrusion detection using deep learning is getting harder as these devices lack enough resources for a large Intrusion Detection System. A compact deep learning-based Intrusion Detection System for IoT, called CID, has been proposed to reduce computational complexity. The proposed CID framework uses MobileNet v1 as the main classification model, and the Binary Greylag Goose Optimization technique is used for feature selection to improve detection while minimizing processing time. On comparing the experimental results, it has been found that the proposed method works better than the baseline methods.

IoT doi: 10.3390/iot7020048

Authors: Flavio Ciravegna Enrico Bravi Silvia Sisinni Antonio Lioy

In recent years, organisations have increasingly transitioned their workloads from on-premise infrastructures to cloud environments, while leveraging edge computing to meet the rising demand for scalable and distributed applications. This shift has accelerated the adoption of IoT devices, which play a key role in enabling these systems. As a result, ensuring the security of sensitive IoT applications has become critical, motivating the use of Trusted Execution Environments (TEEs) to provide isolated execution even in the presence of potentially compromised operating systems. This work focuses on the IoT-oriented Keystone Enclave framework, an open-source TEE built on the RISC-V Instruction Set Architecture. Among its security features, Keystone implements a binary measurement mechanism during the enclave-loading phase. However, this approach guarantees application integrity only at load time, leaving the TEE’s confidentiality and integrity vulnerable to runtime exploitation of software vulnerabilities. To address this limitation, we propose an integrity verification mechanism that provides evidence about the state of sensitive memory regions throughout enclave execution. Compared to traditional load-time measurement techniques, our approach reduces per-execution measurement overhead by 57.5%, while requiring minimal extensions to the Trusted Computing Base. Furthermore, it overcomes key limitations of the existing framework by decoupling enclave applications from the attestation logic.

IoT doi: 10.3390/iot7020047

Authors: Edna Iliana Tamariz-Flores Richard Torrealba-Meléndez Jesús Manuel Muñoz-Pacheco Mario López-López César Augusto Arriaga-Arriaga

Latency is a determining factor in an IoT-enabled Intelligent Transportation System. To solve the latency issue in an edge computing system connected to the cloud, where the primary challenge is the distance between the end device and the cloud server, an implementation in a real urban environment is presented to illustrate the architecture of Intelligent Edge Computing. The IEC design is scalable through a communication system that incorporates latency and distance measurements in the transmission of a detection signal using deep learning at the edge node. This enabled the transmission of 2-byte detection signals to the fog node, where the received information was processed to count vehicles on up to three streets near the intersection. The vehicle detection signal is transmitted between two different embedded platforms. This architecture enabled an average transmission latency of 15.45 ms and a total end-to-end latency of 47.9087 ms over a distance of 600 m in a real-world urban environment. The IEC system leverages this low latency and offers intelligent processing closer to the data source and, therefore, to the user.

IoT doi: 10.3390/iot7020046

Authors: Nasreddine Haqiq Mounia Zaim Abdelhay Haqiq Mohamed Sbihi Aziza El Ouaazizi

Industry 4.0 is speeding up the move to connected, data-driven, and automated production, where the Internet of Things (IoT) enables sensing, communication, and real-time support for decisions. At the same time, rapid growth in industrial IoT studies has led to scattered technologies, architectures, and results. This paper fills this gap through a systematic literature review on IoT for Industry 4.0. It also helps readers compare methods and choose suitable building blocks for real deployments today. We focus on key technologies, integration architectures, application areas, challenges, trends, and reported benefits. Using PRISMA 2020, we searched five major databases (Scopus, MDPI, IEEE Xplore, ScienceDirect, and Web of Science) for 2020–2025 and found 584 records. After removing duplicates and screening, we kept 96 peer-reviewed studies for detailed analysis. Results show that most studies use a layered stack that combines sensing/actuation, industrial networking, data collection pipelines, and analytics across edge, fog, and cloud resources. MQTT, OPC UA, CoAP, LPWAN, and 5G connectivity are often used for communication, while RAMI 4.0, IIRA, and similar layered models guide system design. Many architectures follow an edge–cloud pattern, with growing focus on digital twin/CPS links and security-by-design. Applications are mainly smart manufacturing, predictive maintenance, and logistics, with added work in energy management, Construction 4.0, and agri-food monitoring. The key barriers remain interoperability, data quality and evaluation gaps, cybersecurity risks, legacy integration, and deployment limits. The review points to future work on edge AI/TinyML, deterministic connectivity, scalable digital twins, trusted data sharing, and sustainable industrial IoT.

IoT doi: 10.3390/iot7020045

Authors: Nurlan Tashatov Ruslan Ospanov Dina Satybaldina Yerzhan Seitkulov Banu Yergaliyeva Kuat Utebayev

One area of application for distributed ledger technologies is the Internet of Things. These technologies can provide an effective solution to many problems in this field. The consensus layer is a crucial architectural component of distributed ledger systems. Modern IoT networks place increased demands on the consensus mechanisms used in blockchain systems. There are many consensus protocols with different properties and purposes, including those for IoT blockchain networks. Selecting an appropriate consensus protocol for a specific IoT blockchain system is an important and complex task. Multi-criteria decision analysis methods are widely used in such problems, as they allow for the consideration of multiple conflicting criteria and provide a balanced approach to evaluating alternatives. Given the variability of network parameters and requirements of consensus mechanisms, multi-criteria decision-making methods can support more informed protocol selection. This paper presents a decision support framework for selecting a consensus protocol for blockchain-based Internet of Things networks. The system is an implementation of a previously developed conceptual model for a consensus protocol selection framework. A case study is also provided to demonstrate the application of the system.

IoT doi: 10.3390/iot7020044

Authors: Raad S. Al-Qassas Malik Qasaimeh

Lightweight devices are becoming a crucial part of networked systems, including Internet of Things environments. These devices usually have constraints, such as limited computational power, which have directed researchers to develop lightweight crypto algorithms to secure the data generated by these devices. Therefore, an efficient but secure crypto algorithm for these devices is required. In this paper, we thoroughly evaluate well-known SPN-based algorithms, namely AES, LED, PRESENT, ASCON-128, and ASCON-128a, based on the success rates of statistical randomness tests, including the Frequency, Runs, Discrete Fourier Transform, and Cumulative Sum tests. With these tests, the assessment measures the algorithms’ ability to produce unpredictable text. To ensure thorough evaluation, the experiments included approximately 19,000 image files of varying sizes up to 2560 KB. The extensive experimental results show that the ASCON family achieved high success rates above 98% in all tests, particularly for small file sizes, while AES achieved higher success rates for larger file sizes, and LED showed limited performance for the varied file sizes. The results confirm that ASCON-128 and ASCON-128a offer the needed trade-off between computation and randomness validation. Based on this evaluation, we propose an adaptive encryption framework based on file size, data classification, and device computational power.

IoT doi: 10.3390/iot7020043

Authors: Shokhrukh Kamaletdinov Dauren Ilesaliyev Ma’sud Masharipov Aleksandr Svetashev Sherzod Jumaev Nargiza Svetasheva Timur Sultanov Islom Abdumalikov Fayzulla Xabibullayev Utkir Khusenov

Accurate per-wagon occupancy accounting at freight stations—knowing which wagon entered or exited which track and when—is a prerequisite for automated shunting management, yet existing technologies—axle counters, RFID, computer vision, and LPWAN IoT—each provide only a subset of the required information and depend on dedicated infrastructure or favourable conditions. This paper investigates whether two fixed BLE gateways, combined with Eddystone-TLM beacon nodes proposed for mounting on freight wagon bodies, can classify passage direction from RSSI signals without supervised model training or labelled training data, site-specific measurement campaigns, or track modification. The enabling mechanism is wagon-body attenuation: as a wagon passes between the receivers, its metallic body creates a temporal asymmetry in the RSSI envelopes that encodes travel direction. We present a five-stage online pipeline at O (1) memory per packet: a two-sided CUSUM detector with adaptive per-event baseline estimation segments the RSSI stream; a three-stage validation filter rejects partial passes, lateral paths, and near-gateway reversals; and direction is classified by the normalised Temporal Centroid shift—a speed-invariant feature requiring no training data—with a cascade fallback for ambiguous short windows. Combined with the beacon MAC address as a wagon identifier, the system generates structured occupancy events directly consumable by station management systems. Validated on 151 labelled events across eight scenario categories at Urtaul freight station and the TSTU test polygon, the pipeline achieves 96.7% accuracy (95% Wilson CI: [92.5%, 98.6%]) and zero wrong-direction predictions across all 84 directional events (exact Clopper-Pearson 95% CI for the wrong-direction rate: [0%, 3.5%]); a Random Forest baseline on the same features confirms supervised learning adds no measurable benefit over the training-free approach within this feature space. The validation was conducted on 151 isolated single-wagon events collected under dry-weather conditions at two sites using a fixed 15 m gateway spacing; multi-wagon scenarios and adverse environmental conditions remain topics for future work.

IoT doi: 10.3390/iot7020042

Authors: Mulhim Al Drees Abbas E. Rahma Samah Daffalla Rawabi Alsudais Naser Fathi Alsubaie Mohammed Albrahim Hassan Abdullah Alghanim Mustafa I. Almaghasla

Water quality has become a major concern for public health, agriculture, and industry, necessitating reliable and continuous monitoring. Conventional monitoring methods are often time-consuming, rely on manual sampling, and involve complex equipment or procedures, making them unsuitable for real-time applications. This study presents an Internet of Things (IoT)-based system for real-time water quality monitoring using ESP32 hardware integrated with the ThingSpeak platform. The system enhances the accuracy of turbidity and pH measurements using advanced sensor calibration techniques. Nephelometric methods and glass electrodes are employed for turbidity detection and pH sensing, respectively, across various water types—including tap water, groundwater, wastewater, saline water, and treated water—to address issues such as environmental drift and measurement inaccuracies. The turbidity sensor was calibrated using a standard six-point method with formazin solutions (0–1064 NTU), whereas pH calibration utilized a three-point approach with NIST-traceable buffer solutions (pH 4, 7, and 10). The results indicate that turbidity measurement errors, initially ranging from 15.75% to 422%, were reduced to below 10% after calibration. Similarly, pH accuracy was significantly improved across all tested water matrices. The system enables real-time data visualization via ThingSpeak, and the implementation of multi-point calibration ensures high data reliability for continuous monitoring. Overall, this approach offers an accurate, efficient, and practical solution for real-time water quality management.

