Search Results (813)

Ensuring hygiene compliance in regulated environments—such as food processing facilities, hospitals, and public indoor spaces—requires reliable detection of personal protective equipment (PPE) usage, including gloves, face masks, and hairnets. Manual inspection is labor-intensive and unsuitable for continuous, real-time enforcement. This study benchmarks three lightweight object detection models—YOLOv8n, YOLOv10n, and YOLOv12n—for automated PPE compliance monitoring using a large curated dataset of over 31,000 annotated images. The dataset spans seven classes representing both compliant and non-compliant conditions: glove, no_glove, mask, no_mask, incorrect_mask, hairnet, and no_hairnet. All evaluations were conducted using both detection accuracy metrics (mAP@50, mAP@50–95, precision, recall) and deployment-relevant efficiency metrics (inference speed, model size, GFLOPs). Among the three models, YOLOv10n achieved the highest mAP@50 (85.7%) while maintaining competitive efficiency, indicating strong suitability for resource-constrained IoT-integrated deployments. YOLOv8n provided the highest localization accuracy at stricter thresholds (mAP@50–95), while YOLOv12n favored ultra-lightweight operation at the cost of reduced accuracy. The results provide practical guidance for selecting nano-scale detection models in real-time hygiene compliance systems and contribute a reproducible, deployment-aware evaluation framework for computer vision in hygiene-critical settings. Full article

Modern subway platforms are generally equipped with platform screen door systems to enhance safety, but the gap between the platform screen doors and train doors may cause passengers or objects to become trapped, leading to accidents. Addressing the issues of excessive parameter counts and computational complexity in existing foreign object intrusion detection algorithms, as well as false positives and false negatives for small objects, this article introduces a lightweight deep learning model based on YOLOv11n, named GA-YOLOv11. First, a lightweight GhostConv convolution module is introduced into the backbone network to reduce computational resource waste in irrelevant areas, thereby lowering model complexity and computational load. Additionally, the GAM attention mechanism is incorporated into the head network to enhance the model’s ability to distinguish features, enabling precise identification of object location and category, and significantly reducing the probability of false positives and false negatives. Experimental results demonstrate that in comparison to the original YOLOv11n model, the improved model achieves 3.3%, 3.2%, 1.2%, and 3.5% improvements in precision, recall, mAP@0.5, and mAP@0.5: 0.95, respectively. In contrast to the original YOLOv11n model, the number of parameters and GFLOPs were reduced by 18% and 7.9%, respectfully, while maintaining the same model size. The improved model is more lightweight while ensuring real-time performance and accuracy, designed for detecting foreign objects in subway platform gaps. Full article

Unlike traditional control systems that rely on physical input devices, facial gesture-based interaction offers a contactless and intuitive method for operating autonomous systems. Recent advances in computer vision and deep learning have enabled the use of facial expressions and movements for command recognition in human–robot interaction. In this work, we propose a lightweight, real-time facial gesture recognition method, GhostNet-BiLSTM-Attention (GBA), which integrates GhostNet and BiLSTM with an attention mechanism, is trained on the FaceGest dataset, and is integrated with a 3D robot simulation in Unity. The system is designed to recognize predefined facial gestures such as head tilts, eye blinks, and mouth movements with high accuracy and low inference latency. Recognized gestures are mapped to specific robot commands and transmitted to a Unity-based simulation environment via socket communication across machines. This framework enables smooth and immersive robot control without the need for conventional controllers or sensors. Real-time evaluation demonstrates the system’s robustness and responsiveness under varied user and lighting conditions, achieving a classification accuracy of 99.13% on the FaceGest dataset. The GBA holds strong potential for applications in assistive robotics, contactless teleoperation, and immersive human–robot interfaces. Full article

