Search Results (496)

Falls among the elderly and vulnerable populations represent a critical public health challenge, and camera-based visual sensor systems have emerged as a promising non-intrusive solution for continuous fall monitoring. However, deploying accurate fall detection on resource-constrained edge sensor nodes remains difficult due to the trade-off between model complexity and detection performance. In this paper, we propose WAD-YOLO, an efficient and lightweight fall detection algorithm tailored for visual sensor systems, based on wavelet transform and dynamic convolution. First, a wavelet transform convolution (WTConv) module is introduced to expand the receptive field of the visual feature extractor via cascaded wavelet decomposition, enabling the sensor-driven model to better capture low-frequency fall-related patterns without parameter explosion. Second, a dynamic upsample (DySample) operator is incorporated into the detection head to achieve content-aware, flexible upsampling by generating dynamic offsets, maintaining high efficiency suitable for real-time sensor data processing. Third, an adaptive downsampling (ADown) module is integrated to reduce spatial resolution while preserving semantic information, further reducing the computational burden for deployment on embedded sensor platforms. Experiments on the public Fall Detection dataset demonstrate that, compared with the baseline YOLOv11n, the proposed method increases precision P by 3.8%, mAP50 by 3.7%, and reduces the parameter count by 3.0 × 10${}^5$. The reduced parameter count and matched GFLOPs relative to YOLOv11n suggest that WAD-YOLO is a theoretically promising candidate for lightweight, high-accuracy fall detection on edge sensor platforms. Full article

Intrusion detection in IoT and IIoT networks must operate under tight resource constraints, yet most published machine learning-based IDS solutions report accuracy on held-out data without addressing whether the trained model can actually run on the target hardware. We address this gap with an end-to-end study spanning dataset preprocessing, model training, INT8 quantisation, and physical execution on two real microcontrollers. Five supervised classifiers—Logistic Regression, Decision Tree (depth 5), Random Forest, XGBoost, and LightGBM—plus an MLP deep learning baseline are evaluated on binary and ten-class intrusion detection tasks using the TON_IoT network dataset. A 5-fold stratified cross-validation confirms stable performance across splits, with LightGBM reaching $F_1=0.9993\pm 0.0001$. Models are then exported through three quantisation pipelines: m2cgen C code generation for the two lightest classifiers, TensorFlow Lite Micro full-integer INT8 for the MLP (9.34× size reduction to 13.03 KB), and a custom post-training INT8 binary format for XGBoost and LightGBM (18.91× compression for LightGBM to 73.85 KB). All five quantised models are deployed to an Arduino Mega 2560 (ATmega2560, 16 MHz, 8 KB SRAM) and an ESP32-C3 SuperMini (RISC-V, 160 MHz, 400 KB SRAM) and benchmarked on physical hardware across 500 timed inferences per model (250 per input class), with firmware predictions confirmed to match the Python 3.11 float model on both test vectors. The Decision Tree achieves 5.6 µs inference on the ESP32-C3; LightGBM INT8 ($F_1=0.9992$) provides the best accuracy–size trade-off among ensemble models. Cross-platform comparison reveals that the RISC-V device is 5.8–7.8× faster than the 8-bit AVR for identical model code. A cross-domain evaluation using CIC-IoT-Dataset2023 identifies large normalised distribution shifts (up to $\delta =5.95$ in packet asymmetry), quantifying the generalisation gap that remains an open challenge. Full article

To address the challenge of hand intrusion detection in frozen tuna cutting operations where operators wear thermal-insulating gloves, this study proposes a hand detection method based on dual-domain background modeling with absolute accuracy constraints. To tackle issues arising from low-resolution infrared arrays, such as defective pixels, random noise, and complex low-temperature backgrounds, a data preprocessing pipeline integrating defective pixel correction, exponential moving average (EMA), and median filtering is developed. A dual-domain background suppression (DDBS) strategy, combining spatial-domain and temporal-domain models with sensor absolute accuracy constraints, is employed to extract hand foregrounds under complex thermal conditions. Temperature thresholding, connected-component analysis, and hole-filling are further applied to effectively separate hands from frozen tuna. An experimental platform incorporating a Raspberry Pi 4B and an MLX90640 sensor was constructed, and a dataset comprising 1173 infrared frames was collected for validation purposes. Experimental results demonstrate that the proposed method achieves an accuracy of 94.12%, precision of 91.69%, recall of 97.55%, and F1-score of 94.53% for hand intrusion detection, with an average processing time of approximately 1.84 ms per frame. This provides a cost-effective, real-time solution for hand safety monitoring in frozen food processing operations. Full article