IoT doi: 10.3390/iot7020041

Authors: Hassan Wasswa Timothy Lynar

The rapid proliferation of Internet of Things (IoT) devices has significantly expanded the attack surface of modern networks leading to a surge in IoT-based botnet attacks. Detecting such attacks remains challenging due to the high dimensionality and heterogeneity of IoT network traffic. This study proposes and evaluates three hybrid deep learning architectures for IoT botnet detection that combine representation learning with supervised classification: VAE-encoder-MLP, VAE-encoder-GAT, and VAE-encoder-MoTE. A Variational Autoencoder is initially trained to learn a compact latent representation of the high-dimensional traffic features. Subsequently, the pretrained VAE-encoder component is employed to project the data into a lower-dimensional embedding space. These embeddings are then used to train three different downstream classifiers: a multilayer perceptron (MLP), a graph attention network (GAT), and a mixture of tiny experts (MoTE) model. To further enhance representation discriminability, supervised contrastive learning is incorporated to encourage intra-class compactness and inter-class separability. The proposed architectures are evaluated on two widely studied benchmark datasets—the CICIoT2022 and N-BaIoT dataset—under both binary and multiclass classification settings. Experimental results demonstrate that all three models achieve near-perfect performance in binary attack detection, with accuracy exceeding 99.8%. In the more challenging multiclass scenario, the VAE-encoder-MLP model achieves the best overall performance, reaching accuracies of 98.55% on CICIoT2022 and 99.75% on N-BaIoT. These findings provide insights into the design of efficient and scalable deep learning architectures for IoT intrusion detection.

IoT doi: 10.3390/iot7020040

Authors: Parichehr Dadkhah Parvin Rastegari Mohammad Dakhilalian Phil Yeoh Mingzhong Wang Shahrzad Saremi Rania Shibl

Internet of Things (IoT) assists in efficient connectivity and automation of various applications by making use of wireless communication technology. Ensuring secure authentication and data integrity are the main challenges in this open wireless platform. Although existing cryptographic methods can address these security challenges, most of them incur additional computational and communication overhead, which is unsuitable for resource-constrained IoT devices. Nowadays, researchers have focused on proposing efficient schemes to satisfy security requirements in open wireless IoT frameworks. Recently, a Certificateless Signature (CLS) scheme was developed for the IoT environment. However, in this paper, we show that this CLS scheme is vulnerable to attacks by super Type-II adversaries. To strengthen this scheme, we propose a novel and efficient CLS scheme with existential unforgeability against super adversaries in the Random Oracle Model (ROM). The proposed CLS scheme achieves reduced computational complexity and communication cost. As such, it is suitable for wireless IoT networks to provide secure message authentication and data integrity.

IoT doi: 10.3390/iot7020039

Authors: Dejan Arsenijević Jasmina Arsenijević Srđan Tegeltija Xiaoshuan Zhang Gordana Ostojić Stevan Stankovski

The Internet of Things (IoT) is increasingly recognized as a core digital infrastructure supporting digital transformation, particularly in complex environments such as university campuses, which can be conceptualized as smart campus ecosystems. However, many organizations encounter difficulties when implementing IoT due to insufficient organizational and technological readiness. This paper presents the University Campus IoT (UCIoT) readiness assessment model, which conceptualizes IoT readiness as a manifestation of organizational digital transformation readiness within the smart campus context. The model consists of 24 dimensions grouped into organizational and technological categories and is implemented through structured questionnaires and a supporting software tool. The model was developed using the design science research methodology and evaluated through a case study conducted at the University Campus of Novi Sad, Serbia. The results demonstrate that the model provides a structured and realistic assessment of IoT readiness and helps identify organizational and technological bottlenecks relevant to IoT implementation. The main contribution of this research is a context-specific readiness assessment framework tailored to university campuses that integrates organizational, technological, and client readiness dimensions.

IoT doi: 10.3390/iot7020038

Authors: Garrik Brel Jagho Mdemaya Armel Nkonjoh Ngomade Mthulisi Velempini

Edge computing has emerged as a promising paradigm to minimize latency and energy consumption while improving computational efficiency for mobile devices. Latency-sensitive applications such as autonomous driving, augmented reality, and industrial automation require ultra-low response times, making efficient task offloading a necessity in edge computing. However, distributing optimally computational tasks among edge servers remains a challenge, especially when considering latency, energy consumption, and workload balancing simultaneously. Although existing approaches have focused on one or two of these objectives, they do not provide a holistic solution that incorporates all three factors. In addition, some existing solutions do not take advantage of parallelism at the edge layer, resulting in bottlenecks and inefficient resource usage. In this paper, we propose a novel learning-based task offloading model that integrates parallel processing at the edge layer, adaptive workload balancing, and joint latency–energy optimization. Moreover, by dynamically adjusting the number of selected edge servers for parallel execution, our approach achieves optimal trade-offs between performance and resource efficiency. Our experimental setup includes several edge servers and several randomly deployed devices. It employs Apache HTTP Benchmark (AB) to generate realistic Mobile Edge Computing workloads. The obtained results show that our method outperforms existing approaches by reducing latency, lowering energy consumption, and maintaining a balanced workload across edge nodes.

IoT doi: 10.3390/iot7020037

Authors: Songwut Boonsong Paniti Netinant Rerkchai Fooprateepsiri Meennapa Rukhiran Manasanan Bunpalwong

Thermal hazards in industrial environments often remain undetected until critical failure or injury occurs. Conventional handheld infrared cameras require manual operation and limit continuous situational awareness. This study presents the design and field validation of a wearable helmet-mounted real-time thermal system based on the MLX90640 infrared array sensor and a Raspberry Pi 5 edge computing platform. Experimental validation was performed across multiple scenarios of 400 measurements based on industrial distances of 100 cm and 150 cm. The performance of the system was tested against a pre-calibrated hotspot infrared thermometer using linear regression analysis and standard error metrics to determine proportional agreement. The results indicate a strong proportional relationship between the two systems at both industrial distances, with R2 values ranging from 0.9885 to 0.9973 at 100 cm and from 0.9586 to 0.9867 at 150 cm. A moderate increase in mean absolute error (MAE) was observed as the measurement distance increased. Statistically significant increases in error were identified in mechanically dynamic scenarios where statistically significant increases in measurement error were observed (p-value < 0.05), indicating distance-dependent sensitivity under moving mechanical conditions. The higher absolute errors at longer distances mainly result from field-of-view expansion, reduced target occupancy, and mixed-pixel hotspot effects rather than weakened proportional trend stability. An industrial distance-aware linear regression model was developed to describe behavior and support calibrations under different deployment conditions. Despite minor absolute deviations during dynamic operations, the system maintained strong trend-tracking performance, suggesting suitability for daily preliminary hazard monitoring in industrial safety maintenance.

IoT doi: 10.3390/iot7020036

Authors: Jesús Rosa-Bilbao

Complex Event Processing (CEP) is essential for real-time analytics in domains such as industrial IoT, cybersecurity, and financial monitoring, yet CEP adoption is still hindered by the difficulty of authoring temporal rules and by rigid redeployment workflows. This paper presents PatternStudio, a neuro-symbolic CEP framework that translates natural language specifications into validated event-processing patterns and executes them on a deterministic Apache Flink-based runtime without interrupting service. The generative layer is constrained to produce a typed intermediate representation, while the symbolic layer enforces validation and runtime execution guarantees. We evaluate the prototype as a single-node system-characterization study on commodity hardware representative of edge and near-edge gateways rather than microcontroller-class devices. Under this setting, PatternStudio reaches 47,910 events per second at 250 active rules while maintaining a bounded memory footprint between 1.6 GB and 1.9 GB during the reported runs. Beyond 500 active rules, throughput degradation is driven primarily by CPU saturation and alert amplification, which also explains the sharp increase in tail latency. Additional measurements with parallelism 4, a static baseline, and a two-stage NL-to-IR evaluation further show that the architecture remains functional under partitioned execution, incurs moderate dynamic-orchestration overhead, preserves rule structure reliably under natural-language authoring, and supports interchangeable LLM backends at the semantic front end.

IoT doi: 10.3390/iot7020035

Authors: Hanshi Li Drishti Oza Masami Yoshida Taku Noguchi

Emergency vehicle authentication in vehicular ad hoc networks must satisfy strict latency, privacy, and trust constraints. Existing Public Key Infrastructure- and Conditional Privacy-Preserving Authentication-based schemes incur substantial overhead from certificate management and expensive per-hop verification, making them unsuitable for real-time emergency scenarios. We propose a lightweight zero-knowledge- and blockchain-assisted authentication scheme that eliminates certificates, pseudonym pools, and the requirement for online interaction with a trusted authority during the authentication phase. The Certificate Authority (CA) is involved only during offline initialization stages (vehicle enrollment and Merkle tree construction); once provisioning is complete, the runtime authentication process operates without any online CA interaction. Each emergency vehicle registers one-time hash commitments on-chain after proving membership in a category-specific Merkle tree, and authenticates messages by broadcasting a hash along with a zero-knowledge proof of preimage knowledge. Roadside units verify the proof and consult the on-chain state to enforce single-use semantics, creating a tamper-resistant audit trail. Evaluation using the Veins framework (OMNeT++/SUMO) demonstrated a constant 288-byte authenticated payload, millisecond-level end-to-end delay independent of hop count, and stable blockchain processing under sustained load.

IoT doi: 10.3390/iot7020034

Authors: Suleiman Zubair Bala Alhaji Salihu Altyeb Altaher Taha Yakubu Suleiman Baguda Ahmed Hamza Osman Asif Hassan Syed

The Mobile Reliable Opportunistic Routing (MROR) protocol improves data-forwarding reliability in Cognitive Radio Sensor Networks (CRSNs) through mobility-aware virtual contention groups and handover zoning. However, its heuristic decision logic is difficult to optimize under highly dynamic spectrum access and random node mobility. To address this limitation, we present DRL-MROR, a refined routing framework that incorporates deep reinforcement learning (DRL) to enable intelligent and adaptive forwarding decisions. In DRL-MROR, the secondary users (SUs) act as autonomous agents that observe local state information, including primary-user activity, link quality, residual energy, and neighbor-mobility patterns. Each agent learns a forwarding policy through a Deep Q-Network (DQN) optimized for long-term network utility in terms of throughput, delay, and energy efficiency. We formulate routing as a Markov Decision Process (MDP) and use experience replay with prioritized sampling to improve learning stability and convergence. The DQN used at each node is intentionally lightweight, requiring 5514 trainable parameters, about 21.5 kB of weight storage in 32-bit precision, and approximately 5.4k multiply-accumulate operations per inference, which supports practical deployment on edge-capable CRSN nodes. Extensive simulations show that DRL-MROR outperforms the original MROR protocol and representative AI-based routing baselines such as AIRoute under diverse operating conditions. The results indicate gains of up to 38% in throughput, 42% in goodput, a 29% reduction in energy consumed per packet, and an approximately 18% improvement in network lifetime, while maintaining high route stability and fairness. DRL-MROR also reduces control overhead by about 30% and average end-to-end delay by up to 32%, maintaining strong performance even under elevated PU activity and higher node mobility. These results show that augmenting opportunistic routing with lightweight DRL can substantially improve adaptability and efficiency in next-generation IoT-oriented CRSNs.