Existing building management systems face critical limitations in real-time data integration, primarily relying on static models that lack dynamic updates from IoT sensors. To address this gap, this study proposes a novel system integrating MQTT over WebSocket with Three.js visualization, enabling real-time sensor-data binding to Building Information Models (BIM). The architecture leverages MQTT’s lightweight publish-subscribe protocol for efficient communication and employs a TCP-based retransmission mechanism to ensure 99.5% data reliability in unstable networks. A dynamic topic-matching algorithm is introduced to automate sensor-BIM associations, reducing manual configuration time by 60%. The system’s frontend, powered by Three.js, achieves browser-based 3D visualization with sub-second updates (280–550 ms latency), while the backend utilizes SpringBoot for scalable service orchestration. Experimental evaluations across diverse environments—including high-rise offices, industrial plants, and residential complexes—demonstrate the system’s robustness: Real-time monitoring: Fire alarms triggered within 2.1 s (22% faster than legacy systems). Network resilience: 98.2% availability under 30% packet loss. User efficiency: 4.6/5 satisfaction score from facility managers. This work advances intelligent building management by bridging IoT data with interactive 3D models, offering a scalable solution for emergency response, energy optimization, and predictive maintenance in smart cities. Full article

We propose an edge-enhanced federated learning framework for real-time itinerary optimization in elderly oriented adventure tourism, addressing the critical need for adaptive scheduling that balances activity intensity with health constraints. The system integrates lightweight convolutional neural networks with a priority-based scheduling algorithm, processing participant profiles and real-time biometric data through a decentralized computation model to enable dynamic adjustments. A modified Hungarian algorithm incorporates physical exertion scores, temporal proximity weights, and health risk factors, then optimizes activity assignments while respecting physiological recovery requirements. The federated learning architecture operates across distributed edge nodes, preserving data privacy through localized model training and periodic global aggregation. Furthermore, the framework interfaces with transportation systems and medical monitoring infrastructure, automatically triggering itinerary modifications when vital sign anomalies exceed adaptive thresholds. Implemented on NVIDIA Jetson AGX Orin modules, the system achieves 300 ms end-to-end latency for real-time schedule updates, meeting stringent safety requirements for elderly participants. The proposed method demonstrates significant improvements over conventional itinerary planners through its edge computing efficiency and personalized adaptation capabilities, particularly in handling the latency-sensitive demands of intensive tourism scenarios. Experimental results show robust performance across diverse participant profiles and activity types, confirming the system’s practical viability for real-world deployment in elderly adventure tourism operations. Full article

Background/Objectives: Mpox, a viral disease marked by distinctive skin lesions, has emerged as a global health concern, underscoring the need for scalable, accessible, and accurate diagnostic tools to strengthen public health responses. This study introduces ITMA’INN, an AI-driven healthcare system designed to detect Mpox from skin lesion images using advanced deep learning. Methods: The system integrates three key components: an AI model pipeline, a cross-platform mobile application, and a real-time public health dashboard. We leveraged transfer learning on publicly available datasets to evaluate pretrained deep learning models. Results: For binary classification (Mpox vs. non-Mpox), Vision Transformer, MobileViT, Transformer-in-Transformer, and VGG16 achieved peak performance, each with 97.8% accuracy and F1-score. For multiclass classification (Mpox, chickenpox, measles, hand-foot-mouth disease, cowpox, and healthy skin), ResNetViT and ViT Hybrid models attained 92% accuracy (F1-scores: 92.24% and 92.19%, respectively). The lightweight MobileViT was deployed in a mobile app that enables users to analyze skin lesions, track symptoms, and locate nearby healthcare centers via GPS. Complementing this, the dashboard equips health authorities with real-time case monitoring, symptom trend analysis, and intervention guidance. Conclusions: By bridging AI diagnostics with mobile technology and real-time analytics, ITMA’INN advances responsive healthcare infrastructure in smart cities, contributing to the future of proactive public health management. Full article

