Search Results (1,803)

The rapid expansion of low-altitude unmanned aerial vehicles demands robust obstacle detection and avoidance systems capable of operating under diverse environmental conditions. This paper proposes a multimodal fusion attention network that integrates visual imagery and Light Detection and Ranging (LiDAR) point cloud data for real-time obstacle perception. The architecture incorporates a bidirectional cross-modal attention mechanism that learns dynamic correspondences between heterogeneous sensor modalities, enabling adaptive feature integration based on contextual reliability. An adaptive weighting component automatically modulates modal contributions according to estimated sensor confidence under varying environmental conditions. The network further employs gated fusion units and multi-scale feature pyramids to ensure comprehensive obstacle representation across different distances. A hierarchical avoidance decision framework translates detection outputs into executable control commands through threat assessment and graduated response strategies. Experimental evaluation on both public benchmarks and a purpose-collected low-altitude obstacle dataset demonstrates that the proposed method achieves 84.9% mean Average Precision (mAP) while maintaining 47.3 frames per second (FPS) on Graphics Processing Unit (GPU) hardware and 23.6 FPS on embedded platforms. Ablation studies confirm the contribution of each architectural component, with cross-modal attention providing the most substantial performance improvement. Full article

Fire detection in ancient architecture presents significant challenges due to complex scenes and unique structural characteristics. Traditional detection methods often demonstrate limitations when addressing the specific structural idiosyncrasies of individual ancient buildings and the overlapping occlusion prevalent in architectural complexes. This paper proposes YOLO-AR, a novel fire detection algorithm based on an improved YOLOv8 framework. By embedding the Convolutional Block Attention Module (CBAM) at the end of the backbone network, the algorithm enhances its capability to capture key features of flames and smoke. Furthermore, the Repulsion Loss function is introduced to explicitly optimize bounding box localization accuracy in occluded and dense scenarios. Experiments conducted on a self-constructed ancient architecture dataset comprising 15,847 images demonstrate that YOLO-AR outperforms mainstream comparative algorithms in terms of Precision, Recall, and mean Average Precision (mAP). Specifically, the detection precision reached 90.7%, and the recall rate improved to 89.7%. This study provides an efficient and reliable visual detection solution for early warning systems in ancient architecture, offering significant value for cultural heritage preservation. Full article

This work presents a signal processing and reconstruction system developed for a flexible optical pressure 2D mapping sensor. The sensor consists of a two-dimensional grid of polyurethane optical fibers (PU-OFs) embedded in polydimethylsiloxane (PDMS), which acts as the input device for acquiring light intensity changes caused by external surface-applied pressure. In this study, we propose a system to process these signals through an inverse model based on the Moore–Penrose pseudoinverse for spatial localization, along with a point-specific pressure estimation model to infer the magnitude of the applied force, which is then used to generate quantitative pressure maps. Experimental results show the system’s overall performance, robustness, and repeatability across multiple pressure levels and locations. In most cases, localization errors remain below 5 mm, while pressure estimation errors are around 5 mmHg when the pressure is correctly localized. Performance metrics, such as recall, specificity, and precision, support the system’s ability to detect, localize, and reconstruct pressure events with consistent reliability. These results establish the viability of the proposed methodology for potential integration into low-cost and flexible optical fiber-based 2D pressure monitoring systems for biomedical applications. Full article

The Internet of Things (IoT) is increasingly embedded in critical infrastructures across healthcare, energy, transportation, and industrial automation, yet its pervasiveness introduces substantial security and resilience challenges. This paper presents a comprehensive review of recent advances in IoT resilience, focusing on developments reported between 2022 and 2025. A layered taxonomy is proposed to organize resilience strategies across hardware, network, learning, application, and governance layers, addressing adversarial, environmental, and hybrid stressors. The survey systematically classifies and compares more than forty representative studies encompassing deep learning under adversarial attack, generative and ensemble intrusion detection, hardware and protocol-level defenses, federated and distributed learning, and trust and governance-based approaches. A comparative analysis shows that while adversarial training, GAN-based augmentation, and decentralized learning improve robustness, their evidence is often confined to specific datasets or attack scenarios, with limited validation in large-scale deployments. The study highlights challenges in benchmarking adaptivity, cross-layer integration, and explainable resilience, concluding with future directions for creating antifragile IoT systems that can self-heal and adapt to evolving cyber–physical threats. Full article