IoT doi: 10.3390/iot7020033

Authors: Sethu Subramanian N Prabu P Kurunandan Jain Prabhakar Krishnan

Smart-city IoT ecosystems depend on a large number of devices with limited resources, which often lack built-in security mechanisms. While traditional cloud-based or gateway-centric intrusion detection systems (IDSs) offer essential security, they are still characterized by high detection latency, considerable bandwidth demand, and a lack of precise monitoring of single device actions. This study proposes the Edge AI Bridge, a novel micro-computing security layer positioned between IoT devices and the gateway to enable early-stage threat interception. The architecture integrates embedded AI hardware with a hybrid pipeline, utilizing unsupervised anomaly detection for behavioral profiling and a lightweight signature-matching module to minimize false positives. System operations—including localized traffic inspection, protocol parsing, and feature extraction—are performed before data aggregation, which preserves device-level privacy and reduces the computational burden on the IoT gateway. The contemporary CIC-IoT-2023 dataset, which captures a wide range of smart-city protocols and attack vectors, is used to evaluate the architecture. The Edge AI Bridge leads to a significant reduction in detection latency—≈50 ms on average as opposed to the 500 ms of cloud-based solutions—while the resource footprint is kept low to about 20% CPU utilization. The Edge AI Bridge demonstrates a potential solution that is scalable, modular, and can preserve privacy while improving the cyber resilience of the smart-city infrastructures that are large, heterogeneous, and difficult to manage.

IoT doi: 10.3390/iot7020032

Authors: Shiva Kumar Mysore Gangadhara Krishna Alabhujanahalli Neelegowda Anitha Arekattedoddi Chikkalingaiah Naveena Chikkaguddaiah

The safety and reliability of railway wagon operations largely depend on the timely detection of degradation in safety-critical components such as axle bearings, wheelsets, and braking systems. Conventional maintenance strategies based on fixed inspection intervals are often inadequate for capturing the actual operating conditions of wagon components, leading to delayed fault detection or unnecessary maintenance actions. To address these limitations, this paper proposes a sensor-based health assessment framework for the continuous monitoring of railway wagons under operational conditions. The proposed framework integrates multi-sensor data acquisition, systematic signal preprocessing, feature-based health indicator construction, and temporal degradation analysis to evaluate component health in real time. A safety-oriented decision logic is employed to classify operating conditions and generate reliable alerts while minimizing false detections caused by transient disturbances. The effectiveness of the proposed approach is validated using a publicly available run-to-failure bearing dataset that exhibits degradation characteristics similar to those observed in railway wagon axle bearings. Experimental results demonstrate that the proposed framework achieves improved classification accuracy, higher detection reliability, reduced false alarm rates, and lower detection latency compared to representative existing condition monitoring approaches. In addition, the computational efficiency of the proposed model confirms its suitability for real-time deployment. The results indicate that the proposed health assessment framework provides a practical and reliable solution for safety-critical railway wagon monitoring and forms a strong foundation for future extensions toward predictive maintenance and remaining useful life estimation.

IoT doi: 10.3390/iot7020031

Authors: Gelare Oudi Ghadim Parvin Rastegari Mohammad Dakhilalian Faramarz Hendessi Shahrzad Saremi Rania Shibl Yassine Himeur Shadi Atalla Wathiq Mansoor

The Internet of Vehicles (IoV) is a rapidly evolving technology that provides real-time connectivity, enhanced road safety, and reduced traffic congestion; however, its inherently open communication channels expose it to serious security and privacy threats. In 2021, Chaudhry proposed SMEP-IoV, a lightweight message authentication protocol designed to satisfy essential security requirements. This paper presents a comprehensive security analysis of SMEP-IoV and reveals several serious vulnerabilities. Specifically, sensitive credentials are stored in plaintext without tamper-resistant protection, and both authentication and session key derivation depend directly on these credentials. These structural flaws allow an adversary to extract the stored secrets, generate valid authentication messages, and derive the established session key, enabling vehicle impersonation and session key disclosure attacks. Moreover, compromise of long-term secrets facilitates key compromise impersonation attacks. It also fails to ensure anonymity and perfect forward secrecy. To address these issues, we propose an enhanced authentication protocol for resource-constrained IoV environments, leveraging a three-factor authentication mechanism combined with lightweight cryptographic primitives. Formal security analyses using BAN logic, Tamarin, and ProVerif confirm its resilience against known attacks, while NS-3 simulations validate its scalability, high throughput, and low End-to-End Delay (E2ED). The results highlight the protocol as a robust, efficient, and scalable solution for large-scale IoV deployments.

IoT doi: 10.3390/iot7020030

Authors: Ning Wang Yali Ren

The proliferation of Internet of Things (IoT) devices has introduced significant security challenges. Resource-constrained devices face sophisticated threats but lack the computational capacity for advanced security analysis. This study investigates optimal security task allocation in Cognitive IoT (CIoT) networks. It specifically examines when IoT devices should process security tasks locally or offload them to Mobile Edge Computing (MEC) servers. The problem is formulated as a Continuous-Time Markov Decision Process (CTMDP). The study demonstrates that the optimal offloading policy has a threshold structure. Security tasks are offloaded to MEC servers when the offloading queue length is below a critical threshold, k∗. Otherwise, tasks are processed locally. This structural property is robust to changes in MEC server configurations and threat arrival patterns. It ensures an optimal and easily implementable security policy under the exponential model. Theoretical analysis establishes upper bounds on the performance of AI-based security controllers using the same models. The results also show that standard model-free Q-learning algorithms can recover optimal thresholds without any prior knowledge of the system parameters. Simulations across multiple reinforcement learning architectures, including Q-learning, State–Action–Reward–State–Action (SARSA), and Deep Q-networks (DQN), confirm that all methods converge to the predicted threshold. This empirically validates the analytical findings. The threshold structure remains effective under practical imperfections such as imperfect sensing and parameter estimation errors. Systems maintain 85% to 93% of their optimal performance. This work extends threshold Markov Decision Process (MDP) analysis from classical queuing theory to the context of CIoT security offloading. It provides optimal and practical policies and model-free algorithms for use by resource-constrained devices.

IoT doi: 10.3390/iot7010029

Authors: Ahmad Abuashour Yahia Jazyah Naser Zaeri

Wireless Sensor Networks (WSNs) commonly employ clustering to improve scalability and energy efficiency; however, cluster heads (CHs) located near the base station (BS) often suffer from excessive relay traffic, leading to rapid energy depletion and reduced network lifetime. This article proposes an Energy-Efficient Distance-Controlled Clustering (EEDC) scheme that adjusts CH density and transmission power according to each node’s distance from the BS. In EEDC, a higher number of CHs is deployed near the BS to balance forwarding loads, while fewer CHs are selected in distant regions to conserve energy. Additionally, CHs adapt their transmission power to enable distance-proportional communication. A mathematical model is developed to analyze the relationship between CH distribution, transmission power, and overall energy consumption. Performance evaluation is conducted through simulations and compared with LEACH, HEED, DEEC, SEP, and EECS. The results show that EEDC improves the stability period by up to 42%, extends network lifetime by 23%, increases average residual energy by 13–29%, enhances throughput by 16–44%, and achieves 23–61% higher packet delivery efficiency. Moreover, cumulative CH energy consumption is reduced by 5–21%, leading to more balanced energy distribution. These findings indicate that distance-controlled CH selection and adaptive transmission power effectively alleviate the BS energy bottleneck and enhance the energy efficiency and operational longevity of clustered WSNs.

IoT doi: 10.3390/iot7010028

Authors: Krit Funsian Yaowarat Sirisathitkul Pumiphat Khotchanakhen Apiwit Bunta Kanittha Srikwan Kingkan Bunluepuech Athakorn Promwee Chih-Yi Chiu Karanrat Thammarak

This study presents an Internet of Things (IoT)-assisted semi-open hydroponic system for cultivating Andrographis paniculata under tropical conditions, aiming to enhance biomass productivity, andrographolide (AG) yield, and production efficiency. IoT-assisted hydroponics, non-IoT hydroponics, and soil-based cultivation were compared in 10 m2 greenhouses. The IoT system enabled real-time monitoring and adaptive regulation of temperature, relative humidity, light intensity, nutrient solution pH, and electrical conductivity (EC). IoT-assisted hydroponics achieved earlier harvest (≈90 days) and the highest fresh biomass yield (0.409 ± 0.014 kg m−2) while maintaining per-plant productivity (15.74 ± 0.54 g plant−1) comparable to soil-based cultivation. Andrographolide concentration reached 25.58 ± 3.36 mg g−1 DW (2.56% w/w), meeting pharmacopeial requirements. Owing to stable environmental regulation and tolerance to high planting density, the IoT system produced the highest areal AG productivity (209.5 mg m−2), representing a four- to tenfold increase over the other systems. Despite higher operational costs, IoT-assisted hydroponics achieved the lowest AG unit cost (≈6.77 USD g−1). While most previous studies emphasize tissue-level AG concentration, system-level productivity and cost efficiency under realistic cultivation conditions remain insufficiently explored. Overall, IoT-enabled semi-open hydroponics provides a scalable and economically viable approach for medicinal plant production, bridging the gap between open-field cultivation and fully controlled plant factory systems.

IoT doi: 10.3390/iot7010027

Authors: Salvatore Bramante Filippo Ferrandino Alessandro Cilardo

The pervasive adoption of AI and AIoT applications at the network edge presents both opportunities and challenges for smart cities. With a focus on the energy efficiency of AI in urban environments, this paper provides a systematic comparative analysis of representative edge hardware platforms, i.e., embedded GPUs, FPGAs, and ultra-low-power microcontroller-/sensor-class devices, assessing their suitability for AI workloads in IoT-driven smart city infrastructures. The evaluation, based on direct characterization of diverse neural networks and relevant datasets, quantifies computational performance and energy behavior through inference latency, throughput, and energy/per inference measurements. Across the evaluated network–board pairs, the measured inference power spans several orders of magnitude, ranging from 0.1–10 mW for ultra-low-power Intelligent Sensor Processing Units (ISPUs) up to 1–10 W for embedded GPUs, highlighting the wide design space between the least and most power-demanding configurations. Results indicate that embedded GPUs provide a favorable performance-to-power ratio for computationally intensive workloads, while MCU/ISPU-class solutions, despite throughput limitations, offer compelling advantages in ultra-low-power scenarios when combined with quantization and pruning, making them well-suited for distributed sensing and actuation typical of smart city deployments. Overall, this comparative analysis guides hardware selection for heterogeneous, sustainable AI-enabled urban services.

