Search Results (3,474)

Rural digitization in the management of woody crops like olive orchards lags significantly behind the technological benchmarks established in other highly digitized sectors. We propose a modular Digital Twin (DT) framework that implements a multi-scale data fusion strategy integrating satellite, UAV-based hyperspectral/LiDAR sensing, and IoT devices. This study addresses a primary technological bottleneck: the high computational cost and disk I/O latency inherent in the real-time fusion and analysis of high-dimensional spectral data and dense 3D geometries. Conventional geospatial software often fails to provide real-time interactivity for these massive datasets due to frequent memory swapping. We designed the system’s core as a high-performance C++17engine (GEU), which leverages innovative data structures (Meanlets and Meshlets) to enable real-time 3D interaction and spectral “picking” directly in main memory. Experimental validation demonstrates that this approach eliminates I/O bottlenecks, providing instantaneous feedback on datasets exceeding typical memory limits. Additional modules round out the DT’s functionality. Furthermore, the integrated AI module achieves a strategic 8-month lead time for early crop yield estimation with absolute errors below 20%. The model also demonstrates high precision, reaching overall accuracies of 90.19% for Arbequina and 88.04% for Picual cultivars using 1D CNNs. Finally, ubiquitous mobile applications empower farmers as “human actuators” in the cyber–physical cycle. This framework establishes a replicable methodology for the digital transformation of the Mediterranean agricultural sector. Full article

Software-Defined Networking (SDN) centralizes control logic, improving programmability but exposing the controller to volumetric and low-rate Distributed Denial of Service (DDoS) attacks. Entropy-based detectors often raise late alarms or require significant traffic distribution changes, while machine-learning approaches impose high training and inference overhead. To address these issues, this work proposes a Statistical Mean Renyi Entropy (SMRE)-based early-warning system that amplifies micro-level disturbances in flow randomness using a tunable sensitivity weight (μ). The formulation enhances responsiveness to entropy deviations without adding computational complexity, enabling O(n) single-pass execution per monitoring window. The method was implemented on a Mininet testbed (nine switches, 64 hosts, POX controller with the L3_learning module) with mixed benign traffic and hping3/Scapy-generated UDP and TCP flood attack traffic at intensities ranging from 10 to 75%. Experimental results demonstrate that SMRE detects early-stage attacks with 94.7–98.1% accuracy, 0.8–2.3% false positive rate, and 6.5–14 ms detection latency, outperforming Shannon and classical Renyi entropy detectors. ROC analysis (AUC ≈ 0.99) and paired t-tests (p < 0.01) confirm statistical significance. Resource profiling shows negligible CPU and memory overhead, supporting real-time deployment. By eliminating model training and ensuring robust early detection, SMRE offers a lightweight and practical detection mechanism for SDN environments, whose applicability to cloud, edge, and IoT deployments will be further substantiated through validation on real traffic traces and multi-controller architectures. Full article