Drowsy driving contributes to roughly 20% of traffic fatalities, yet most detection systems rely on behavioral cues that appear only after impairment has set in. Here we ask whether first and second derivatives of heart rate variability (HRV) can detect pre-crash states earlier than conventional approaches. Twenty-five participants completed 49 driving simulator sessions while we recorded cardiac activity through capacitive ECG electrodes embedded in the seat backrest—a non-contact method that avoids the privacy concerns of camera-based monitoring. To prevent circular evaluation, ground truth labels were based solely on crash proximity rather than HRV-derived scores. The combined HRV feature set (conventional metrics plus derivatives) achieved AUC = 0.863 for pre-crash prediction; derivatives alone reached only AUC = 0.573, indicating their value as complementary rather than standalone features. Driving performance indicators remained the strongest predictors (AUC = 0.999). Temporally, derivative-based detection preceded behavioral manifestations by 5–8 min and crash events by 6.8 ± 2.3 min. Across 1591 crashes and 6.78 million data points, we found that HRV derivatives capture physiological changes that precede overt impairment, though their utility depends on integration with other feature types. Full article

Background: Research on vibrations induced by running has gained significant attention due to its implications for athletes’ performance, injury prevention, and overall well-being. Distance running exposes the body to repetitive impulsive forces, causing significant vibrations to travel through physiological systems and biomechanical structures. These vibrations increase fatigue and the risk of injury. Although it has gained importance, research on induced vibration during running and wearable equipment for monitoring is scarce. This study aims to evaluate the performance of a measurement system for monitoring the acceleration levels of induced vibrations during long-distance running, exploring the capability of non-invasive wearable devices to characterise vibration transmissibility and exposure. Moreover, a preliminary quantitative assessment of induced vibration levels for an indoor testing scenario is given. Methods: Metrological characterisation of Xsens Motion Trackers Awinda (MTw), off-the-shelf inertial magnetic motion trackers, was performed by measuring the sensors’ frequency bandwidth in a controlled environment, providing logarithmic sweep sine excitations at different levels (2 g, 5 g, 7 g, where g is meant to be the gravitational acceleration). A testing protocol for indoor testing was derived from the literature, allowing characterisation of the sensors’ behaviour in terms of vibration transmissibility and exposure detection in the intended application. Time domain and frequency domain analyses were conducted by following the ISO 2631 standard guideline for vibration exposure assessment, and measurement uncertainty was defined, either for the dynamic correction of the sensors’ frequency behaviour or for the computed time and frequency domain metrics. In this framework, a treadmill-based test was conducted. The aim was to evaluate the Xsens sensors’ performance in measuring vibration dose exposure and transmissibility. Three MTws were placed on the subject’s right tibia, back, and forehead using elastic bands. A 25-year-old female amateur runner completed a series of tests consisting of walking for 1 min at 3.5 km/h (instrumentation setup), followed by running at two speeds (8 km/h and 11 km/h) for 2–4 min per trial, with 5 min rest periods between tests. Conclusions: The tested measurement system showed promising results due to its capability to assess vibration exposure during sports activities, but dynamic correction was found to be mandatory for accurate vibration level assessment. The main outcome of this study is a method for characterising the accelerometers embedded in the proposed devices, along with an analysis strategy for future testing campaigns. Thanks to the portability of IMUs (inertial measurement units), this approach enables the evaluation of induced vibrations during in-field running measurements. Full article