The Internet of Vehicles (IoV) is reshaping intelligent transportation through pervasive connectivity, real-time data exchange, cooperative perception, and vehicle–edge–cloud services, while also expanding cybersecurity and privacy risks across heterogeneous cyber–physical environments. This paper presents a PRISMA 2020-informed systematic review of IoV security and privacy protection research. A cross-layer and lifecycle-oriented analytical framework is developed by integrating a four-layer IoV architecture—sensing layer, network access layer, coordinative computing layer, and application layer—with a five-stage data lifecycle covering data collection, transmission, storage, usage, and disposal. Based on this framework, the paper examines representative threat surfaces, vehicle-to-everything (V2X) communication security, public key infrastructure (PKI) based authentication, trust management, privacy-preserving data sharing, intrusion detection, active defense, and AI-assisted security analytics. Privacy-preserving mechanisms, including differential privacy, federated learning, blockchain, homomorphic encryption, and secure multi-party computation, are further compared in terms of deployment layer, lifecycle stage, real-time suitability, and representative performance evidence. In addition, the review discusses the engineering relevance of UNECE WP.29 R155/R156, ISO/SAE 21434, and related national standards, with emphasis on compliance evidence, over-the-air (OTA) governance, supply-chain coordination, and lifecycle cybersecurity management. The review shows that no single protection mechanism can simultaneously satisfy the requirements of real-time performance, scalability, privacy preservation, trustworthiness, and regulatory compliance in dynamic IoV environments. Future research should emphasize lightweight and adaptive protection, cross-layer trust coordination, privacy–utility co-optimization, trustworthy AI-assisted security operations, and evidence-based lifecycle governance. This review provides a structured reference for researchers and a practical basis for secure and privacy-aware IoV system design. Full article

Intrusion detection serves as a core technology for securing heterogeneous edge networks, including IoT, industrial edges, and 5G networks. However, existing federated learning-based intrusion detection systems suffer from environmental heterogeneity, limited sample availability, and severe class imbalance—issues that result in inefficient resource allocation and compromised detection performance against rare attacks. In this paper, we propose a novel lightweight intrusion detection model for heterogeneous edge networks, named FedNIDS-CNN, which is based on dynamic distillation-aided federated learning with a CNN backbone. In the data preprocessing phase, a two-level class balancing strategy integrating nearest-neighbor interpolation augmentation and adaptive synthetic sampling is employed to ensure distortion-free sample synthesis. For feature and model optimization, principal component analysis (PCA) is used to reduce the dimensionality of traffic features, while a lightweight 1D-CNN is adopted as the base model to alleviate computational overhead on edge devices. During federated training and knowledge aggregation, a dynamic weight distillation loss mechanism is designed to enhance the model’s ability to recognize minority-class attacks. Meanwhile, the federated framework supports client-side local training and server-side weighted soft-label aggregation, enabling effective knowledge fusion across heterogeneous models. Experimental results on the CICIDS2017 dataset demonstrate that the proposed method achieves an accuracy of 98.55% and an F1-score of 98.40%. Benefiting from the soft-label transmission and parameter-free aggregation design, the framework gets rid of the constraint of homogeneous model architecture and natively supports heterogeneous network models and edge devices with different computing capabilities. It also significantly reduces communication traffic and per-round training latency, confirming its excellent real-time performance and applicability in resource-constrained edge environments. Full article

This study proposes a novel intrusion detection and response architecture that formulates network traffic analysis as a sequential decision-making problem rather than a static classification task. The architecture integrates a Transformer Encoder for temporal feature extraction with a Dueling Double Deep Q-Network (DDQN) to enable autonomous and risk-aware security decisions. Network flows are modeled within a Markov Decision Process, where the agent learns an optimal policy over a hierarchical action space consisting of IGNORE, LOG, ESCALATE, and BLOCK actions. To evaluate generalization capability, a transfer learning-based cross-domain adaptation strategy was employed. The CICIDS2018 and CICIoT2023 datasets were re-partitioned using a stratified 70/15/15 train/validation/test split. The proposed model achieved high detection performance on these datasets with F1-scores of 99.48% and 99.13%, respectively. After transfer learning to the AWID3 dataset, the model preserved strong generalization capability with F1-scores of 96.76% and 96.61%, demonstrating its robustness across wired, IoT, and wireless network environments. A risk-aware reward function is designed to balance detection accuracy and operational cost, while Integrated Gradients-based explainability is incorporated to analyze decision behavior. Experimental results further show that the proposed Transformer–DDQN framework achieves more stable learning, lower optimization loss, and more consistent action policies compared to alternative reinforcement learning-based approaches. The model operates with high computational efficiency while maintaining real-time processing capability in high-throughput network environments. Full article