IoT doi: 10.3390/iot7010026

Authors: Juan Castillo Pere Aran Vila Francisco Palacio Blas Garrido Sergi Hernández Albert Cirera

The continuous expansion of the Internet of Things (IoT) has intensified the need to evaluate and guarantee the quality of entropy sources used in random number generation, an essential element in securing communications used in IoT ecosystems. This work presents an automated and web-based framework designed to execute and analyze the results of statistical tests defined in the NIST SP 800-22 standard, enabling systematic assessment of entropy sources and random numbers generators in IoT devices and environments. The proposed system integrates a Python-based backend built upon an optimized implementation of the original NIST suite, along with an intuitive web interface that facilitates configuration, monitoring, and parallel execution of tests through Representational State Transfer (REST) endpoints. Session management based on Redis ensures reliable and concurrent operation of multiple users or devices while maintaining isolation and data integrity. To demonstrate its applicability, an emulated IoT ecosystem was implemented in which multiple virtual devices periodically and asynchronously request real-time validation of their local random numbers generators. The obtained results confirm the system’s capability to detect deficiencies in pseudo random generators and validate true random number sources, highlighting its potential as a diagnostic and verification tool for distributed IoT security systems. The tool developed in this work is fully accessible to the public, allowing researchers, engineers, and practitioners to evaluate random number generators without requiring specialized hardware or proprietary software.

IoT doi: 10.3390/iot7010025

Authors: Yutong Chen Daisuke Sumiyoshi Xiangyu Wang Takahiro Yamamoto Takahiro Ueno Jewon Oh

Occupant presence is a primary driver of Heating, Ventilation, and Air Conditioning (HVAC) and lighting energy consumption in office environments. Existing occupancy-sensing solutions often rely on privacy-sensitive modalities or require costly infrastructure, limiting their applicability in Small and Medium Offices (SMOs). To address these limitations, this study proposes a lightweight CSI-based occupancy-sensing framework based on a dual-core ESP32-S3 architecture, enabling concurrent CSI processing, environmental sensing, and cloud communication. A multi-stage signal preprocessing pipeline compresses raw CSI streams into a compact 56×8 statistical feature matrix, achieving 98.86% classification accuracy for multi-level occupancy estimation. Compared with image-based baselines such as DenseNet121, the proposed approach reduces input data size to 24 kB and model parameters to 138 K, yielding over 129× reduction in transmission volume without sacrificing performance. These results demonstrate that the proposed framework provides a practical, privacy-preserving, and edge-deployable solution for occupancy-aware energy management in SMOs.

IoT doi: 10.3390/iot7010024

Authors: Bakhan Tofiq Ahmed Noor Ghazi M. Jameel Bakhtiar Ibrahim Saeed

Malware’s proliferation in the Internet of Things (IoT) ecosystem requires precise, efficient detection systems capable of operating on IoT devices. Existing static analysis approaches often fail due to computational inefficiency stemming from high feature dimensionality inherent in raw opcode features. This research addresses this limitation by proposing a novel machine-learning (ML)-driven Intelligent Hybrid Feature Selection (IHFS) framework with two distinct architectures. IHFS1 combines a filter method (variance threshold) with an embedded method (LGBM feature importance). Conversely, IHFS2 integrates variance thresholding with a wrapper method (Recursive Feature Elimination with Cross-Validation using LGBM) for optimal selection. This framework is specifically designed to select an optimally stable and minimal feature subset from the initial 1183 opcode frequency vector extracted from ARM binaries. Applying this framework to a multi-family IoT malware dataset, the IHFS architectures yielded distinct and highly efficient feature subsets: IHFS1 achieved a 95.77% reduction (to 50 features), while IHFS2 attained a 98.06% reduction (to 23 features). Evaluation across eight ML models confirmed that the Random Forest (with IHFS1 subset) and Decision Tree (with IHFS2 subset) classifiers were the best performing, achieving robust classification metrics that outperform current state-of-the-art solutions. The Decision Tree model demonstrated exceptional detection capabilities, with an accuracy of 99.87%, a precision of 99.82%, a recall of 99.88%, and an F1-score of 99.85%. It achieved an average inference time of 0.058 ms per sample. Experimental results attained on a native ARM64 environment validate the deployment feasibility of the proposed system for resource-constrained IoT devices, such as the Raspberry Pi. The proposed system achieves a high-throughput, low-overhead security posture while maintaining host operational stability, processing a single ELF binary in just 3.431 ms.

IoT doi: 10.3390/iot7010023

Authors: Ernando P. Batista Alex Santos Maycon Peixoto Gustavo Figueiredo Cassio Prazeres

The growing demand for IoT applications in highly dynamic environments with multiple connected devices introduces significant scalability and low-latency challenges. In the context of software-defined networking (SDN) integrated with Edge environments, adopting machine learning (ML) techniques has emerged as a promising approach to meet these requirements. This study presents a Systematic Literature Review (SLR) that identifies and analyzes ML-based solutions applied to Software-Defined Internet of Things (SD-IoT) infrastructures in Edge environments, emphasizing improving low latency and scalability. Following established methodological best practices, we conducted the review, including a clear definition of research questions, well-defined inclusion and exclusion criteria, a structured search protocol, and multiple scientific databases. Based on the analysis of selected studies, the main strategies employed to enhance network performance are categorized, along with the level of fidelity and complexity of the experimental environments used, and the realism and applicability of the proposed solutions are discussed. Furthermore, drawing from the context of the selected studies, the most recurrent ML approaches are presented—including supervised, unsupervised, and reinforcement learning methods—along with a discussion of their advantages and limitations in dynamic network scenarios. By compiling and organizing the contributions from the literature, this paper provides a comprehensive overview of the state of the art in applying ML to SD-IoT networks, shedding light on current trends, existing gaps, and research opportunities aimed at building more intelligent and adaptable solutions for IoT environments.

IoT doi: 10.3390/iot7010022

Authors: Rendy Munadi Dadan Nur Ramadan Sussi Nurwulan Fitriyanti Hilal H. Nuha

Traffic congestion and travel time uncertainty remain major challenges to the operational efficiency of Bus Rapid Transit (BRT) systems in urban areas of developing countries. This study proposes an integrated solution for the Trans Metro Bandung (TMB) system by leveraging Internet of Things (IoT)–based GPS data and tree-based ensemble machine learning algorithms. Spatio-temporal data collected from on-board GPS modules are processed to predict traffic congestion levels and estimate travel time across route segments. The performance of Decision Tree, Random Forest, and XGBoost models is evaluated in terms of prediction accuracy, interpretability, and computational efficiency, with particular consideration for deployment on resource-constrained hardware. Experiments conducted on 20,156 data samples show that the Decision Tree model achieves the highest congestion classification accuracy of 96.8%, while Random Forest outperforms other models in travel time regression, achieving an R2 value of 0.95 and a root mean square error (RMSE) of 5.80 min. The trained models are successfully deployed on a Raspberry Pi 3B microcontroller for real-time inference, enabling fleet management and travel planning without reliance on cloud connectivity. The results demonstrate that cost-effective and interpretable machine learning solutions can deliver reliable performance in heterogeneous urban infrastructures while providing a replicable framework for medium-sized cities seeking to implement affordable smart transportation systems.

IoT doi: 10.3390/iot7010021

Authors: Bader Alobaywi Mohammed G. Almutairi Frederick T. Sheldon

Multi-tenancy is essential for scalable IoT–Cloud systems; however, it introduces complex security vulnerabilities at the intersection of shared cloud infrastructures and resource-constrained IoT environments. This systematic review evaluates next-generation security frameworks designed to enforce tenant isolation without violating the strict latency (<10 ms) and energy bounds of lightweight sensors. Adhering to PRISMA guidelines, we analyze selected high-quality studies to categorize intersectional threats, including cross-tenant data leakage, side-channel attacks, and privilege escalation. Our analysis identifies a critical, unresolved conflict: existing mitigation strategies often incur a 12% computational and communication overhead, creating a significant barrier for real-time applications. Furthermore, we critically analyze emerging technologies, including Zero Trust Architectures (ZTA), adaptive Artificial Intelligence (AI), blockchain, and Post-Quantum Cryptography (PQC). We find that direct PQC deployment is currently infeasible for LPWAN protocols due to key-size constraints (1.6 KB) that exceed typical payload limits. To address these challenges, we propose a novel multi-layer security design principle that offloads heavy isolation and cryptographic workloads to hardware-accelerated edge gateways, thereby maintaining tenant isolation without compromising real-time performance. Finally, this review serves as a roadmap for future research, highlighting federated learning and hardware enclaves as essential pathways for securing next-generation multi-tenant IoT ecosystems.

IoT doi: 10.3390/iot7010020

Authors: Shervin Mehryar

The prevalence of radio frequency signals in indoor environments has in recent years given rise to new technologies across many domains such as robotics, healthcare, and surveillance. Radio frequency signals propagate in the wireless medium through multiple paths and carry useful environment-dependent information. Capturing and analyzing these signal patterns can offer new solutions for a number of applications relevant to ranging, tracking, perception and recognition. In this work we propose a novel architecture, separating physical, back-bone networks, and inference layers, towards fully ubiquitous passive recognition systems that scale with the number of environments and applications. We propose a back-bone architecture that utilizes a novel Cross Dual-Path Attention (CDPA) block to capture spatial and temporal correlations from Channel State Information (CSI) for device-free, multi-task applications. Subsequently, a distill and transfer algorithm is proposed to generalize the inference capabilities of CDPA over multiple target environments for scalable training and reduced computational costs. By sharing knowledge between models across a shared network, experimentation shows that edge devices can be deployed with improved performance while simultaneously meeting strict computation and memory requirements. Our distributed learning paradigm demonstrates that CDPA-based models are capable of using passive signals in a non-intrusive and privacy-protecting manner, in order to achieve ubiquitous recognition at scale in smart environments.

IoT doi: 10.3390/iot7010019

Authors: Fazeleh Dehghani Ashkezari Andreas Jacobsson Kayode S. Adewole Klara Svalin Martin Höst

Smart homes are becoming increasingly common, bringing convenience to users but also raising serious security concerns. As the number of connected devices grows, so does the research interest in securing smart homes. However, the literature is broad, making it difficult to understand the main research directions and how they are connected. Given the scope and diversity of existing research, a systematic mapping study was chosen to provide a high-level overview of smart home security research by mapping research communities, identifying dominant themes, and examining their evolution over time. We retrieved articles from the Scopus database published between 2000 and April 2025, resulting in approximately 13,600 articles. After filtering out unrelated domains such as smart vehicles, smart industry, and general IoT, a final set of 6313 publications specifically focused on smart home security was used for analysis. We applied a citation-based network analysis approach, constructed an author citation graph, and used the Louvain community detection algorithm to identify 12 main research communities. Each community was further analyzed based on its keywords, most-cited publications, leading authors, and institutions. Our results provide a structured overview of the field, highlighting its key themes and evolution over time. This work can help researchers better navigate the smart home security landscape and identify future research opportunities.