Real-time detection of gait phase is a critical challenge for closed-loop neuromodulation systems aimed at restoring locomotion after spinal cord injury (SCI). However, many existing gait analysis approaches rely on offline processing or computationally intensive models that are unsuitable for low-latency, embedded deployment. In this study, we present a hybrid AI-based sensing architecture that enables real-time kinematic extraction and on-device gait-phase classification for closed-loop neuromodulation in SCI mice. A vision AI module performs marker-assisted, high-speed pose estimation to extract hindlimb joint angles during treadmill locomotion, while a lightweight edge AI model deployed on a microcontroller classifies gait phase and generates real-time phase-dependent stimulation triggers for closed-loop neuromodulation. The integrated system generalized to unseen SCI gait patterns without injury-specific retraining and enabled precise phase-locked biphasic stimulation in a bench-top closed-loop evaluation. This work demonstrates a low-latency, attachment-free sensing and control framework for gait-responsive neuromodulation, supporting future translation to wearable or implantable closed-loop neurorehabilitation systems. Full article

Ensuring strategic resilience in critical infrastructures supported with a machine learning approach requires moving beyond compliance checklists and post-incident analysis toward proactive, intelligence-based approaches. This study introduces the Forensic Resilience Operational Model (FROM), a systems thinking framework designed to embed forensic intelligence into the resilience cycle of complex socio-technical systems. To quantify this integration, the study investigates the determinants of the extent to which four operational pillars (forensic readiness, anomaly detection, governance and privacy safeguards, and structured intelligence integration) affect forensic resilience, using empirical survey data from 212 cybersecurity professionals across critical infrastructure sectors. We deploy Partial Least Squares Structural Equation Modelling (PLS-SEM) to investigate these relationships, and the results confirm that anomaly detection is the strongest contributor to forensic resilience, followed by structured intelligence integration and forensic readiness. Governance safeguards, while comparatively weaker, provide the necessary legitimacy and assurance of compliance. Supported with sector-specific case studies in the maritime, financial, and CERT domains, the findings highlight both the adaptability of the proposed FROM and the operational constraints encountered in real-world contexts. The study contributes to the field of systems-oriented strategic management by demonstrating that, when systematically embedded, forensic intelligence enhances adaptive capacity, supports predictive decision-making, and strengthens resilience in environments characterized by uncertainty and high complexity. Full article

This work presents a novel soft gripper concept featuring integrated force feedback and a compact, resource-efficient geometry. The gripper is designed to provide a low-cost, adaptable, and precise solution for manipulating delicate and irregularly shaped objects. By embedding force feedback directly into the structure, the system reliably detects contact and enables controlled, gentle gripping of fragile items. The design was developed for collaborative and assistive robotic applications, where safety and human–robot interaction are prioritized. The prototype is fabricated using consumer-grade 3D-printed components and employs a simple cable-driven actuation system. The hybrid soft–rigid architecture combines compliant fingers with a rigid, sensorized thumb, preserving the adaptive grasping characteristics of soft robotics while simplifying sensing integration and construction. A motor-based control mechanism synchronizes finger motion through cable traction, ensuring reliable and repeatable performance. Experimental evaluations demonstrate secure, damage-free handling across diverse object types, highlighting the gripper’s potential in assistive robotics, cobot environments, biomedical contexts, and other domains requiring safe and delicate manipulation. Full article

Manufacturing companies face significant challenges in leveraging artificial intelligence for equipment management due to high infrastructure costs and limited availability of labeled data for failures. While most manufacturing AI applications focus on structured sensor data, vast amounts of unstructured textual information containing valuable maintenance knowledge remain underutilized. This study presents a practical generative AI-based framework for structured information extraction that automatically converts unstructured equipment maintenance texts into predefined semantic fields to support predictive maintenance in manufacturing environments. We adopted and evaluated three representative generative models—Bidirectional and Auto-Regressive Transformers (BART) with KoBART, Text-to-Text Transfer Transformer (T5) with pko-t5-base, and the large language model Qwen—to generate structured outputs by extracting three predefined fields: failed components, failure types, and corrective actions. The framework enables the structuring of equipment management text data from Manufacturing Execution Systems (MES) to build predictive maintenance support systems. We validated the approach using a large-scale MES dataset consisting of 29,736 equipment maintenance records from a major automotive parts manufacturer, from which curated subsets were used for model training and evaluation. Our methodology employs Generative Pre-trained Transformer 4 (GPT-4) for initial dataset construction, followed by domain expert validation to ensure data quality. The trained models achieved promising performance when evaluated using extraction-aligned metrics, including exact match (EM) and token-level precision, recall, and F1-score, which directly assess field-level extraction correctness. ROUGE scores are additionally reported as a supplementary indicator of lexical overlap. Among the evaluated models, Qwen consistently outperformed BART and T5 across all extracted fields. The structured outputs are further processed through domain-specific dictionaries and regular expressions to create a comprehensive analytical database supporting predictive maintenance strategies. We implemented a web-based analytics platform enabling time-series analysis, correlation analysis, frequency analysis, and anomaly detection for equipment maintenance optimization. The proposed system converts tacit knowledge embedded in maintenance texts into explicit, actionable insights without requiring additional sensor installations or infrastructure investments. This research contributes to the manufacturing AI field by demonstrating a comprehensive application of generative language models to equipment maintenance text analysis, providing a cost-effective approach for digital transformation in manufacturing environments. The framework’s scalability and cloud-based deployment model present significant opportunities for widespread adoption in the manufacturing sector, supporting the transition from reactive to predictive maintenance strategies. Full article