Unauthorized plucking of flowers, fruits, and vegetables from residential plant beds is a recurring concern in urban and semi-urban household, causing damage to gardening resources, economic loss and inconvenience to sustainable gardening. To address this issue, the present study proposes an IoT-enabled Smart Residential Plant Bed Protection System (SRPBPS), which is the integration of motion sensors, plant disturbance sensors, a video monitoring unit, a microcontroller, a communication module, and an alarm mechanism for real-time intrusion detection and monitoring. The behaviour of the proposed system is analyzed using a continuous-time Markov modelling approach by considering various operational and failed states of system components. Important reliability measures, including system reliability, mean time to system failure (MTTF), and the expected number of failures over time, are evaluated analytically. In addition, sensitivity analysis of reliability and MTTF are carried out to identify the critical components influencing overall system performance. The obtained results provide useful insights into component-level impact on system effectiveness and support reliability-oriented design enhancement. The proposed framework contributes toward the development of intelligent, secure, and sustainable residential plant bed protection systems for modern residential environments. Full article

Microfinance institutions (MFIs) are vital in promoting financial inclusion for underserved populations. However, these institutions face growing security threats, including sophisticated burglary tactics like underground tunneling. In the Philippines, notable incidents, such as the “Termite Gang” heist in Marikina City and a mall robbery in Ozamiz, highlight the limitations of conventional security systems in addressing subterranean intrusions. This study addresses the gap in existing security technologies by developing a real-time detection system that integrates a vibration sensor, a Global System for Mobile Communications (GSM) module for sending real-time SMS alerts, an audible alarm, and a solar-powered backup system for continuous operation. The system was simulated in the electrical technology laboratory to enhance classroom learning. The system’s core is an Arduino Uno microcontroller that processes inputs from the SW-420 vibration sensor, activating alarms and triggering SMS notifications via the SIM900A module when it detects unusual vibrations. Simulations A, B, and C were conducted to evaluate the system’s response time, with results showing a progressive reduction in detection time from five seconds to one second, indicating improved calibration and system efficiency. These findings also support the existing literature on user interaction with vibration alerts, demonstrating high accuracy in interpreting haptic notifications and the cognitive trade-offs involved. The proposed solution offers a proactive, energy-resilient, and cost-effective security system specifically designed to address underground burglary attempts. It applies to MFIs, pawnshops, and other high-risk financial environments. Future research should explore the application of machine learning for adaptive threat detection, expand the system’s scalability, and integrate mobile applications to enable user customization and enhance alert management. Full article

The growing sophistication of the internet and web space has spawned highly dynamic, multi-vector cyber threats that cannot be handled by automated detectives and hence the necessity to introduce analyst-oriented, cognitively powerful security analysis apparatus. The character of current visualization-based security frameworks is that they are inclined to deliver data unproactively, fail to engage the dynamic setting, and fail to comprehend the evolving motive of assailants, resulting in subsequent identification and a fractured understanding of coordinated web attacks. The paper introduces a new model of interactive security visualization known as Context-Oriented Visual Exploration of Resilient Threats (COVERT), a hybrid of behavioral context modeling, adaptive visual storytelling, and intent-sensitive interaction. COVERT is dynamically rearranged to the development of threats, patterns of interaction between analysts, and objectives of the possible attacks, which helps in releasing relevant security capabilities gradually. The framework integrates graphical threat flows, attention-directed visual cues, and real-time feedback loops to align system responses to the thinking processes of the analysts. The evaluation of high-scale web traffic and attack simulation dataset indicates that COVERT is much more effective in the multi-stage detection of attacks, false-positive interpretation is minimized, and the investigation period is reduced compared to the visualization infrastructure of the static and semi-interactive infrastructure. According to user studies, there is higher situation awareness, enhanced correlation of distributed events, and enhanced decision-making in complex web intrusion situations, such as advanced persistent threats and web exploitation coordination. Combining contextual intelligence with adaptive interaction and visualization of security, COVERT reveals that intent-based visual analytics may greatly improve internet and web threat detection and analysis systems to support more agile and resilient cyber defense procedures. The proposed COVERT strategy achieved 93% threat-detection rate, the false positives were reduced to 6%, the response time of the analysts was reduced to 140 s, and the situational awareness was increased to 88%. Full article