Machine learning techniques for network-based intrusion detection systems (NIDS) have advanced considerably over the past decade. Still, improvements are inhibited by handcrafted feature pipelines, isolated public benchmark data, and evaluation procedures that do not reflect real-life deployment. AutoML, a branch of ML automating model selection, automated architecture search, and the creation of model pipelines, may help overcome these shortcomings. While numerous NIDS applications employing automated ML techniques have been proposed, and recent surveys have mapped the AutoML framework landscape for network intrusion detection, no existing review critically audits the evaluation practice of this literature: the quality of its benchmark datasets, the reproducibility of its reported results, and the realism of its deployment assumptions. This paper critically reviews 26 research works published between January 2023 and June 2026, collected via a two-phase structured search: a documented keyword search across five databases (Scopus, IEEE Xplore, Web of Science, ACM Digital Library, and Google Scholar), followed by full-text eligibility screening, citation chaining, and expert evaluation. Findings drawn from this collection capture trends observed among the selected studies, rather than reflecting the broader state of the field. Analysis of the corpus reveals that 88% of dataset-verified studies evaluate exclusively or partly on the legacy benchmark family (KDD-derived, CICIDS, UNSW-NB15, CIDDS), 21% evaluate on a single dataset only, and among attribute-verified studies only 32% release source code, 40% report statistical significance testing, and 36% include variance analysis, findings that collectively motivate the four contributions of this study. First, a recommended evaluation framework is proposed, addressing baseline parity, transparent search-space and budget reporting, nested cross-validation for selection-bias control, and stability reporting across multiple random seeds. Second, a dataset quality scoring framework is introduced, assessing five dimensions: overlap rate, duplication rate, label correctness, attack-type representativeness, and coverage of benign, IoT, and IIoT traffic. Third, a cross-domain justification is provided for neural architecture search (NAS) and meta-learning in NIDS, grounded in advances in federated NAS, out-of-distribution robustness, edge-constrained search cost reduction, and few-shot adaptation. Fourth, a structured research roadmap is outlined, targeting real-world validation, standardized benchmarks, curated datasets, resource-aware AutoML, and privacy-preserving federated NAS. In contrast to prior surveys of AutoML for network intrusion detection, which map frameworks and computational paradigms, this review contributes a formalized evaluation checklist, an explicit and partially empirically validated dataset quality scoring scheme, and evidence-based methodological guidance grounded in a transparent, fully enumerated study corpus. Full article

This systematic review summarises advances in artificial intelligence (AI) and machine learning (ML) for foodborne pathogen detection, covering applications in various technologies (AI-assisted microscopy, spectroscopy, biosensors and sensor-based systems), food supply chains, analytical performance, operational metrics and regulatory developments, addressing gaps in previous reviews limited to individual technologies or lacking regulatory analysis. Following PRISMA 2020 guidelines, Scopus, PubMed, and Web of Science were searched from 1 January 2010 to 25 June 2026 using a validated string. Inclusion criteria were explicit detection of a pathogen, clearly described AI/ML algorithm, study evaluation on food or supply chains, and quantitative validation metrics. Exclusion criteria were chemical-only studies, human-diagnostic studies, or purely theoretical studies. Given heterogeneity in the evidence, qualitative quality indicators were favoured over formal quantitative risk-of-bias tools, in distinction to internal cross-validation versus independent external validation. Key data were extracted using a standardised matrix, and after screening and snowballing, the final corpus consisted of 152 studies. CNN (Convolutional Neural Network)-based microscopy provides >99% accuracy in bacterial identification, SERS (Surface-Enhanced Raman Spectroscopy) and CNN 98.68% for pathogens and 99.85% for resistant strains. ML-driven biosensors show 80–100% prediction accuracy in the presence of environmental noise. Yet, performance drops dramatically on external validation, with models falling from 95% internal to 78–82% on independent test sets. Supply chain applications cover meat, dairy, seafood and produce, but most are still at pilot scale. The main constraints are data heterogeneity, lack of public benchmarks, matrix interference, non-standard validation protocols, and regulatory dissonance. However, the integration of AI with Internet of Things (IoT), blockchain and edge computing improves sensitivity, reduces false results and enables real-time monitoring despite the challenges. AI is a powerful decision-support tool that complements existing food safety controls rather than replacing them. To translate these technologies reliably into routine practice, effective implementation requires rigorous external validation and regulatory harmonisation. Full article