Spiking neural networks (SNNs) have emerged as a promising model for energy-efficient, event-driven processing of asynchronous event streams from Dynamic Vision Sensors (DVSs), a class of neuromorphic image sensors with microsecond-level latency and high dynamic range. Nevertheless, challenges persist in optimising training and effectively handling spatio-temporal complexity, which limits their potential for real-time applications on embedded sensing systems such as object tracking and recognition. Targeting this neuromorphic sensing pipeline, this paper proposes the Dynamic Tracking with Event Attention Spiking Network (DTEASN), a novel framework designed to address these challenges by employing a pure SNN architecture, bypassing conventional convolutional neural network (CNN) operations, and reducing GPU resource dependency, while tailoring the processing to DVS signal characteristics (asynchrony, sparsity, and polarity). The model incorporates two innovative, self-developed components: an event-driven multi-scale attention mechanism and a spatio-temporal event convolver, both of which significantly enhance spatio-temporal feature extraction from raw DVS events. An Event-Weighted Spiking Loss (EW-SLoss) is introduced to optimise the learning process by prioritising informative events and improving robustness to sensor noise. Additionally, a lightweight event tracking mechanism and a custom synaptic connection rule are proposed to further improve model efficiency for low-power, edge deployment. The efficacy of DTEASN is demonstrated through empirical results on event-based (DVS) object recognition and tracking benchmarks, where it outperforms conventional methods in accuracy, latency, event throughput (events/s) and spike rate (spikes/s), memory footprint, spike-efficiency (energy proxy), and overall computational efficiency under typical DVS settings. By virtue of its event-aligned, sparse computation, the framework is amenable to highly parallel neuromorphic hardware, supporting on- or near-sensor inference for embedded applications. Full article

The diverse usage of Unmanned Aerial Vehicles (UAVs) across commercial, military, and civil domains has significantly heightened the need for robust cybersecurity mechanisms. Given their reliance on wireless communications, real-time control systems, and sensor integration, UAVs are highly susceptible to cyber intrusions that can disrupt missions, compromise data integrity, or cause physical harm. This paper presents a comprehensive literature review of Intrusion Detection Systems (IDSs) that leverage artificial intelligence (AI) to enhance the security of UAV and UAV swarm environments. Through rigorous analysis of recent peer-reviewed publications, we have examined the studies in terms of AI model algorithm, dataset origin, deployment mode: centralized, distributed or federated. The classification also includes the detection strategy: online versus offline. Results show a dominant preference for centralized, supervised learning using standard datasets such as CICIDS2017, NSL-KDD, and KDDCup99, limiting applicability to real UAV operations. Deep learning (DL) methods, particularly Convolutional Neural Networks (CNNs), Long Short-term Memory (LSTM), and Autoencoders (AEs), demonstrate strong detection accuracy, but often under ideal conditions, lacking resilience to zero-day attacks and real-time constraints. Notably, emerging trends point to lightweight IDS models and federated learning frameworks for scalable, privacy-preserving solutions in UAV swarms. This review underscores key research gaps, including the scarcity of real UAV datasets, the absence of standardized benchmarks, and minimal exploration of lightweight detection schemes, offering a foundation for advancing secure UAV systems. Full article

Early train detection is vital for ensuring the safety of railway personnel, particularly in remote locations where fixed signaling infrastructure is unavailable. Unlike many existing solutions that rely on high-power, high-cost sensors and compute platforms, this work presents a lightweight, low-cost, and portable framework designed to run entirely on resource-constrained microcontrollers with just kilobytes of Random Access Memory (RAM). The proposed system uses vibration data from low-cost accelerometers and employs a simple yet effective Linear Regression (LR) model for almost real-time prediction of train arrival times. To ensure feasibility on low-end hardware, a parallel-processing framework is introduced, enabling continuous data collection, Machine Learning (ML) inference, and wireless communication with strict timing and energy constraints. The decision-making process, including data preprocessing and ML prediction, completes in under 10 ms, and alerts are transmitted via LoRa, enabling kilometer-range communication. Field tests on active railway lines confirm that the system detects approaching trains 15 s in advance with no false negatives and a small number of explainable false positives. Power characterization demonstrates that the system can operate for more than 6 days on a 10 Ah battery, with potential for months of operation using wake-on-vibration modes. Full article

