Search Results (1,445)

Even a decade after the Fukushima Daiichi Nuclear Power Plant (FDNPP) accident on 11 March 2011, fluctuations in atmospheric ¹³⁷Cs were still observed, and explanations for the fluctuations and their carriers remained elusive. In this study, small fluctuations within 0.0002 Bq∙m⁻³ were still detected in aerosol samples obtained from January to April, and slightly higher levels of atmospheric ¹³⁷Cs were observed from May to September in a heavily contaminated area of Fukushima prefecture. Specifically, it is demonstrated that the ¹³⁷Cs carriers in the aerosol samples were a combination of carbon-containing particles and aluminum-containing particles (Al particles dominated, with the percentage being 68%) in early May, whereas the main ¹³⁷Cs carriers were carbonaceous particles, with the average percentage being 88% in September and at the end of May, using fluorescent upright microscope and scanning electron microscope equipped with an energy-dispersive X-ray spectrometer quantitatively. Additionally, small particles (less than 2 μm) and medium particles (2–8 μm) of carbonaceous particles had a higher level in the aerosol samples of May and September. Specifically, bacteria (1–1.8 μm) and spores (1.8–10 μm) had a linear relationship with the distribution of atmospheric ¹³⁷Cs in the aerosol samples of September. In addition, temperature and precipitation were the main impact factors affecting the distribution of ¹³⁷Cs and their carriers. This observation further suggests that there is still a need for long-term monitoring of atmospheric ¹³⁷Cs. Full article

Intelligent Transportation Systems (ITS) have progressively incorporated machine learning to optimize traffic efficiency, enhance safety, and improve real-time decision-making. However, the traditional centralized machine learning (ML) paradigm faces critical limitations regarding data privacy, scalability, and single-point vulnerabilities. This study explores FL as a decentralized alternative that preserves privacy by training local models without transferring raw data. Based on a systematic literature review encompassing 39 ITS-related studies, this work classifies applications according to their architectural detail—distinguishing systems from models—and identifies three families of federated learning (FL) frameworks: privacy-focused, integrable, and advanced infrastructure. Three representative frameworks—Federated Learning-based Gated Recurrent Unit (FedGRU), Digital Twin + Hierarchical Federated Learning (DT + HFL), and Transfer Learning with Convolutional Neural Networks (TFL-CNN)—were comparatively analyzed against a client–server baseline to assess their suitability for ITS adaptation. Our qualitative, architecture-level comparison suggests that DT + HFL and TFL-CNN, characterized by hierarchical aggregation and edge-level coordination, are conceptually better aligned with scalability and stability requirements in vehicular and traffic deployments than pure client–server baselines. FedGRU, while conceptually relevant as a meta-framework for coordinating multiple organizational models, is primarily intended as a complementary reference rather than as a standalone architecture for large-scale ITS deployment. Through application-level evaluations—including traffic prediction, accident detection, transport-mode identification, and driver profiling—this study demonstrates that FL can be effectively integrated into ITS with moderate architectural adjustments. This work does not introduce new experimental results; instead, it provides a qualitative, architecture-level comparison and adaptation guideline to support the migration of ITS applications toward federated learning. Overall, the results establish a solid methodological foundation for migrating centralized ITS architectures toward federated, privacy-preserving intelligence, in alignment with the evolution of edge and 6G infrastructures. Full article