IoT doi: 10.3390/iot7010018

Authors: Andric Rodríguez Asdrúbal López-Chau Leticia Dávila-Nicanor Víctor Landassuri-Moreno Saul Lazcano-Salas

Since the deployment of the Internet of Things (IoT), it has transformed everyday life by enabling intelligent environments that improve efficiency and automate services in domains such as agriculture, healthcare, smart cities, and industry. However, the rapid proliferation of IoT devices has introduced significant security challenges, largely driven by the heterogeneity of devices, resource constraints, and the increasing exposure of network communications. This work proposes a lightweight security protection mechanism for IoT networks based on trust modelling. The proposed approach integrates machine learning techniques to evaluate IoT node behavior using network-layer (Layer 3) traffic features under different labeling granularities, including binary, categorical, and subcategorical classifications. By focusing on network-layer observations, the model remains applicable across heterogeneous IoT devices while preserving a low computational footprint. In addition, the Common Vulnerability Scoring System (CVSS) is incorporated as a standardized vulnerability severity metric, enabling the integration of probabilistic security evidence with contextual information about potential impact. This combination allows the estimation of trust to reflect not only the likelihood of anomalous behavior but also its associated severity. Experimental evaluation was conducted using a representative IoT traffic dataset, multiple preprocessing strategies, and several classical machine learning models. The results demonstrate that aggregating traffic-based intrusion detection outputs with vulnerability severity metrics enables a more robust, flexible, and interpretable trust estimation process. This approach supports the early identification of potentially compromised nodes while maintaining scalability and efficiency, making it suitable for deployment in heterogeneous IoT environments.

IoT doi: 10.3390/iot7010017

Authors: Mohammed G. Almutairi Frederick T. Sheldon

Migrating to Post-Quantum Cryptography (PQC) is critical for securing resource-constrained Internet of Things (IoT) devices against the “harvest-now, decrypt-later” threat. While ML-KEM (CRYSTALS-Kyber) has been standardized under FIPS 203 for general encryption, these devices often operate on unreliable networks suffering from high latency and packet loss. Our recent systematic review identified a critical gap that existing research overwhelmingly focuses on Transport Layer Security (TLS). This leaves the resilience of lightweight protocols like MQTT and CoAP under challenging network conditions largely unexplored. This paper introduces PQC-IoTNet, a novel Software-in-the-Loop (SITL) framework to address this gap. Our three-tier architecture integrates a Python-based IoT client with kernel-level emulation to test the full protocol stack. Validation results comparing Kyber and ECC demonstrate the framework’s ability to capture critical performance cliffs caused by TCP retransmissions. Notably, the framework revealed that while Kyber maintained an 18% speed advantage over ECC at 5% packet loss, both protocols experienced nonlinear latency spikes. This work provides a reproducible blueprint to identify operational boundaries and select resilient protocols for secure IoT systems.

IoT doi: 10.3390/iot7010016

Authors: Suzan Sallam May El Barachi Nan Li

The rapid growth of the Internet of Things (IoT) has exposed billions of interconnected, heterogeneous, and resource-constrained devices to increasingly sophisticated threats. To evaluate the readiness of current intrusion detection systems (IDSs), this study reviews 32 recent IoT-IDS proposals spanning conventional, machine-learning, deep-learning, and hybrid approaches. Each system is assessed against 10 criteria that reflect practical IoT requirements, including real-time performance, latency, lightweight design, detection accuracy, mitigation capabilities, integrated detection-and-mitigation workflows, adaptability, resilience to advanced attacks, validation in realistic environments, and scalability. The results indicate that although many approaches achieve high detection accuracy, most do not meet real-time and lightweight thresholds commonly cited in IoT deployment literature. Mitigation features are often absent, adaptability is rarely implemented, and 29 out of 32 studies rely solely on offline datasets, thereby limiting confidence in their robustness to deployment. Scalability remains the most significant limitation, as none of the reviewed IDSs have tested their performance under realistic multi-node or high-traffic conditions, even though scalability is critical for large IoT ecosystems. Overall, the review suggests that future IoT IDS research should move beyond accuracy-focused models and toward lightweight, adaptive, and autonomous solutions that incorporate mitigation, support real-time inference, and undergo standardized evaluations under real-world operating conditions.

IoT doi: 10.3390/iot7010015

Authors: Tareq Khan

Gun violence in U.S. schools not only causes loss of life and physical injury but also leaves enduring psychological trauma, damages property, and results in significant economic losses. One way to reduce this loss is to detect the gun early, notify the police as soon as possible, and implement lockdown procedures immediately. In this project, a novel gun detector Internet of Things (IoT) system is developed that automatically detects the presence of a gun either from images or from gunshot sounds, and sends notifications with exact location information to the first responder’s smartphones using the Internet within a second. The device also sends wireless commands using Message Queuing Telemetry Transport (MQTT) protocol to close the smart door locks in classrooms and announce to act using public address (PA) system automatically. The proposed system will remove the burden of manually calling the police and implementing the lockdown procedure during such traumatic situations. Police will arrive sooner, and thus it will help to stop the shooter early, the injured people can be taken to the hospital quickly, and more lives can be saved. Two custom deep learning AI models are used: (a) to detect guns from image data having an accuracy of 94.6%, and (b) the gunshot sounds from audio data having an accuracy of 99%. No single gun detector device is available in the literature that can detect guns from both image and audio data, implement lockdown and make PA announcement automatically. A prototype of the proposed gunshot detector IoT system, and a smartphone app is developed, and tested with gun replicas and blank guns in real-time.

IoT doi: 10.3390/iot7010014

Authors: Brian Mulhern Chitra Balakrishna Jan Collie

Healthcare 5.0 and the Internet of Medical Things (IoMT) is emerging as a scalable model for the delivery of customised healthcare and chronic disease management, through Remote Patient Monitoring (RPM) in patient smart home environments. Large-scale RPM initiatives are being rolled out by healthcare providers (HCPs); however, the constrained nature of IoMT devices and proximity to poorly administered smart home technologies create a cyber risk for highly personalised patient data. The recent Network and Information Systems (NIS 2) directive requires HCPs to improve their cyber risk management approaches, mandating heavy penalties for non-compliance. Current research into cyber risk management in smart home-based RPM does not address scalability. This research examines scalability through the lens of the Non-adoption, Abandonment, Scale-up, Spread and Sustainability (NASSS) framework and develops a novel Scalability Index (SI), informed by a PRISMA guided systematic literature review. Our search strategy identified 57 studies across major databases including ACM, IEEE, MDPI, Elsevier, and Springer, authored between January 2016 and March 2025 (final search 21 March 2025), which focussed on cyber security risk management in the RPM context. Studies focussing solely on healthcare institutional settings were excluded. To mitigate bias, a sample of the papers (30/57) were assessed by two other raters; the resulting Cohen’s Kappa inter-rater agreement statistic (0.8) indicating strong agreement on study selection. The results, presented in graphical and tabular format, provide evidence that most cyber risk approaches do not consider scalability from the HCP perspective. Applying the SI to the 57 studies in our review resulted in a low to medium scalability potential of most cyber risk management proposals, indicating that they would not support the requirements of NIS 2 in the RPM context. A limitation of our work is that it was not tested in a live large-scale setting. However, future research could validate the proposed SI, providing guidance for researchers and practitioners in enhancing cyber risk management of large-scale RPM initiatives.

IoT doi: 10.3390/iot7010013

Authors: Daniel Ayo Oladele Ayokunle Ige Olatunbosun Agbo-Ajala Olufisayo Ekundayo Sree Ganesh Thottempudi Malusi Sibiya Ernest Mnkandla

Intrusion detection in IoT networks is challenged by data heterogeneity, label scarcity, and privacy constraints. Traditional federated learning (FL) methods often assume IID data or require supervised labels, limiting their practicality. We propose G-PFL-ID, a graph-driven personalized federated learning framework for unsupervised intrusion detection in non-IID IoT systems. Our method trains a global graph encoder (GCN or GAE) with a DeepSVDD objective under a federated regularizer (FedReg) that combines proximal and variance penalties, then personalizes local models via a lightweight fine-tuning head. We evaluate G-PFL-ID on the IoT-23 (Mirai-based captures) and N-BaIoT (device-level dataset) under realistic heterogeneity (Dirichlet-based partitioning with concentration parameters α∈{0.1,0.5,∞} and client counts K∈{10,15,20} for IoT-23, and natural device-based partitioning for N-BaIoT). G-PFL-ID outperforms global FL baselines and recent graph-based federated anomaly detectors, achieving up to 99.46% AUROC on IoT-23 and 97.74% AUROC on N-BaIoT. Ablation studies confirm that the proximal and variance penalties reduce inter-round drift and representation collapse, and that lightweight personalization recovers local sensitivity—especially for clients with limited data. Our work bridges graph-based anomaly detection with personalized FL for scalable, privacy-preserving IoT security.

IoT doi: 10.3390/iot7010012

Authors: Tina Babu Rekha R. Nair Balamurugan Balusamy Sumendra Yogarayan

The rapid expansion of Internet of Things (IoT)-enabled smart grids has intensified the need for reliable fault detection and autonomous self-healing under non-stationary operating conditions characterized by frequent concept drift. To address the limitations of static and single-strategy adaptive models, this paper proposes H-CLAS, a novel Hybrid Continual Learning for Adaptive Self-healing framework that unifies regularization-based, memory-based, architectural, and meta-learning strategies within a single adaptive pipeline. The framework integrates convolutional neural networks (CNNs) for fault detection, graph neural networks for topology-aware fault localization, reinforcement learning for self-healing control, and a hybrid drift detection mechanism combining ADWIN and Page–Hinkley tests. Continual adaptation is achieved through the synergistic use of Elastic Weight Consolidation, memory-augmented replay, progressive neural network expansion, and Model-Agnostic Meta-Learning for rapid adaptation to emerging drifts. Extensive experiments conducted on the Smart City Air Quality and Network Intrusion Detection Dataset (NSL-KDD) demonstrate that H-CLAS achieves accuracy improvements of 12–15% over baseline methods, reduces false positives by over 50%, and enables 2–3× faster recovery after drift events. By enhancing resilience, reliability, and autonomy in critical IoT-driven infrastructures, the proposed framework contributes to improved grid stability, reduced downtime, and safer, more sustainable energy and urban monitoring systems, thereby providing significant societal and environmental benefits.