The rapid proliferation of Narrowband Internet of Things (NB-IoT) devices necessitates robust, privacy-preserving intrusion detection systems. While Federated Learning (FL) mitigates data privacy risks through localized training, it introduces vulnerabilities to model poisoning and computational bottlenecks on edge devices. To address these challenges, we propose a secure, hardware-optimized Blockchain-Federated Learning (BC-FL) framework. Deploying a lightweight Hybrid CNN-RNN model on Edge Gateways, we relieve end-sensors of heavy computational tasks. To overcome the ‘cold-start’ problem, we introduce a Domain-Adaptive Transfer Learning strategy, dynamically adapting a pre-trained binary classifier to a multi-class task (Normal, Mirai, Bashlite). Furthermore, a lightweight blockchain ledger provides an immutable audit trail and a reputation-based isolation mechanism to penalize malicious nodes. Evaluated on the N-BaIoT dataset, the proposed 3-class CNN-RNN model achieves 95.62% overall accuracy, with precision/recall/F1-scores of 0.99/0.91/0.95 for Mirai and 0.93/0.99/0.96 for Bashlite attacks. The framework reduces communication bandwidth by 96% compared to centralized learning. During simulated Byzantine attacks, the reputation mechanism successfully banned malicious nodes, maintaining a robust 95.62% global accuracy. This framework offers a highly scalable, secure, and computationally feasible solution for real-time anomaly detection in resource-constrained IoT edge environments. Full article

Deep learning-based intrusion detection systems offer world-class accuracy in threat classification. They are also generally not easily explainable to security analysts, which represents a major hurdle in their use in real-world Security Operations Centers (SOCs) where explainability and trust are critical. This operational challenge is tackled with a systems-engineered approach combining the CNN-LSTM architecture with the computationally optimized SHAP and LIME approaches for enabling real-time, interpretable threat detection. Unlike novel mathematical formulations, we concentrate on practical innovations in systems engineering that we believe are required to generate explanations in real-time: quantization of the numbers to INT8, execution of explanation algorithms in parallel, asynchronously, and caching of similar traffic patterns. CNN-LSTM combines the convolutional function to capture spatial dependencies and the recurrent function to capture temporal dynamics of network traffic, and SHAP and LIME capture global and local feature attributions, respectively. One of the major innovations is the parallel execution which brings the latency of explanation down from 117 ms (sequential SHAP + LIME) to 46 ms (parallel, cache-miss) and 39 ms (average with caching) and 46 ms (without caching), which is sufficient for operational “real-time” requirements. The framework is evaluated on CICIDS2017 and NSL-KDD benchmark datasets, and results show that it can achieve 98.7% accuracy with 98.6% F1-score and sub-50 ms explanation latency. The results here show that explainability and operational efficiency can be attained with the same level of accuracy in the detection of abnormal events, through careful systems engineering. This paper presents a systems-engineered framework demonstrating the feasibility of real-time, interpretable IDS for deployment in Security Operations Centers (SOCs) and addresses the challenges of combining high-performance deep learning with operational transparency in cybersecurity. Full article

Intrusion Detection Systems (IDSs) remain essential for securing modern network infrastructures, where traffic data are often high-dimensional and contain redundant or weakly informative attributes. This study proposes a hybrid feature selection approach that combines Information Gain with L1-regularized selection to construct a compact and informative representation of the UNSW-NB15 dataset. The method applies relevance-based filtering followed by sparsity-driven refinement within a leakage-aware pipeline, in which preprocessing and feature selection are derived exclusively from the training data. Under a reduced six-class configuration, the proposed approach reduces 42 candidate predictors to 21 traffic-related features. Across multiple classifiers, Random Forest + IGL1 achieved the best performance, with an accuracy of 0.8432 and an F1-score of 0.8376, while MLP and Gradient Boosting also remained competitive. These findings indicate that the selected features preserve consistent discriminative patterns rather than favoring a single classifier. Overall, the study highlights the importance of leakage-aware evaluation for producing reliable, reproducible intrusion detection results. Future work will extend the analysis to the full multi-class setting and examine applicability in real-time or streaming environments. Full article