Traditional automated monitoring systems adopted for Intersection Traffic Control still face challenges, including high costs, maintenance difficulties, insufficient coverage, poor multimodal data integration, and limited traffic information analysis. To address these issues, the study proposes a sovereign AI-driven Smart Transportation governance approach, developing a mobile AI solution equipped with multimodal perception, task decomposition, memory, reasoning, and multi-agent collaboration capabilities. The proposed system integrates computer vision, multi-object tracking, natural language processing, Retrieval-Augmented Generation (RAG), and Large Language Models (LLMs) to construct a Pipeline-based Traffic Analysis System (PTAS). The PTAS can produce real-time statistics on pedestrian and vehicle flows at intersections, incorporating potential risk factors such as traffic accidents, construction activities, and weather conditions for multimodal data fusion analysis, thereby providing forward-looking traffic insights. Experimental results demonstrate that the enhanced DuCRG-YOLOv11n pre-trained model, equipped with our proposed new activation function $\beta silu$, can accurately identify various vehicle types in object detection, achieving a frame rate of 68.25 FPS and a precision of 91.4%. Combined with ByteTrack, it can track over 90% of vehicles in medium- to low-density traffic scenarios, obtaining a 0.719 in MOTA and a 0.08735 in MOTP. In traffic flow analysis, the RAG of Vertex AI, combined with Claude Sonnet 4 LLMs, provides a more comprehensive view, precisely interpreting the causes of peak-hour congestion and effectively compensating for missing data through contextual explanations. The proposed method can enhance the efficiency of urban traffic regulation and optimizes decision support in intelligent transportation systems. Full article

Automotive dashboard cameras are widely used to record driving events and often serve as critical evidence in accident investigations and insurance claims. However, the availability of free and low-cost editing tools has increased the risk of video tampering, underscoring the need for reliable methods to verify video authenticity. Temporal tampering typically involves manipulating frame order through insertion, deletion, or duplication. This paper proposes a computationally efficient framework that transforms high-dimensional video into compact one-dimensional temporal signals and learns tampering patterns using a shallow one-dimensional convolutional neural network (1D-CNN). Five complementary features are extracted between consecutive frames: frame-difference magnitude, structural similarity drift (SSIM drift), optical-flow mean, forward–backward optical-flow consistency error, and compression-aware temporal prediction error. Per-video robust normalization is applied to emphasize intra-video anomalies. Experiments on a custom dataset derived from D²-City demonstrate strong detection performance in single-attack settings: 95.0% accuracy for frame deletion, 100.0% for frame insertion, and 95.0% for frame duplication. In a four-class setting (non-tampered, insertion, deletion, duplication), the model achieves 96.3% accuracy, with AUCs of 0.994, 1.000, 0.997, and 0.988, respectively. Efficiency analysis confirms near real-time CPU inference (≈12.7–12.9 FPS) with minimal memory overhead. Cross-dataset tests on BDDA and VIRAT reveal domain-shift sensitivity, particularly for deletion and duplication, highlighting the need for domain adaptation and augmentation. Overall, the proposed multi-feature 1D-CNN provides a practical, interpretable, and resource-aware solution for temporal tampering detection in dashcam videos, supporting trustworthy video forensics in IoT-enabled transportation systems. Full article

Safety on construction sites is an essential yet challenging issue due to the inherently hazardous nature of these sites. Workers are expected to wear Personal Protective Equipment (PPE), such as helmets, vests, and safety glasses, to prevent or minimize their exposure to injuries. However, ensuring compliance remains difficult, particularly in large or complex sites, which require a time-consuming and usually error-prone manual inspection process. The research proposes an automated PPE detection system utilizing the deep learning model YOLO11, which is trained on the CHVG dataset, to identify in real-time whether workers are adequately equipped with the necessary gear. The proposed PPE-EYE method, using YOLO11x, achieved a mAP50 of 96.9% and an inference time of 7.3 ms, which is sufficient for real-time PPE detection systems, in contrast to previous approaches involving the same dataset, which required 170 ms. The model achieved these results by employing data augmentation and fine-tuning. The proposed solution provides continuous monitoring with reduced human oversight and ensures timely alerts if non-compliance is detected, allowing the site manager to act promptly. It further enhances the effectiveness and reliability of safety inspections, overall site safety, and reduces accidents, ensuring consistency in follow-through of safety procedures to create a safer and more productive working environment for all involved in construction activities. Full article