This paper addresses the issue of low detection accuracy in underwater optical images for unmanned underwater vehicles (UUVs) during practical operations, caused by factors such as uneven lighting, blur, complex backgrounds, and target occlusion. To enhance the autonomous perception and control capabilities of UUVs, a high-precision algorithm named MBACA-YOLO is proposed based on the YOLOv13n model. Firstly, the convolutional layers in the backbone network of YOLOv13n are optimized by replacing stride-2 convolutions with stride-1 and embedding SPD layers to enable richer feature extraction. Secondly, the newly proposed MBACA attention mechanism is integrated into the final layer of the backbone network, enhancing effective features and suppressing background noise interference. Thirdly, traditional upsampling in the neck network is replaced with CARAFE upsampling to mitigate noise pollution. Finally, an Alpha-Focal-CIoU loss function is designed to improve the accuracy of bounding box regression for underwater targets. To validate the algorithm’s effectiveness, experiments were conducted on the URPC dataset with the following evaluation protocol: 640 × 640 input resolution, batch size 1, FP32 precision, and standard NMS. All results are from a single random seed with 300 epochs of training. The proposed MBACA-YOLO algorithm outperforms the baseline YOLOv13n model, improving mAP@0.5 and mAP@0.5:0.95 by 3.1% and 2.8% respectively, while adding only 0.49M parameters and 1.0 GFLOPs, with an FPS drop of just 2 frames. This makes it an efficient, deployable perception solution for automated Unmanned Underwater Vehicles (UUVs), significantly advancing intelligent underwater systems. Full article

The low-altitude airspace of bird flocks is gradually shared by unmanned aerial vehicles (UAVs), posing safety risks that necessitate accurate trajectory forecasting. However, existing vision-based methods often treat trajectory prediction and UAV detection as separate tasks, assume light-tailed Gaussian noise, and rely on heavy backbones. These limitations, when applied to bird trajectory forecasting, limit uncertainty calibration and embedded deployment in ground-based monocular surveillance. In this work, we propose a unified framework for low-altitude monitoring. Its core, Mini-BirdFormer, combines a lightweight Transformer encoder with a Student-t mixture density head to model heavy-tailed flight dynamics and produce calibrated uncertainty. Experiments on a real-world dataset show the model achieves strong long-horizon performance with only 1.05 million parameters, attaining a minADE of 0.785 m and reducing negative log-likelihood from 1.25 to −2.01 (lower is better) compared with a Gaussian Long Short-Term Memory (LSTM) baseline. Crucially, it enables low-latency inference on resource-constrained platforms at 616 FPS. Additionally, a system-level extension supports zero-shot UAV detection via open-vocabulary learning, attaining 92% recall without false alarms. Results demonstrate that combining heavy-tailed probabilistic modeling with a compact backbone provides a practical, deployable approach for monitoring shared airspace. Full article