The increasing adoption of digital technologies, robotic systems, and IoT applications in sectors such as medicine, agriculture, and industry drives a surge in data generation and necessitates secure and efficient encryption. For resource-constrained systems, lightweight yet robust cryptographic algorithms are critical. This study addresses the security demands of IoRT systems by proposing an enhanced chaos-based encryption method. The approach integrates the lightweight structure of NIST-standardized Ascon-AEAD128 with the randomness of the Zaslavsky map. Ascon-AEAD128 is widely used on many hardware platforms; therefore, it must robustly resist both passive and active attacks. To overcome these challenges and enhance Ascon’s security, we integrate into Ascon the keys and nonces generated by the Zaslavsky chaotic map, which is deterministic, nonperiodic, and highly sensitive to initial conditions and parameter variations.This integration yields a chaos-based Ascon variant with a higher encryption security relative to the standard Ascon. In addition, we introduce exploratory variants that inject non-repeating chaotic values into the initialization vectors (IVs), the round constants (RCs), and the linear diffusion constants (LCs), while preserving the core permutation. Real-time tests are conducted using Raspberry Pi 3B devices and ROS 2–based IoRT robots. The algorithm’s performance is evaluated over 100 encryption runs on 12 grayscale/color images and variable-length text transmitted via MQTT. Statistical and differential analyses—including histogram, entropy, correlation, chi-square, NPCR, UACI, MSE, MAE, PSNR, and NIST SP 800-22 randomness tests—assess the encryption strength. The results indicate that the proposed method delivers consistent improvements in randomness and uniformity over standard Ascon-AEAD128, while remaining comparable to state-of-the-art chaotic encryption schemes across standard security metrics. These findings suggest that the algorithm is a promising option for resource-constrained IoRT applications. Full article

Dynamic environments pose significant challenges for Visual Simultaneous Localization and Mapping (VSLAM), as moving objects can introduce outlier observations that severely degrade localization and mapping performance. To address this problem, we propose YSAG-VINS, a VSLAM algorithm specifically designed for dynamic scenes. The system integrates an enhanced YOLOv8 object detection network with an adaptive epipolar constraint strategy to effectively identify and suppress the impact of dynamic features. In particular, a lightweight YOLOv8n model augmented with ODConv and UIB modules is employed to balance detection accuracy with real-time efficiency. Based on semantic detection results, images are divided into static background and potentially dynamic regions, and the motion state of these regions is further verified using geometric constraints. Features belonging to truly dynamic objects are then removed to enhance robustness. Comprehensive experiments on multiple public datasets demonstrate that YSAG-VINS achieves superior pose estimation accuracy compared with VINS-Fusion, VDO-SLAM, and Dynamic-VINS. On three dynamic sequences of the KITTI dataset, the proposed method achieves average RMSE improvement rates of 48.62%, 12.18%, and 13.50%, respectively. These results confirm that YSAG-VINS provides robust and high-accuracy localization performance in dynamic environments, making it a promising solution for real-world applications such as autonomous driving, service robotics, and augmented reality. Full article

Deploying deep learning (DL) models in real-world environments remains a major challenge, particularly under resource-constrained conditions where achieving both high accuracy and compact architectures is essential. While effective, Conventional pruning methods often suffer from high computational overhead, accuracy degradation, or disruption of the end-to-end training process, limiting their practicality for embedded and real-time applications. We present Dynamic Attention-Guided Pruning (DAGP), a Dynamic Attention-Guided Soft Channel Pruning framework that overcomes these limitations by embedding learnable, differentiable pruning masks directly within convolutional neural networks (CNNs). These masks act as implicit attention mechanisms, adaptively suppressing non-informative channels during training. A progressively scheduled L1 regularization, activated after a warm-up phase, enables gradual sparsity while preserving early learning capacity. Unlike prior methods, DAGP is retraining-free, introduces minimal architectural overhead, and supports optional hard pruning for deployment efficiency. Joint optimization of classification and sparsity objectives ensures stable convergence and task-adaptive channel selection. Experiments on CIFAR-10 (VGG16, ResNet56) and PlantVillage (custom CNN) achieve up to 98.82% FLOPs reduction with accuracy gains over baselines. Real-world validation on an enhanced PlantDoc dataset for agricultural monitoring achieves 60 ms inference with only 2.00 MB RAM on a Raspberry Pi 4, confirming efficiency under field conditions. These results illustrate DAGP’s potential to scale beyond agriculture to diverse edge-intelligent systems requiring lightweight, accurate, and deployable models. Full article