Drowsy driving and sudden medical emergencies are major contributors to traffic accidents, necessitating continuous, non-intrusive driver monitoring. Since current technologies often struggle to balance accuracy with practicality, this study presents the design, fabrication, and validation of a smart steering wheel prototype. The device integrates dry-contact electrocardiogram (ECG), photoplethysmography (PPG), and inertial sensors to facilitate multimodal physiological monitoring. The system underwent a two-stage evaluation involving a single participant: laboratory validation benchmarking acquired signals against medical-grade equipment, followed by real-world testing in a custom electric research vehicle to assess performance under dynamic conditions. Laboratory results demonstrated that the prototype captured high-quality signals suitable for reliable heart rate variability analysis. Furthermore, on-road evaluation confirmed the system’s operational functionality; despite increased noise from motion artifacts, the ECG signal remained sufficiently robust for continuous R-peak detection. These findings confirm that the multimodal smart steering wheel is a feasible solution for unobtrusive driver monitoring. This integrated platform provides a solid foundation for developing sophisticated machine-learning algorithms to enhance road safety by predicting fatigue and detecting adverse health events. Full article

Health and safety concerns at construction sites have become increasingly significant, especially with the rapid technological development and the opportunities it brings. Since fall-from-height incidents are the most frequent construction accidents in the field, this paper focuses on a fall risk prevention method for building construction sites by integrating algorithm-based techniques with BIM models and introducing a smart adaptive system that automatically detects danger zones and places requiring safety equipment regardless of the layout complexity and design modifications. Moreover, the work reveals the optimal quantities and material takeoffs for the suggested safety plan over time, based on the construction sequence. It provides a 4D BIM simulation of building projects, in which the appropriate configurations, quantities, lengths, and costs of the required safety equipment can be derived at any chosen time interval within the construction stage. Full article

Background/Objectives: An individual with a hand disability, whether caused by an accident, disease, or congenital condition, may have significant problems with their daily activities, self-perception, and ability to work. Prosthetic hands can be used to restore essential hand functions, and features such as adaptive grasps can enhance their usability. Due to noise in the sEMG signal and hardware limitations in the system, reliable myoelectric control remains a challenge for low-cost prosthetics. ESP32 microcontrollers are used in this study to develop an SVM-based sEMG classifier that addresses these issues and improves responsiveness and accuracy. A 3D-printed mechanical structure supports the prosthesis, reducing production costs and making it more accessible. Methods: The prosthetic hand is developed using an ESP32 as the microcontroller, a Myoware Muscle Sensor to detect muscle activity, and an ESP32-based control system that integrates sEMG acquisition, SVM classification, and finger actuation with FSR feedback. A surface electromyography (sEMG) method is paired with a Support Vector Machine (SVM) algorithm to help classify signals from the sensor to improve the user’s experience and finger adaptability. Results: The SVM classifier achieved 89.10% accuracy, an F1-score of 0.89, and an AUC of 0.92, with real-time testing demonstrating that the ESP32 could reliably distinguish flexion and extension signals and actuate the servo, accordingly, producing movements consistent with the kinematic simulations. Complementing this control performance, the prosthetic hand was constructed using a coupled 4 bar linkage mechanism fabricated in PLA+, selected for its superior factor of safety compared to the other tested materials, ensuring sufficient structural reliability during operation. Conclusions: The results demonstrate that SVM-based sEMG classification can be effectively implemented on low-power microcontrollers for intuitive, low-cost prosthetic control. Further work is needed to expand beyond two-class detection and increase robustness against muscle fatigue and sensor placement variability. Full article