To address critical limitations in conventional forward collision warning (FCW) systems including inadequate road condition detection accuracy, significant warning area prediction errors, and poor environmental adaptability on wet/snow-covered roads, this study develops an adaptive collision warning framework based on real-time road slippery states recognition. An enhanced ED-ResNet50 model is proposed, incorporating grouped convolutions within the backbone network and embedding ECA attention mechanisms after the second/third residual blocks alongside DDS-DA modules after the fourth block, significantly improving discriminative capability for pavement texture analysis under adverse conditions. This vision-based recognition system synchronizes with YOLOv8 for preceding vehicle detection, enabling the construction of a friction-sensitive safety distance and the time-to-collision model that dynamically calibrates warning thresholds according to instantaneous vehicle velocity and road adhesion coefficients. Real-vehicle validation demonstrates an 8.76% improvement in overall warning accuracy and 7.29% reduction in lateral and early false alarm rates compared to static-threshold systems, confirming practical efficacy for safety assurance in inclement weather. Full article

This paper tackles the growing uncertainty in distribution networks caused by distributed generation, load fluctuations, and frequent topological changes. It proposes a multi-source data fusion framework using enhanced selective convolution (SKNet) and graph attention networks (GAT). First, heterogeneous measurement data, including Phasor Measurement Unit (PMU) and Supervisory Control and Data Acquisition (SCADA) data, are processed through a unified normalization and outlier elimination technique to ensure data quality. Second, SKNet is utilized to extract spatiotemporal multi-scale features, improving the detection of both rapid disturbances and long-term trends. Third, the extracted features are fed into GAT to model node electrical couplings, while power flow residual constraints are embedded in the loss function to enforce the physical validity of the estimated states. This physics-informed design overcomes a key limitation of pure data-driven models and enables an end-to-end framework that integrates data-driven learning with physical mechanism constraints. Finally, comprehensive validation is performed on the improved IEEE 33-node and IEEE 123-node test systems. The test scenarios include Gaussian measurement noise, data outliers, missing measurements, and topological changes. The results show that the proposed method outperforms baseline models such as Multi-Scale Graph Attention Network (MS-GAT), Bidirectional Long Short-Term Memory (BiLSTM), and traditional weighted least squares (WLS). It achieves Root Mean Square Error (RMSE) reductions of up to 18% and Mean Absolute Error (MAE) reductions of up to 15%. The average inference latency is only 10–18 ms. Even under unknown topological changes, the estimation error increases by only 15–25%. These results demonstrate the superior accuracy, robustness, and real-time performance of the proposed method for intelligent distribution network state estimation. Full article

Honey fraud represents a persistent and analytically challenging form of food adulteration, driven by globalised supply chains, strong economic incentives and asymmetries in regulatory oversight and analytical capacity. Conventional physicochemical, spectroscopic and isotopic methods provide legally robust tools for routine control, yet increasingly struggle to detect sophisticated adulteration strategies that are compositionally optimised to mimic authentic honey profiles. These challenges are amplified in a global context, where heterogeneous enforcement landscapes and fragmented analytical infrastructures create exploitable vulnerabilities across international trade networks. This narrative review synthesises current knowledge on honey fraud typologies and critically evaluates established analytical approaches alongside emerging omics-based authentication strategies, including genomics, metabolomics, proteomics and microbiome profiling. Omics-based approaches extend authenticity assessment beyond single-marker paradigms by capturing multidimensional biological and compositional signatures, thereby improving sensitivity to subtle and system-aware fraud (i.e., adulteration strategies that adapt to prevailing analytical detection methods and regulatory thresholds) strategies. To maintain evidentiary clarity, this review explicitly distinguishes between analytically demonstrated vulnerabilities, technically feasible adulteration scenarios and fraud practices documented in regulatory or enforcement contexts. Advanced technology-driven strategies are therefore discussed as potential system-level risks rather than confirmed large-scale honey fraud cases. This differentiation not only safeguards evidentiary precision but also highlights the structural limits of purely analytical solutions. Beyond analytical performance, honey authentication is framed as a systemic challenge embedded in global food systems. This review highlights the need for integrated, data-driven and scalable authentication frameworks that align analytical innovation with reference harmonisation, governance structures and international regulatory cooperation to support resilient and globally robust honey authenticity control. Full article