IoT doi: 10.3390/iot7010011

Authors: Saugat Sharma Grzegorz Chmaj Henry Selvaraj

In Internet of Things (IoT) systems, data collected by geographically distributed sensors is often incomplete due to device failures, harsh deployment conditions, energy constraints, and unreliable communication. Such data gaps can significantly degrade downstream data processing and decision-making, particularly when failures result in the loss of all locally redundant sensors. Conventional imputation approaches typically rely on historical trends or multi-sensor fusion within the same target environment; however, historical methods struggle to capture emerging patterns, while same-location fusion remains vulnerable to single-point failures when local redundancy is unavailable. This article proposes a correlation-aware, cross-location data fusion framework for data imputation in IoT networks that explicitly addresses single-point failure scenarios. Instead of relying on co-located sensors, the framework selectively fuses semantically similar features from independent and geographically distributed gateways using summary statistics-based and correlation screening to minimize communication overhead. The resulting fused dataset is then processed using a lightweight KNN with an Iterative PCA imputation method, which combines local neighborhood similarity with global covariance structure to generate synthetic data for missing values. The proposed framework is evaluated using real-world weather station data collected from eight geographically diverse locations across the United States. The experimental results show that the proposed approach achieves improved or comparable imputation accuracy relative to conventional same-location fusion methods when sufficient cross-location feature correlation exists and degrades gracefully when correlation is weak. By enabling data recovery without requiring redundant local sensors, the proposed approach provides a resource-efficient and failure-resilient solution for handling missing data in IoT systems.

IoT doi: 10.3390/iot7010010

Authors: Tudor Covrig Adrian Duka Liviu Miclea

The predominant approach in the realm of industrial process monitoring and control involves the utilization of HMI (Human–Machine Interface) interfaces and conventional SCADA (Supervisory Control and Data Acquisition) systems. This limitation restricts user mobility, interaction with industrial equipment, and process status assessment. In the context of Industry 4.0, the ability to monitor and control industrial processes in real time is paramount. The present paper designs and implements a system for monitoring and controlling an industrial assembly line based on mixed reality. The technology employed to facilitate communication between the system and the industrial line is S7.Net. These elements facilitate direct communication with the industrial process equipment. The system facilitates the visualization of operating parameters and the status of the equipment utilized in the industrial process and its control. All data is superimposed on the physical environment through virtual operational panels. The system functions independently, negating the necessity for intermediate servers or other complex structures. The system’s operation is predicted on a series of algorithms. These instruments facilitate the automated analysis of industrial process parameters. These devices are utilized to ascertain the operational dynamics of the industrial line. The experimental results were obtained using a real industrial line. These models are employed to demonstrate the performance of data transmission, the identification of the system’s operating states, and the system’s ability to shut down in the event of operating errors. The proposed system is designed to function in a variety of industrial environments within the paradigm of Industry 4.0, facilitating the utilization of multiple virtual interfaces that enable user interaction with various elements through which the assembly process is monitored and controlled.

IoT doi: 10.3390/iot7010009

Authors: Jorge Rendulich Rony Almiron Xiomara Vilca Miguel Zea

The growing need to foster inclusive education in university environments has driven the development of technological solutions aimed at improving the academic experiences of students with disabilities. These individuals often face barriers to autonomy and participation, especially on large and complex campuses. This article presents the performance evaluation of a LoRaWAN network specifically designed for monitoring people with disabilities on a university campus. The system aims to provide equitable access to campus resources and real-time support to students with disabilities. Leveraging the advantages of Low-Power Wide-Area Networks (LPWAN), particularly LoRaWAN, the proposed system enables real-time tracking with broad coverage and minimal power consumption, without requiring any active user interaction. Each student receives a wearable LoRa-enabled device that wirelessly communicates with a network of gateways strategically installed throughout the campus. To evaluate the system’s performance, this work conducts link-level experiments focusing on the communication between the LoRa end devices (nodes) and the central gateway. The analysis focuses on the network coverage, signal strength (RSSI), signal-to-noise ratio (SNR), and packet reception rate (PRR). The experimental results confirmed that the proposed system is technically robust and operationally effective under real campus conditions. Beyond its technical contributions, the proposed solution represents a concrete step toward building safer and more accessible academic environments that reinforce the autonomy and inclusion of students with disabilities.

IoT doi: 10.3390/iot7010008

Authors: Xaver Zak Peter Brida Juraj Machaj

A low-power IPv6 mesh standard, Thread, is gaining traction in smart-home, building-automation, and industrial IoT deployments. It extends mesh connectivity with the help of Router-Eligible End Devices (REEDs), which can be promoted to, or demoted from, the router status. Promotion and demotion hinge on two tunable parameters, the router upgrade and the router downgrade thresholds. Yet the OpenThread reference stack ships with fixed values (16/23) for these thresholds. This paper presents a systematic study of how these thresholds shape router-election dynamics across diverse traffic loads and network topologies. Leveraging an extended OpenThread Network Simulator, a sweep through both router upgrade and router downgrade thresholds with different gaps was performed. Results reveal that the default settings may over-provision routing capacity and may result in increased frame retransmissions, wasting airtime and reducing energy efficiency.

IoT doi: 10.3390/iot7010007

Authors: Valters Skrastins Vladislavs Medvedevs Dmitrijs Orlovs Juris Ormanis Janis Judvaitis

Narrowband Internet of Things (NB-IoT) is widely used for connecting low-power devices that must operate for years without maintenance. To design reliable systems, it is essential to understand how much energy these devices consume under different conditions and which power sources can support long lifetimes. This study presents a detailed experimental evaluation of NB-IoT power consumption using a commercial System-on-Module (LMT-SoM). We measured various transmissions across different payload sizes, signal strengths, and temperatures. The results show that sending larger packets is far more efficient: a 1280-byte message requires about 7 times less energy per bit than an 80-byte message. However, standby currents varied widely between devices, from 6.7 µA to 23 µA, which has a major impact on battery life. Alongside these experiments, we compared different power sources for a 5-year deployment. Alkaline and lithium-thionyl chloride batteries were the most cost-effective solutions for indoor use, while solar panels combined with supercapacitors provided a sustainable option for outdoor applications. These findings offer practical guidance for engineers and researchers to design NB-IoT devices that balance energy efficiency, cost, and sustainability.

IoT doi: 10.3390/iot7010006

Authors: Berhanyikun Amanuel Gebreselassie Nuno M. Garcia Dida Midekso

The proliferation of mobile devices has driven significant growth in adaptive mobile applications (AMAs) that dynamically adjust their behavior based on contextual changes. While existing research has extensively studied individual adaptive systems, limited attention has been given to cooperative adaptation—where multiple AMAs coordinate their adaptive behaviors within shared mobile ecosystems. This systematic literature review addresses this research gap by analyzing 95 peer-reviewed studies published between 2010 and 2025 to characterize the current state of cooperative adaptation in mobile applications. Following established systematic review protocols, we searched six academic databases and applied rigorous inclusion/exclusion criteria to identify relevant studies. Our analysis reveals eight critical dimensions of cooperative adaptation: Monitor–Analyze–Plan–Execute–Knowledge (MAPE-K) structure, application domain, adaptation goals, context management, adaptation triggers, aspect considerations, coordination mechanisms, and cooperation levels. The findings indicate that 63.2% of studies demonstrate some form of cooperative behavior, ranging from basic context sharing to sophisticated conflict resolution mechanisms. However, only 7.4% of studies explicitly address high-level cooperative adaptation involving global goal optimization or comprehensive conflict resolution. Energy efficiency (21.1%) and usability (33.7%) emerge as the most frequently addressed adaptation goals, with Android platforms dominating the research landscape (36.8%). The review identifies significant gaps in comprehensive lifecycle support, standardized evaluation methodologies, and theoretical frameworks for multi-application cooperation. These findings establish a foundation for advancing research in cooperative adaptive mobile systems and provide a classification framework to guide future investigations in this emerging domain.

IoT doi: 10.3390/iot7010005

Authors: Petros Amanatidis Eleftherios Lyratzis Vasileios Angelopoulos Eleftherios Kouloumpris Efstratios Skaperdas Nick Bassiliades Ioannis Vlahavas Fotios Maris Dimitrios Emmanouloudis Dimitris Karampatzakis

In the 21st century, Urbanization, population growth, and climate change have created significant problems in water resource management. Recent advancements in technologies such as Internet of Things (IoT), Edge Computing (EC), Artificial Intelligence (AI), and Big Data Analytics (BDA) are changing the operations of the water resource management systems. In this study, we present a systematic review, highlighting the contributions of these technologies in water management systems. More specifically, we highlight the IoT and EC water monitoring systems that enable real-time sensing of water quality and consumption. In addition, AI methods for anomaly detection and predictive maintenance are reviewed, focusing on water demand forecasting. BDA methods are also discussed, highlighting their ability to integrate data from different data sources, such as sensors and historical data. Additionally, a discussion is provided of how Water management systems could enhance sustainability, resilience, and efficiency by combining big data, IoT, EC, and AI. Lastly, future directions are outlined regarding how state-of-the-art technologies may further support efficient water resources management.

IoT doi: 10.3390/iot7010004

Authors: Bruno Monteiro Jorge Granjal

The rapid expansion of Internet of Things (IoT) systems in critical infrastructures has raised significant concerns regarding network security and reliability. In particular, RPL (Routing Protocol for Low-Power and Lossy Networks), widely adopted in IoT communications, remains vulnerable to topological manipulation attacks such as Decreased Rank, Increased Rank, and the less-explored Worst Parent Selection (WPS). While several RPL security approaches address rank manipulation attacks, most assume static topologies and offer limited support for mobility. Moreover, trust-based routing and hybrid IDS (Intrusion Detection System) approaches are seldom integrated, which limits detection reliability under mobility. This study introduces a unified IDS framework that combines mobility awareness with trust-based decision-making to detect multiple rank-based attacks. We evaluate two lightweight, rule-based IDS architectures: a fully distributed model and a hybrid model supported by designated monitoring nodes. A trust-based mechanism is incorporated into both architectures, and their performance is assessed under static and mobile scenarios. Results show that while the distributed IDS provides rapid local responsiveness, the hybrid IDS maintains more stable latency and packet delivery under mobility. Additionally, incorporating trust metrics reduces false alerts and improves detection reliability while preserving low latency and energy usage, supporting time-sensitive applications such as healthcare monitoring.

IoT doi: 10.3390/iot7010003

Authors: Fouad Ailabouni Jesús-Ángel Román-Gallego María-Luisa Pérez-Delgado

Zero-day intrusions on IoT endpoints demand defenses that curtail attacker impact and persistence after breach. This article presents Fine-Grained Runtime Containment Agent (FG-RCA), a lightweight post-exploitation containment system that learns least-privilege behavior from execution and enforces it in the kernel via eBPF with Linux Security Modules (LSM). In a learn phase, LSM/eBPF probes stream security-relevant events to a Rust agent that synthesizes policies per device role. In an enforce phase, policies are compiled into eBPF maps and evaluated at an extended hook set spanning process execution (bprm_check_security), file access (file_open), network egress and exfiltration (socket_connect, socket_sendmsg), privilege use (capable), process injection (ptrace_access_check), tamper/anti-forensics (inode_unlink). Policies bind to kernel-truth identities—inode, device, mount intrusion detection system (IDS), executable SHA-256, and cgroup/namespace identifiers—rather than paths, mitigating time-of-check to time-of-use (TOCTOU) and aliasing. Operational safeguards include Ed25519-signed policies, atomic rollback, and shadow mode logging events to enable policy evolution. Evaluation on embedded Linux demonstrates containment with low overhead.