The rapid development and expansion of the Internet of Things (IoT) ecosystem require managing increasing computational demands with the aid of advanced hierarchical architectures. The integration of a complete four-tier hierarchy—including Mobile, Edge, Fog, and Cloud layers—and the priority requirements are being overlooked in the literature despite the effort of existing studies. The goal of this study is to fill these gaps by proposing a novel, context-aware task-offloading framework designed for multi-dimensional ecosystems involving multi-server and multi-application environments. A targeted biomimetic approach is utilized at the core of this research. The decentralized foraging behavior of biological swarms is translated into a concrete engineering solution. This solution is designed specifically for computational offloading and resource management. To achieve this, a “Learning-guided Meta-heuristic” hybrid model is developed. Within this framework, bio-inspired Ant Colony Optimization (ACO) is directly integrated with an Upper Confidence Bound (UCB)-inspired exploration mechanism. Natural, pheromone-based imitation is solely relied upon by traditional biomimetic algorithms. In contrast, higher-order cognitive learning is fully incorporated by this hybrid synergy. Consequently, underlying system dynamics are adaptively learned. Local minima traps are also successfully avoided. This avoidance is achieved by dynamically selecting the optimal layer for each individual task. Both energy consumption and latency are optimized simultaneously. Meanwhile, strict operational feasibility is ensured through a dynamic penalty-based mechanism. Battery and deadline constraints are explicitly handled by this mechanism. Extensive simulations demonstrate the superiority of the proposed UCB-ACO model over state-of-the-art meta-heuristics, including Particle Swarm Optimization (PSO), Gray Wolf Optimizer (GWO), ACO, Artificial Bee Colony Optimization (ABO), and Non-dominated Sorting Genetic Algorithm II (NSGA-II). The findings reveal that the proposed framework outperforms the methods compared by achieving 22.5% lower latency and 23% lower energy consumption. This study effectively maps the current literature and then introduces a pioneering solution for next-generation resource management in distributed computing. Full article

The increasing deployment of Internet of Things (IoT) service platforms has motivated the development of queueing models capable of capturing congestion, retrials, and service interruptions. This paper investigates an M/M/1 retrial queue with balking and feedback during working vacations, where a central processing unit or gateway handles requests from a large number of smart devices. Customer arrivals are modeled as a Poisson process and receive immediate service when the server is idle, and otherwise either balk or join an orbit from which customers retry for service after a random time interval. The server enters a vacation whenever the system becomes empty and provides service at a reduced rate during working vacations. In addition, after the completion of service during a working vacation, customers may either leave the system or rejoin the orbit, representing feedback. Probability generating function (PGF) techniques are employed to analyze the system’s steady-state performance, and explicit expressions for important performance measures are obtained. Numerical experiments are presented to illustrate and validate the analytical findings. The results provide insights into the impact of working vacations, balking, and feedback on system performance and demonstrate the applicability of the proposed model to IoT-based service environments. Full article

Classical coherent chaos shift keying (CSK) provides certain physical-layer advantages by exploiting chaotic waveforms, but it relies on fragile chaos synchronization, which is difficult to maintain in multipath fading channels. To overcome this limitation, we propose a novel non-coherent CSK detector based on the spectral centroid (SC)—the center of mass of the power spectral density. We demonstrate that the SC is an intrinsic invariant of a chaotic map, enabling a fixed-threshold detection scheme that requires no synchronization, no reference sequence, and no channel estimation. Simulation results over multipath Rayleigh fading channels show that the proposed system significantly outperforms conventional CSK pairs. Unlike coherent CSK, which suffers from an error floor under frequency-selective fading, the proposed SC-CSK system benefits from frequency diversity and achieves robust performance. Moreover, while conventional differential chaos shift keying (DCSK) degrades severely under high-mobility scenarios, the proposed system maintains a stable BER across a wide range of Doppler shifts. The receiver is lightweight, interpretable, and well-suited for resource-constrained applications such as Internet of Things (IoT) devices. Full article