Chloride and sulfate ion attacks are among the leading causes of deterioration in reinforced concrete structures, leading to the corrosion of steel reinforcement, expansion, cracking, and premature structural failure. Early detection of these ion-induced deteriorations is essential not only for maintaining safety but also for supporting sustainability objectives by extending service life, reducing material consumption, and minimizing carbon-intensive repairs. This review synthesizes current advances in non-destructive testing (NDT) techniques used to identify and quantify the impacts of chloride and sulfate ions in reinforced concrete. The mechanisms of ion ingress and their associated degradation processes are examined together with the operating principles, strengths, and limitations of key NDT methods, including electrical resistivity, acoustic emission, infrared thermography, ground penetrating radar, and ultrasonic pulse velocity. By enabling timely maintenance decisions and reducing unnecessary demolition or intrusive testing, these NDT methods contribute directly to sustainable infrastructure management. Through comparative analysis and real-world case studies, the paper highlights the most effective NDT applications for deterioration scenarios and outlines emerging innovations that enhance accuracy, data interpretation, and long-term monitoring capabilities. The findings demonstrate how advancements in NDT support the development and preservation of durable and sustainable concrete structures. Full article

Intrusion detection on in-vehicle networks requires high accuracy, which is reported by many papers so far, but also computational efficiency to make it suitable for real-world scenarios. The achievement of both requirements at the same time becomes harder to achieve, especially as the number of attacks diversifies. An approach to leverage computational costs is the use of sliding windows, i.e., batch processing, which extends the detection over multiple frames, but the use of multitask learning is also advantageous because a number of layers are shared between classes to extract common relevant features. While indeed the greatest computational gains are from the use of a sliding window, multitask learning has benefits too and is in fact necessary as multiple attack types can coexist in the same window. We explore the benefits of this approach on three existing attack datasets and we also build our own dataset that garners more attack complexity so that we can concretely measure the benefits of multitask learning both in terms of detection rate and computational savings. Our approach considers the feature-level similarity between attack types and legitimate frames, extracted from the mutual information between the two, and extends detection over windows of multiple frames, which justify multitask learning as frames belonging to different classes can co-exist in the same window. Full article

With the rapid expansion of rail transit networks and increasing operational density, foreign object intrusion on tracks has emerged as a critical threat to train safety. Conventional manual inspection methods suffer from low efficiency, high miss rates, and inadequate real-time performance, failing to meet the stringent requirements of modern intelligent railway maintenance. While deep learning offers a promising paradigm shift, existing models often struggle with complex background interference and multi-scale target detection in railway scenarios. To address these challenges, this paper proposes CMF-Net, a unified detection framework for railway track foreign object detection. The CGG module serves as a lightweight feature extraction unit in the backbone, mitigating gradient vanishing and overfitting. The MSAF module enables adaptive multi-scale feature fusion via dual attention (CBAM), enhancing small-object detectability. The FGAF module captures fine-grained edges and textures through a four-branch decomposed convolution and fine-grained attention, suppressing complex background interference. The BiFPN module restructures the neck for efficient bidirectional cross-scale feature fusion. Furthermore, the TPSA module injects explicit railway-domain prior knowledge by fusing a learnable rail-centerline distance-decay field with the CBAM spatial attention map, guiding the detector to focus on operational danger zones and reducing false positives. Experiments on the OFBDs dataset demonstrate that CMF-Net achieves a mean Average Precision (mAP50) of 89.2% and an mAP50:95 of 64.5%, surpassing the baseline YOLOv5s by 4.8 pp and 5.3 pp, respectively. The model maintains a compact parameter size of 5.4 M, a computational cost of 15.2 GFLOPs, and real-time inference capability (56.2 FPS). Edge-deployment feasibility is validated via on-device benchmarking on three Jetson platforms (Nano, Xavier NX, and Orin Nano), where INT8 TensorRT inference achieves 16.2, 108.7, and 153.8 FPS, respectively, under one-hour continuous-inference soak tests with peak power below 16 W and steady-state junction temperatures within safe thermal margins. Statistical significance testing (p < 0.05) confirms the stability of these performance gains. These results indicate that CMF-Net provides rapid and accurate detection of various track intrusions, enabling robust real-time monitoring in dynamic railway environments and enhancing operational safety and intelligence. Full article