IoT doi: 10.3390/iot7010002

Authors: Rodrigo Aldana-López Omar Longoria-Gandara Jose Valencia-Velasco Javier Vázquez-Castillo Luis Pizano-Escalante

There is increasing interest in improving the reliability of short-range wireless links in dense IoT deployments, where BLE is widely used due to its low power consumption and robust GFSK modulation. For this purpose, this work presents a novel Orthogonal Space-Time (OST) scheme for transmission and detection of BLE signals while preserving the BLE GFSK waveform and modulation constraints. The proposed signal processing system integrates advanced OST coding techniques with nonlinear GFSK modulation to achieve high-quality communication while maintaining phase continuity. This implies that the standard BLE GFSK modulator and demodulator blocks can be reused, with additional processing introduced only in the multi-antenna encoder and combiner. A detailed theoretical analysis demonstrates the feasibility of employing the Rayleigh fading channel model in BLE communications and establishes the BER performance bounds for various MIMO configurations. Simulations confirm the advantages of the proposed OST-GFSK signal processing scheme, maintaining a consistent performance when compared with OST linear modulation approaches under Rayleigh fading channels. As a result, the proposed IoT-enabling technology integrates the advantages of widely used OST linear modulation with nonlinear GFSK modulation required for BLE.

IoT doi: 10.3390/iot7010001

Authors: Isaac Olayemi Olaleye Oluwafemi Olowojuni Asoro Ojevwe Blessing Jesús Rodríguez-Molina

The integrity of certification processes in the agrifood and fishing industries is essential for combating fraud, ensuring food safety, and meeting rising consumer expectations for transparency and sustainability. Yet, current certification systems remain fragmented, and they are vulnerable to tampering and highly dependent on manual or centralized procedures. This study addresses these gaps by providing a comprehensive survey that systematically classifies blockchain-based certification technologies and methodologies applied to the fisheries sector. The survey examines how the blockchain enhances trust through immutable record-keeping, smart contracts, and decentralized verification mechanisms, ensuring authenticity and accountability across the supply chain. Special attention is given to case studies and implementations that focus on ensuring food safety, verifying sustainability claims, and fostering consumer trust through transparent labeling. Furthermore, the paper identifies technological barriers, such as scalability and interoperability, and puts forward a collection of functional and non-functional requirements for holistic blockchain implementation. By providing a detailed overview of current trends and gaps, this study aims to guide researchers, industry stakeholders, and policymakers in adopting and optimizing blockchain technologies for certification. The findings highlight the potential of blockchain to innovate certification systems, easing the way for more resilient, sustainable, and consumer-centric agrifood and fishing industries.

IoT doi: 10.3390/iot6040078

Authors: Oleksandr Kuznetsov Saltanat Adilzhanova Serhiy Florov Valerii Bushkov Danylo Peremetchyk

The proliferation of Internet of Things (IoT) devices in financial markets has created distributed ecosystems where cryptocurrency exchanges, trading platforms, and market data providers operate as autonomous edge nodes generating massive volumes of sensitive financial data. Collaborative machine learning across these distributed financial IoT nodes faces fundamental challenges: institutions possess valuable proprietary data but cannot share it directly due to competitive concerns, regulatory constraints, and trust management requirements in decentralized networks. This study presents a privacy-preserving federated learning framework tailored for distributed financial IoT systems, combining differential privacy with Shamir secret sharing to enable secure collaborative intelligence across blockchain-based cryptocurrency trading networks. We implement per-layer gradient clipping and Rényi differential privacy composition to minimize utility loss while maintaining formal privacy guarantees in edge computing scenarios. Using 5.6 million orderbook observations from 11 cryptocurrency pairs collected across distributed exchange nodes, we evaluate three data partitioning strategies simulating realistic heterogeneity patterns in financial IoT deployments. Our experiments reveal that federated edge learning imposes 9–15 percentage point accuracy degradation compared to centralized cloud processing, driven primarily by data distribution heterogeneity across autonomous nodes. Critically, adding differential privacy (ε = 3.0) and cryptographic secret sharing increases this degradation by less than 0.3 percentage points when mechanisms are calibrated appropriately for edge devices. The framework achieves 62–66.5% direction accuracy on cryptocurrency price movements, with confidence-based execution generating 71–137 basis points average profit per trade. These results demonstrate the practical viability of privacy-preserving collaborative intelligence for distributed financial IoT while identifying that the federated optimization gap dominates privacy mechanism costs. Our findings offer architectural insights for designing trustworthy distributed systems in blockchain-enabled financial IoT ecosystems.

IoT doi: 10.3390/iot6040077

Authors: Dmitrijs Orlovs Artis Rusins Valters Skrastiņš Janis Judvaitis

Low Power Wide Area Networks (LPWAN) have emerged as essential connectivity solutions for the Internet of Things (IoT), addressing requirements for long range, energy efficient communication that traditional wireless technologies cannot meet. With LPWAN connections projected to grow at 26% compound annual growth rate until 2027, understanding real-world performance is crucial for technology selection. This review examines four leading LPWAN technologies—LoRaWAN, Sigfox, Narrowband IoT (NB-IoT), and LTE-M. This review analyzes 20 peer reviewed studies from 2015–2025 reporting real-world deployment metrics across power consumption, range, data rate, scalability, availability, and security. Across these studies, practical performance diverges from vendor specifications. In the cited rural and urban LoRaWAN deployments LoRaWAN achieves 2+ year battery life and 11 km rural range but suffers collision limitations above 1000 devices per gateway. Sigfox demonstrates exceptional range (280 km record) with minimal power consumption but remains constrained by 12 byte payloads and security vulnerabilities. NB-IoT provides robust performance with 96–100% packet delivery ratios at −127 dBm on the tested commercial networks, and supports tens of thousands devices per cell, though mobility increases energy consumption. In the cited trials LTE-M offers highest throughput and sub 200 ms latency but fails beyond −113 dBm where NB-IoT maintains connectivity. NB-IoT emerges optimal for large scale stationary deployments, while LTE-M suits high throughput mobile applications.

IoT doi: 10.3390/iot6040076

Authors: Karrar A. Yousif Jorge Calvillo-Arbizu Agustín W. Lara-Romero

Remote patient monitoring is a promising and transformative pillar of healthcare. However, deploying such systems at a scale—across thousands of patients and Internet of Medical Things (IoMT) devices—demands robust, low-latency, and scalable storage systems. This research examines the application of Fog Computing for remote patient monitoring in IoMT settings, where a large volume of data, low latency, and secure management of confidential healthcare information are essential. We propose a four-layer IoMT–Fog–Cloud architecture in which Fog nodes, equipped with graph-based databases (Neo4j), conduct local processing, filtering, and integration of heterogeneous health data before transmitting it to cloud servers. To assess the viability of our approach, we implemented a containerised Fog node and simulated multiple patient-device networks using a real-world dataset. System performance was evaluated using 11 scenarios with varying numbers of devices and data transmission frequencies. Performance metrics include CPU load, memory footprint, and query latency. The results demonstrate that Neo4j can efficiently ingest and query millions of health observations with an acceptable latency of less than 500 ms, even in extreme scenarios involving more than 12,000 devices transmitting data every 50 ms. The resource consumption remained well below the critical thresholds, highlighting the suitability of the proposed approach for Fog nodes. Combining Fog computing and Neo4j is a novel approach that meets the latency and real-time data ingestion requirements of IoMT environments. Therefore, it is suitable for supporting delay-sensitive monitoring programmes, where rapid detection of anomalies is critical (e.g., a prompt response to cardiac emergencies or early detection of respiratory deterioration in patients with chronic obstructive pulmonary disease), even at a large scale.

IoT doi: 10.3390/iot6040075

Authors: João Batista Firmino Junior Francisco Dantas Nobre Neto Bruno Neiva Moreno Tiago Brasileiro Araújo

The increasing availability of IoT-enabled mobility data and intelligent transportation systems in Smart Cities demands efficient and interpretable models for destination prediction. This study presents a comparative analysis between Markov Chains and Hidden Markov Models applied to urban mobility trajectories, evaluated through mean precision values. To ensure methodological rigor, the Smart Sampling with Data Filtering (SSDF) method was developed, integrating trajectory segmentation, spatial tessellation, frequency aggregation, and 10-fold cross-validation. Using data from 23 vehicles in the Vehicle Energy Dataset (VED) and a filtering threshold based on trajectory recurrence, the results show that the HMM achieved 61% precision versus 59% for Markov Chains (p = 0.0248). Incorporating day-of-week contextual information led to statistically significant precision improvements in 78.3% of cases for precision (95.7% for recall, 87.0% for F1-score). The remaining 21.7% indicate that model selection should balance model complexity and precision-efficiency trade-off. The proposed SSDF method establishes a replicable foundation for evaluating probabilistic models in IoT-based mobility systems, contributing to scalable, explainable, and sustainable Smart City transportation analytics.

IoT doi: 10.3390/iot6040074

Authors: Heyfa Ammar Asma Cherif

The proliferation of Internet of Medical Things (IoMT) devices in healthcare requires robust intrusion detection systems to protect sensitive data and ensure patient safety. While existing neural network-based Intrusion Detection Systems have shown considerable effectiveness, significant challenges persist—particularly class imbalance and high data dimensionality. Although various approaches have been proposed to mitigate these issues, their actual impact on detection accuracy remains insufficiently explored. This study investigates advanced Artificial Neural Network (ANN) architectures and preprocessing strategies for intrusion detection in IoMT environments, addressing critical challenges of feature dimensionality and class imbalance. Leveraging the WUSTL-EHMS-2020 dataset—a specialized dataset specifically designed for IoMT cybersecurity research—this research systematically examines the performance of multiple neural network designs. Our research implements and evaluates five distinct ANN architectures: the Standard Feedforward Network, the Enhanced Channel ANN, Dual-Branch Addition and Concatenation ANNs, and the Shortcut Connection ANN. To mitigate the class imbalance challenge, we compare three balancing approaches: the Synthetic Minority Over-sampling Technique (SMOTE), Hybrid Over-Under Sampling, and the Weighted Cross-Entropy Loss Function. Performance analysis reveals nuanced insights across different architectures and balancing strategies. SMOTE-based models achieved average AUC scores ranging from 0.8491 to 0.8766. Hybrid sampling strategies improved performance, with AUC increasing to 0.8750. The weighted cross-entropy loss function demonstrated the most consistent performance. The most significant finding emerges from the Dual-Branch ANN with addition operations and a weighted loss function, which achieved 0.9403 Accuracy, 0.8786 AUC, a 0.8716 F1-Score, 0.8650 Precision, and 0.8786 Recall. Compared to the related work’s baseline, it demonstrates a substantial increase in F1 Score by 8.45% and an improvement of 18.67% in AUC and Recall, highlighting the model’s superiority at identifying potential security threats and minimizing false negatives.