Internet of Things (IoT) environments, which are distributed and resource-constrained, present unique security challenges, making it essential to develop robust and transparent intrusion detection system (IDS) solutions. This study presents a specialized system for IoT environments that combines hybrid feature selection methods with anomaly detection algorithms and classification strategies, alongside explainability techniques, to enhance security measures and event transparency. The novelty of this work lies in combining several modern approaches: hybrid feature selection by combining Random Forest (RF) and SelectKBest to reduce computational overhead while preserving high accuracy of detection; the application of Deep Autoencoders (DAEs) for detecting anomalous traffic deviating from learned normal behavior, enabling detection of previously unseen attack patterns under controlled experimental conditions; feedforward neural networks (FNNs) are applied to classify anomalous data with high accuracy and reduced training time, and explainability tools such as Shapley Additive Explanations (SHAP) and Local Interpretable Model-Agnostic Explanations (LIME) are incorporated to provide insights into model decisions and improve trust. We utilize the CIC-IDS2017 and EIIoT datasets to evaluate their effectiveness in identifying critical cyber threats and subsequently classifying them. This proposed framework, HDATL-XAI (Hybrid Dimension-reduction Autoencoder and Traditional Learning with Explainable Artificial Intelligence), integrates advanced techniques to offer comprehensive protection while ensuring transparency, enhancing security and trustworthiness, and serving as an essential tool for protecting IoT networks. Full article

The rapid proliferation of the Internet of Things (IoT) has transformed industries by enabling seamless interconnectivity among devices, applications, and networks. However, this widespread adoption has also introduced significant security vulnerabilities, exposing IoT ecosystems to cyber threats such as unauthorized access, data breaches, and large-scale cyber-attacks. As IoT technology continues to evolve, mitigating these vulnerabilities remains a complex and pressing challenge. In this context, penetration testing, which is also known as pen testing, serves as a proactive security measure, enabling organizations to identify and address potential weaknesses before they can be exploited by malicious actors. Penetration testing for IoT systems is a specialized security assessment that addresses the unique vulnerabilities of interconnected devices, networks, and communication protocols, differing significantly from traditional computing and network penetration testing methodologies. In this regard, this study presents a review of penetration testing as a critical methodology for identifying, assessing, and mitigating security risks in IoT environments. We examine the key steps, tools, and methodologies specifically designed for IoT penetration testing, demonstrating their applicability across diverse infrastructures through a simple case study. Further, this study also proposes a novel Artificial Intelligence (AI)-enabled automated conceptual framework, AutoAIPenTest, that integrates machine learning, reinforcement learning, and large language models to perform intelligent, real-time security assessments in dynamic IoT ecosystems. Our findings highlight the critical role of proactive security measures, including structured penetration testing, secure development practices, and regulatory compliance, in strengthening the resilience of the IoT ecosystem. By discussing existing challenges and proposing effective security strategies, this study contributes to ongoing efforts to secure IoT domains and ensure that technological advancements do not come at the expense of cybersecurity. Full article

This paper presents the development and experimental validation of a low-cost IoT-enabled turbidity monitoring platform intended for laboratory-scale bioprocess applications. The proposed system was designed as a modular turbidity acquisition subsystem that can be integrated into broader bioreactor automation platforms. The hardware architecture is based on an ESP8266 microcontroller, a TS-300B optical turbidity sensor, a resistive voltage divider for analog signal conditioning, an OLED display for local visualization, and a Google Sheets-based cloud logging solution. A blank-based relative Turbidity Index was defined in order to compensate for optical configuration and environmental variations. The embedded firmware implements multi-sample averaging, blank calibration, serial command control, local display updates, CSV logging, and optional cloud transmission through HTTP requests. The calibration procedure was performed using serial dilutions of a yeast suspension, and the obtained data were fitted using a nonlinear power-law model and a log-log representation. An additional comparison with OD600 reference measurements showed a monotonic relationship between the proposed Turbidity Index and conventional optical-density measurements. The system was further validated through a yeast-based monitoring experiment performed under consistent optical conditions. The results showed the capability of the platform to acquire, process, visualize, and store turbidity-related data over an extended interval. The proposed platform provides a practical, affordable, and reproducible solution for turbidity monitoring and IoT-based data acquisition in small-scale bioprocess applications. Full article