Traffic violations and road accidents remain significant challenges in developing safe and efficient transportation systems. Despite technological advancements, improving vehicle detection accuracy and enabling real-time traffic management remain critical research priorities. This study proposes YOLO-LIO, an enhanced vehicle detection framework designed to address these challenges by improving small-object detection and optimizing real-time deployment. The system introduces multi-scale detection, virtual zone filtering, and efficient preprocessing techniques, including grayscale transformation, Laplacian variance calculation, and median filtering to reduce computational complexity while maintaining high performance. YOLO-LIO was rigorously evaluated on five datasets, GRAM Road-Traffic Monitoring (99.55% accuracy), MAVD-Traffic (99.02%), UA-DETRAC (65.14%), KITTI (94.21%), and an Author Dataset (99.45%), consistently demonstrating superior detection capabilities across diverse traffic scenarios. Additional system features include vehicle counting using a dual-line detection strategy within a virtual zone and speed detection based on frame displacement and camera calibration. These enhancements enable the system to monitor traffic flow and vehicle speeds with high accuracy. YOLO-LIO was successfully deployed on Jetson Nano, a compact, energy-efficient hardware platform, proving its suitability for real-time, low-power embedded applications. The proposed system offers an accurate, scalable, and computationally efficient solution, advancing intelligent transportation systems and improving traffic safety management. Full article

Road safety ranks among the most apparent concerns in present-day urban existence, with risky driving the most prevalent cause of road crashes. In this paper, we present an external camera video-based automatic hazardous driving behavior detection model for use in smart cities. We addressed the problem with a holistic approach covering data collection to hazardous driving behavior classification including zig-zag driving, risky overtaking, and speeding over a pedestrian crossing. Our strategy employs a specially generated dataset with diverse driving situations under diverse traffic conditions and luminosities. We advocate for a Multi-Speed Transformer model with dual vehicle trajectory data timescale operation to capture near-future actions in the context of extended driving trends. A new contribution lies in our symbiotic system which, apart from the detection of unsafe driving, also assumes the responsibility of triggering countermeasures through a real-time continuous loop with vehicle systems. Empirical results demonstrate the Multi-Speed Transformer’s performance with 97.5% in accuracy and 93% in F1-score over our balanced corpus, surpassing comparison baselines including Temporal Convolutional Networks and Random Forest classifiers by significant amounts. The performance is boosted to 98.7% in accuracy as well as 95.5% in F1-score with the symbiotic framework. They confirm the promise of leading-edge neural architectures paired with symbiotic systems in enhancing road safety in smart cities. The ability of the system to provide real-time risky driving behavior detection with mitigation offers a real-world solution for the prevention of accidents while not restricting driver autonomy, a balance between automatic intervention, and passive monitoring. Empirical evidence on the TRAF-derived corpus, which includes 18 videos and 414 labelled trajectory segments, indicates that the Multi-Speed Transformer reaches an accuracy of 97.5% and an F1-score of 93% under the balanced-training protocol, and in this configuration it consistently surpasses the considered baselines when we use the same data splits and the same evaluation metrics. Full article

Electrical energy in urban and industrial power supply networks is mainly transmitted through 6–10-kV cable networks with an isolated neutral, where most lines are made as bunches of cables. Up to 75–90% of electrical faults in these cable networks belong to single-phase ground faults (SGFs), which can cause more severe accidents accompanied by significant economic damage. Widely known simple and directional protections against SGFs are relatively selective and, hence, often incapable of properly responding to SGFs in a network with such lines and detecting a cable with SGFs in the bunch of a damaged line. These disadvantages can be eliminated by using new, simple, and inexpensive, absolutely selective protections capable of detecting a cable with SGFs in a damaged line. We suggest the techniques and devices based on zero-sequence current transformers and ring measuring converters for building up such protection systems. The methods for calculating zero-sequence currents in cables of a bunched cable line, depending on the SGF point and the currents in the responding elements, are developed, as well as a procedure for determining a damaged cable and methods for estimating the responding element thresholds and the length of the protection dead zone. Full article