IoT doi: 10.3390/iot6040073

Authors: Haider Q. Mutashar Hiba A. Abu-Alsaad Sawsan M. Mahmoud

It is essential to assign the correct triage level to patients as soon as they arrive in the emergency department in order to save lives, especially during peak demand. However, many healthcare systems estimate the triage levels by manual eyes-on evaluation, which can be inconsistent and time consuming. This study creates a full Digital Twin-based architecture for patient monitoring and automated triage level recommendation using IoT sensors, AI, and cloud-based services. The system can monitor all patients’ vital signs through embedded sensors. The readings are used to update the Digital Twin instances that represent the present condition of the patients. This data is then used for triage prediction using a pretrained model that can predict the patients’ triage levels. The training of the model utilized the synthetic minority over-sampling technique, combined with Tomek links to lessen the degree of data imbalance. Additionally, Lagrange element optimization was applied to select those features of the most informative nature. The final triage level is predicted using the Tabular Prior-Data Fitted Network, a transformer-based model tailored for tabular data classification. This combination achieved an overall accuracy of 87.27%. The proposed system demonstrates the potential of integrating digital twins and AI to improve decision support in emergency healthcare environments.

IoT doi: 10.3390/iot6040072

Authors: Halit Uyanık Tolga Ovatman

Internet of Things (IoT) devices can be used to provide safety, security, and other services that ensure that smart systems work as intended. However, the increasing complexity of the tasks is increasing the potential of performance loss when limited resources are not utilized appropriately. Distributed complex event processing (CEP) applications can be used to execute multiple unique tasks on sensor data. Since these operations can require a variety of data from multiple sensors across separate task steps, non-optimal code and data management can lead to increased processing delays. In this study, a mathematical model for optimizing critical path performance across multiple independent CEP flows is proposed. The model optimally assigns both where codes are executed at, as well as where their respective data should be placed at. The proposed solution is implemented within an open source library with the inclusion of operator placement heuristics from the literature. Approaches are tested within a realistic smart-street scenario. Consumer delays, algorithm runtimes, and delivery ratios within different time windows are reported. The results indicate that the proposed approach can reduce the delivery times for the critical CEP paths better than the heuristic solutions, with the downside of increased optimization runtimes.

IoT doi: 10.3390/iot6040071

Authors: Ishara Dissanayake Anuradhi Welhenge Hesiri Dhammika Weerasinghe

The Internet of Things (IoT) has rapidly evolved into a central component of today’s technological landscape, enabling seamless connectivity and communication among a vast array of devices. It underpins automation, real-time monitoring, and smart infrastructure, serving as a foundation for Industry 4.0 and paving the way toward Industry 5.0. Despite the potential of IoT systems to transform industries, these systems face a number of challenges, most notably the lack of processing power, storage space, and battery life. Whereas cloud and fog computing help to relieve computational and storage constraints, energy limitations remain a severe impediment to long-term autonomous operation. Among the threats that exploit this weakness, the Denial-of-Sleep (DoSl) attack is particularly problematic because it prevents nodes from entering low-power states, leading to battery depletion and degraded network performance. This research investigates machine-learning (ML) and deep-learning (DL) methods for identifying such energy-wasting behaviors to protect IoT energy resources. A dataset was generated in a simulated IoT environment under multiple DoSl attack conditions to validate the proposed approach. Several ML and DL models were trained and tested on this data to discover distinctive power-consumption patterns related to the attacks. The experimental results confirm that the proposed models can effectively detect anomalous behaviors associated with DoSl activity, demonstrating their potential for energy-aware threat detection in IoT networks. Specifically, the Random Forest and Decision Tree classifiers achieved accuracies of 98.57% and 97.86%, respectively, on the held-out 25% test set, while the Long Short-Term Memory (LSTM) model reached 97.92% accuracy under a chronological split, confirming effective temporal generalization. All evaluations were conducted in a simulated environment, and the paper also outlines potential pathways for future physical testbed deployment.

IoT doi: 10.3390/iot6040070

Authors: Mohammed Rauf Ali Khan Abdulaziz Y. Barnawi Adnan Munir Zainab Alsalman Dario Marcelo Satan Sanunga

The rapid expansion of IoT devices has introduced significant security challenges, with malware authors constantly evolving their techniques to exploit vulnerabilities in IoT networks. Despite this growing threat, progress in developing effective detection solutions remains limited. In this study, we present an ML-based framework for detecting and classifying network threats targeting IoT environments. Using the CTU-IoT-Malware-Capture 2023 dataset and the UNSW Bot-IoT dataset, we transformed the task into a structured multi-class classification problem to better reflect real-world detection challenges. Our primary contribution lies in demonstrating the effectiveness of post-training quantization on gradient-boosted models, specifically a Quantized XGB variant enhanced with histogram-based quantization. This approach significantly reduces model size and inference time without sacrificing accuracy. The proposed model achieved high classification accuracies of 99.93% and 99.99% on the two datasets, while the quantization step led to 1.42× and 3× improvements in inference speed, and reductions in model size by 3.61× and 2.71×, respectively, making it well-suited for deployment in resource-constrained IoT settings. This work demonstrates not only the effectiveness of gradient boosting in handling complex traffic data but also introduces an efficient optimization strategy for real-time IoT threat detection.

IoT doi: 10.3390/iot6040069

Authors: Yevheniy Khomenko Sergii Babichev

Cloud-centric IoT frameworks remain dominant; however, they introduce major challenges related to data privacy, latency, and system resilience. Existing open-source solutions often lack standardized principles for scalable, local-first deployment and do not adequately integrate fault tolerance with hybrid automation logic. This study presents a practical and extensible local-first IoT architecture designed for full operational autonomy using open-source components. The proposed system features a modular, layered design that includes device, communication, data, management, service, security, and presentation layers. It integrates MQTT, Zigbee, REST, and WebSocket protocols to enable reliable publish–subscribe and request–response communication among heterogeneous devices. A hybrid automation model combines rule-based logic with lightweight data-driven routines for context-aware decision-making. The implementation uses Proxmox-based virtualization with Home Assistant as the core automation engine and operates entirely offline, ensuring privacy and continuity without cloud dependency. The architecture was deployed in a real-world office environment and evaluated under workload and fault-injection scenarios. Results demonstrate stable operation with MQTT throughput exceeding 360,000 messages without packet loss, automatic recovery from simulated failures within three minutes, and energy savings of approximately 28% compared to baseline manual control. Compared to established frameworks such as FIWARE and IoT-A, the proposed approach achieves enhanced modularity, local autonomy, and hybrid control capabilities, offering a reproducible model for privacy-sensitive smart environments.

IoT doi: 10.3390/iot6040068

Authors: Saman Abdanan Mehdizadeh Aghajan Bahadori Manocheher Ebadian Mohammad Hasan Sadeghian Mansour Nasr Esfahani Yiannis Ampatzidis

Subsoil compaction is a major constraint in sugarcane production, limiting yields and reducing resource-use efficiency. This study presents WireDepth, an innovative cloud-connected monitoring system that leverages edge computing and IoT technologies for real-time, spatially aware analysis and visualization of subsoiling depth. The system integrates ultrasonic, laser, inclinometer, and potentiometer sensors mounted on the subsoiler, with on-board microcontroller processing and dual wireless connectivity (LoRaWAN and NB-IoT/LTE-M) for robust data transmission. A cloud platform delivers advanced analytics, including 3D depth maps and operational efficiency metrics. System accuracy was assessed using 300 reference depth measurements, with Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE) calculated per sensor. The inclinometer and potentiometer achieved the highest accuracy (MAPE of 0.92% and 0.84%, respectively), with no significant deviation from field measurements (paired t-tests, p > 0.05). Ultrasonic and laser sensors exhibited higher errors, particularly at shallow depths, due to soil debris interference. Correlation analysis confirmed a significant effect of depth on sensor accuracy, with laser sensors showing the strongest association (Pearson r = 0.457, p < 0.001). Field validation in commercial sugarcane fields demonstrated that WireDepth improves subsoiling precision, reduces energy waste, and supports sustainable production by enhancing soil structure and root development. These findings advance precision agriculture by offering a scalable, real-time solution for subsoiling management, with broad implications for yield improvement in compaction-affected systems.

IoT doi: 10.3390/iot6040067

Authors: Hisham Abdul Karim Yassine Mohammed El Saleh Bilal Ezzeddine Nakhal Abdallah El Chakik

The exponential growth of Internet of Things (IoT) devices introduces significant security challenges due to their resource constraints and diverse attack surfaces. To address these issues, this paper proposes the Centralized Two-Tiered Tree-Based Intrusion Detection System (C2T-IDS), a lightweight framework designed for efficient and scalable threat detection in IoT networks. The system employs a hybrid edge-centralized architecture, where the first tier, deployed on edge gateways, performs real-time binary classification to detect anomalous traffic using optimized tree-based models. The second tier, hosted on a centralized server, conducts detailed multi-class classification to diagnose specific attack types using advanced ensemble methods. Evaluated on the realistic CIC-IoT-2023 dataset, C2T-IDS achieves a Macro F1-Score of up to 0.94 in detection and 0.80 in diagnosis, outperforming direct multi-class classification by 5–15%. With inference times as low as 6 milliseconds on edge devices, the framework demonstrates a practical balance between accuracy, efficiency, and deployability, offering a robust solution for securing resource-constrained IoT environments.

IoT doi: 10.3390/iot6040066

Authors: Adriel Henrique Monte Claro da Silva Mikaelle Karoline da Silva Augusto Santos Luis Arturo Gómez-Malagón

Ammonia is a gas primarily produced for use in agriculture, refrigeration systems, chemical manufacturing, and power generation. Despite its benefits, improper management of ammonia poses significant risks to human health and the environment. Consequently, monitoring ammonia is essential for enhancing industrial safety and preventing leaks that can lead to environmental contamination. Given the abundance and diversity of studies on Internet of Things (IoT) systems for gas detection, the main objective of this paper is to systematically review the literature to identify emerging research trends and opportunities. This review follows the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology, focusing on sensor technologies, microcontrollers, communication technologies, IoT platforms, and applications. The main findings indicate that most studies employed sensors from the MQ family (particularly the MQ-135 and MQ-137), microcontrollers based on the Xtensa architecture (ESP32 and ESP8266) and ARM Cortex-A processors (Raspberry Pi 3B+/4), with Wi-Fi as the predominant communication technology, and Blynk and ThingSpeak as the primary cloud-based IoT platforms. The most frequent applications were agriculture and environmental monitoring. These findings highlight the growing maturity of IoT technologies in ammonia sensing, while also addressing challenges like sensor reliability, energy efficiency, and development of integrated solutions with Artificial Intelligence.