This study investigates the application of Artificial Neural Network (ANN), Long Short-Term Memory network (LSTM) as a representative of Recurrent Neural Network (RNN), and one-dimensional Convolutional Neural Network (1D-CNN) for time series prediction, demonstrated through a use case of low-cost gas sensor readings from transient signals. Despite the widespread use of these architectures in IoT forecasting applications, there is a lack of systematic comparative studies that evaluate their performance under identical experimental conditions, particularly in energy-constrained sensing scenarios. The primary objective is to evaluate the trade-offs between model accuracy, computational cost, and memory requirements under energy-efficient data acquisition scenarios. A comprehensive experimental analysis was conducted using 186 recorded transient samples, where all models were trained and evaluated under consistent preprocessing, identical data splits, and uniform hyperparameter settings. Performance was assessed using RMSE, MAE, $R^2$, training time, and model size as key evaluation metrics under varying input sequence lengths. The results show that the LSTM model achieved the highest accuracy, with an RMSE of 3.69%, $R^2$ of 0.85 and scaled MAE of 0.04, effectively capturing long-term temporal dependencies. The 1D-CNN exhibited a balanced compromise between accuracy and training efficiency, while the ANN provided the shortest training time but lower overall performance. Reducing the number of input readings from 186 to as few as 10–20 resulted in only a 2–4% increase in RMSE, with model size reductions of up to 50%, making such configurations particularly suitable for edge or embedded IoT devices. The findings demonstrate that artificial neural networks can maintain high prediction accuracy even under reduced data conditions, contributing to the development of low-power, resource-efficient sensing systems for intelligent and distributed IoT environments. Full article

With the rapid advancement of the IoT society and growing awareness of environmental issues, thermoelectric conversion technology—which directly converts waste heat into electricity—is gaining attention as a self-powered, autonomous power source capable of driving countless devices. While currently mainstream metal-based inorganic thermoelectric materials demonstrate high performance, their high rigidity and brittleness, as well as their frequent inclusion of toxic heavy metals, have limited their application in biological systems and on curved surfaces. As a next-generation alternative, single-walled carbon nanotubes (SWCNTs)—which possess excellent flexibility, electrical conductivity, and mechanical strength while being low in toxicity—are garnering significant attention. However, n-type SWCNT materials, which are essential for thermoelectric module fabrication, have faced two major barriers to practical application: low atmospheric stability (they easily revert to p-type upon exposure to atmospheric oxygen and moisture) and thermoelectric performance that falls short of inorganic materials. This review comprehensively outlines the latest composite approaches designed to overcome these critical challenges and achieve both extreme atmospheric stability and high thermoelectric performance in n-type SWCNT materials, along with the flexibility required to withstand severe deformation. Three main strategies are discussed. The first is the organic/polymer approach, which involves doping with organic small molecules that control the LUMO level or bicyclic organic superbases with strong electron-donating properties, as well as polymer coating, to achieve long-term stable n-type characteristics and high power output even in air or under severe high-temperature conditions. The second is the inorganic hybrid strategy, which involves nanoscale compositing with inorganic materials such as Bi₂Te₃ and Cu₂O; this reduces thermal conductivity through phonon scattering via interface control, while the inorganic layer physically blocks oxygen to ensure long-term atmospheric stability. The third approach involves ultra-long-term stabilization techniques, such as bulk encapsulation using cationic or gemini surfactants, and environmentally friendly aqueous processes utilizing natural amino acids. Furthermore, we discuss the latest developments in imparting practical-level toughness (flexibility) capable of withstanding thousands of bending cycles and high tensile stress through the introduction of dynamic covalent network polymers and elastomers. The conformal flexible thermoelectric power generation modules created through the integration of composite optimization, low-environmental-impact processes, and doping techniques will serve as a crucial foundational technology for realizing a sustainable next-generation electronics society, including future wearable devices, artificial skin, and smart sensor networks. Full article