The rapid evolution of autonomous vehicle technologies has amplified the need for crash detection that operates robustly under complex traffic conditions with minimal latency. We propose a hybrid temporal hierarchy that augments a Region-based Convolutional Neural Network (R-CNN) with an adaptive time-variant Kalman filter (with total-variation prior), a Hidden Markov Model (HMM) for state stabilization, and a lightweight Artificial Neural Network (ANN) for learned temporal refinement, enabling real-time crash detection from monocular video. Evaluated on simulated traffic in CARLA and real-world driving in Istanbul, the full temporal stack achieves the best precision–recall balance, yielding 83.47% F1 offline and 82.57% in real time (corresponding to 94.5% and 91.2% detection accuracy, respectively). Ablations are consistent and interpretable: removing the HMM reduces F1 by 1.85–2.16 percentage points (pp), whereas removing the ANN has a larger impact of 2.94–4.58 pp, indicating that the ANN provides the largest marginal gains—especially under real-time constraints. The transition from offline to real time incurs a modest overall loss (−0.90 pp F1), driven more by recall than precision. Compared to strong single-frame baselines, YOLOv10 attains 82.16% F1 and a real-time Transformer detector reaches 82.41% F1, while our full temporal stack remains slightly ahead in real time and offers a more favorable precision–recall trade-off. Notably, integrating the ANN into the HMM-based pipeline improves accuracy by 2.2%, while the time-variant Kalman configuration reduces detection lag by approximately 0.5 s—an improvement that directly addresses the human reaction time gap. Under identical conditions, the best RCNN-based configuration yields AP@0.50 ≈ 0.79 with an end-to-end latency of 119 ± 21 ms per frame (~8–9 FPS). Overall, coupling deep learning with probabilistic reasoning yields additive temporal benefits and advances deployable, camera-only crash detection that is cost-efficient and scalable for intelligent transportation systems. Full article

This study addresses the problem of anomaly detection in water treatment systems by proposing a hybrid VAE–LSTM model with a combined loss function that integrates reconstruction and prediction errors. Following the signal flow of wastewater treatment systems, data acquisition, transmission, and cyberattack scenarios were simulated, and a dual-dimensional learning framework of “feature space—temporal space” was designed: the VAE learns latent data distributions and computes reconstruction errors, while the LSTM models temporal dependencies and computes prediction errors. Anomaly decisions are made through feature extraction and weighted scoring. Experimental comparisons show that the proposed fusion model achieves an accuracy of approximately 0.99 and an F1-Score of about 0.75, significantly outperforming single models such as Isolation Forest and One-Class SVM. It can accurately identify attack anomalies in devices such as the LIT101 sensor and MV101 actuator, e.g., water tank overflow and state transitions, with reconstruction errors primarily beneath 0.08 ensuring detection reliability. In terms of time efficiency, Isolation Forest is suitable for real-time preliminary screening, while VAE-LSTM adapts to high-precision detection scenarios with an “offline training (423 s) + online detection (1.39 s)” mode. This model provides a practical solution for intelligent monitoring of industrial water treatment systems. Future research will focus on model lightweighting, enhanced data generalization, and integration with edge computing to improve system applicability and robustness. The proposed approach breaks through the limitations of traditional single models, demonstrating superior performance in detection accuracy and scenario adaptability. It offers technical support for improving the operational efficiency and security of water treatment systems and serves as a paradigm reference for anomaly detection in similar industrial systems. Full article

This paper presents a hardware-in-the-loop (HIL) simulation case study on the application of High-Order Sliding Mode Control (HOSMC) to a flexible-link robotic arm. The developed HIL platform combines physical hardware components with a simulated plant model, enabling real-time testing of control algorithms under realistic operating conditions without requiring a full-scale prototype. HOSMC, an advanced nonlinear control strategy, mitigates the chattering effects inherent in conventional sliding mode control by driving the system to a reduced-order sliding manifold within a finite time, resulting in smoother actuator commands and reduced mechanical stress. Flexible-link arms, while lightweight and energy-efficient, are inherently nonlinear and prone to vibration, posing significant control challenges. In this case study, the experimental HIL environment is used to evaluate HOSMC performance, demonstrating improved trajectory tracking, reduced overshoot, and minimized steady-state error. The results confirm that HIL simulation offers an effective bridge between theoretical control design and practical implementation for advanced robotic systems. Full article