Seconds count differently for people in danger. We present a real-time streaming pipeline for audio-based detection of hazardous life events affecting life and property. The system operates online rather than as a retrospective analysis tool. Its objective is to reduce the latency between the occurrence of a crime, conflict, or accident and the corresponding response by authorities. The key idea is to map reality as perceived by audio into a written story and question the text via a large language model. The method integrates streaming, zero-shot algorithms in an online decoding mode that convert sound into short, interpretable tokens, which are processed by a lightweight language model. CLAP text–audio prompting identifies agitation, panic, and distress cues, combined with conversational dynamics derived from speaker diarization. Lexical information is obtained through streaming automatic speech recognition, while general audio events are detected by a streaming version of Audio Spectrogram Transformer tagger. Prosodic features are incorporated using pitch- and energy-based rules derived from robust F0 tracking and periodicity measures. The system uses a large language model configured for online decoding and outputs binary (YES/NO) life-threatening risk decisions every two seconds, along with a brief justification and a final session-level verdict. The system emphasizes interpretability and accountability. We evaluate it on a subset of the X-Violence dataset, comprising only real-world videos. We release code, prompts, decision policies, evaluation splits, and example logs to enable the community to replicate, critique, and extend our blueprint. Full article

This study aims to analyze the spatial and temporal distribution of traffic accidents between 2017 and 2021 and their underlying causes. Antalya (Turkey) was selected as the study area due to its significant seasonal population fluctuations, which influence traffic patterns. Geographic Information Systems (GIS) were employed to investigate the spatial and temporal interactions of factors contributing to accidents, categorized as internal (e.g., driver age, driver errors) and external (e.g., road density, holiday periods, and the effects of the COVID-19 pandemic). Accidents were classified by type (e.g., fatal, injury related) to identify critical areas for intervention. The Kernel Density Estimation method was employed to detect accident hotspots, while driver characteristics, accident outcomes, and age distributions were systematically analyzed. The obtained results reveal that most accidents involved drivers aged 20–39 years, primarily due to negligence or failure to adjust speed to road conditions. Seasonal variations and holiday periods were also found to influence the spatial distribution of accidents. A detailed evaluation of high-risk roundabouts using Torus software 6.1 identified a potential design deficiency at one specific roundabout. These results provide valuable insights for improving traffic safety and optimizing road infrastructure in regions experiencing dynamic population changes. Full article

In recent years, artificial intelligence technology has developed rapidly, and the automobile industry has launched autonomous driving systems. However, autonomous driving systems installed in unmanned vehicles still have room to be strengthened in terms of cybersecurity. Many potential attacks may lead to traffic accidents and expose passengers to danger. We explored two potential attacks against autonomous driving systems: stroboscopic attacks and colored light illumination attacks, and analyzed the impact of these attacks on the accuracy of traffic sign recognition based on deep learning models, such as convolutional neural networks (CNNs) and You Only Look Once (YOLO)v5. We used the German Traffic Sign Recognition Benchmark dataset to train CNN and YOLOv5 to establish a machine learning model, and then conducted various attacks on traffic signs, including the following: LED strobe, various colors of LED light illumination and other attacks. By setting up an experimental environment, we tested how LED lights with different flashing frequencies and light color changes affect the recognition accuracy of the machine learning model. From the experimental results, we found that, compared to YOLOv5, CNN has better resilience in resisting the above attacks. In addition, different attack methods will interfere with the original machine learning model to some extent, affecting the ability of self-driving cars to recognize traffic signs. This may cause the self-driving system to fail to detect the presence of traffic signs, or make incorrect decisions about identification results. Full article

This paper addresses two safety issues regarding smart vehicles: that of intoxicated drivers (one of the most common causes for car accidents) and that of theft. More specifically, it presents the design and implementation of an intelligent system based on the Arduino-Mega2560 board. The issue of intoxicated drivers is addressed by using an MQ3 alcohol sensor that is capable of sensing the driver’s breath and a relay that immobilizes the vehicle if it detects alcohol above the permissible limit. Regarding theft, there are two safety layers: the first layer uses a fingerprint sensor which would not let the vehicle move unless the user is authenticated, while the second layer includes a GPS module that collects the information about the vehicle’s location and, through an incorporated GSM module, transmits the location data to an Internet-of-Things (IoT) server. The main contribution of the proposed system is that it treats two essential safety-security issues (drunk driving and theft) at the same time with the additional merits of low-cost implementation and easy placement and use within a vehicle. Full article