The rapid development of Internet of Things (IoT)-enabled healthcare systems, including wearable medical sensors and remote patient monitoring devices, has led to dense multiuser communication scenarios in which numerous low-power devices simultaneously transmit physiological data. In such environments, multiuser interference significantly degrades reliability and increases error rates, which may compromise clinical decision-making. This paper proposes a real-time symmetric Independent Component Analysis (ICA)-based Code Division Multiple Access (CDMA) receiver, termed symmetric independent CDMA (i-CDMA) receiver, to enhance multiuser detection in dense healthcare IoT networks. Unlike conventional ICA-CDMA receivers that utilize the orthogonality of users’ spreading codes and higher-order statistics (HoS) of users’ message symbols in signal separation, the proposed approach utilizes a symmetric independence process that jointly utilizes the independence of separating codes and the statistical independence of users’ message symbols. The proposed receiver avoids the runtime optimization of scaling parameter for different user densities and SNR conditions. Furthermore, a modified whitening transform is introduced to exploit the complete signal-plus-noise subspace while avoiding overlearning. Simulation results demonstrate significant performance improvement over symmetric Gram–Schmidt orthogonalization-based standard ICA-CDMA receiver in terms of bit error rate (BER) under varying SNR and user-density scenarios for both uplink and downlink systems. The proposed receiver provides a scalable and interference-resilient communication framework suitable for real-time IoT-enabled healthcare monitoring applications. Full article

Wireless Internet-of-Things (IoT) data acquisition is an emerging instrumentation paradigm for nuclear and particle physics facilities, offering a flexible complement to established wired architectures based on VME, CAMAC, and OPC-UA. Despite growing deployment activity, the evidence base remains fragmented. It is spread across conference proceedings, technical notes, and journal publications in instrumentation, nuclear science, and telecommunications. This scoping review systematically maps the evidence on wireless IoT DAQ in this context, following the PRISMA Extension for Scoping Reviews (PRISMA-ScR) framework. A structured search of IEEE Xplore, Scopus, Web of Science, and the CERN Document Server, covering publications from 2015 to 2025, identified 47 papers meeting eligibility criteria after screening. LoRaWAN^® dominates current deployments, appearing in 72% of identified systems, driven by its infrastructure independence and sub-GHz propagation characteristics suited to shielded environments. Radiation monitoring at Large-Hadron-Collider-scale facilities is the most evidence-rich application domain; cyclotron equipment health monitoring is the most active non-CERN domain. Five priority evidence gaps are identified: empirical RF propagation data for African geological formations, long-term total-ionising-dose degradation data from deployed nodes, standardised wired-to-wireless DAQ integration interfaces, sub-millisecond wireless synchronisation, and documentation of Global South facility deployments. The review is grounded in direct operational experience across ATLAS/CERN detector instrumentation, the Dolosse DAQ framework at NRF–iThemba LABS, and the proposed Paarl Africa Underground Laboratory (PAUL). Full article

Smart campus development is increasingly associated with the combined use of IoT technologies, artificial intelligence, cloud infrastructures, and large-scale data analytics in higher education. Despite this progress, many existing data models are not well-suited to the educational domain, particularly when interoperability and real-time analytical capabilities are required. To address this limitation, the study proposes a Smart Campus Education Data Model (SCEDM), which can be integrated into any FIWARE-based platform. The model is organized as a layered architecture that includes data acquisition, processing, and storage; analytics and decision support; application presentation; and security. The proposed model is not presented only at a conceptual level; it is also validated in a containerized FIWARE environment built around the Orion-ld Context Broker and NGSI-ld specifications. The SCEDM model is validated in a system that supports real-time state management across multiple campus domains. The model’s practical operation is validated across several experimental scenarios, including a simulation of a lecture process, classroom occupancy monitoring, and automated notifications to external platforms. In addition, the study compares five international case studies from different contexts. The comparison shows that, despite differences across local settings, similar benefits can be observed in campus operations and learning conditions. The study also recognizes several continuing challenges in the development of smart campuses, including interoperability, long-term scalability, data governance, privacy protection, stakeholder engagement, and financial sustainability. In response to these issues, the authors propose practical design guidelines alongside strategic recommendations for adoption at the institutional level. Full article