Search Results (175)

Background: Since the introduction of rental e-scooters, they have become a popular mode of transportation not only in German cities but in other cities as well. However, this rapid increase in usage has coincided with a significant rise in associated injuries and accidents, outpacing those related to bicycles. A disproportionate number of these incidents involve alcohol consumption and young people under the age of 25, with a low incidence of helmet use. Following the example of driver training for children on bicycles, we carried out driver safety training with e-scooters and examined the results scientifically. Methods: The study conducted three voluntary driving safety training sessions in Berlin and Munich, with participants completing questionnaires before and after the training to measure their knowledge and skills (on a scale between 0 and 5; 0 = totally insecure and 5 = absolutely secure). The training included a technical introduction, practical exercises, and an educational component on injury data and prevention strategies. During the statistical analysis, the novice drivers (group 1) were compared to the non-novice drivers (group 2). Results: Out of 136 participants, 103 completed the training (a response rate of 75.7%). The mean age of the participants was 37.1 years, and 52.4% of them were female. A total of 59% had never used an e-scooter and were therefore assigned to group 1 (group 2 = experienced drivers). Both groups showed significant improvements in both knowledge of traffic laws and driving skills. Conclusions: The findings suggest that driving safety training potentially enhances the safe operation of e-scooters. However, the training demands a high level of time and motivation, making it less attractive for younger drivers who are most prone to accidents. Therefore, we recommend the use of digital driving safety training before the first use of e-scooters. Full article

Reliable detection of safety helmets is essential for ensuring personnel protection in large-scale outdoor operations. However, recognition becomes difficult when monitoring relies on low-resolution or compressed video streams captured by fixed or mobile platforms such as UAVs—conditions commonly encountered in intelligent transportation and urban surveillance. This study proposes a super-resolution-enhanced detection framework that integrates video super-resolution with ROI-guided inference to improve the visibility of small targets while reducing computational cost. Focusing on a single, carefully selected VSR module (BasicVSR++), the framework achieves an F1-score of 0.904 in helmet detection across multiple low-quality surveillance scenarios. This demonstrates the framework’s effectiveness for robust helmet monitoring in low-resolution and compressed surveillance scenarios. Full article

The construction industry relies on the Internet of Things (IoT) and wearable technologies to enhance workplace safety. This research investigates the use of IoT and wearable technology among Saudi Arabian construction sector employees, analyzing their implementation difficulties and the factors contributing to successful implementation. A structured questionnaire was distributed to 567 construction professionals across different roles and projects. Frequency analysis was used to study adoption patterns, chi-square tests to study demographic factors, and principal component analysis for exploratory factor analysis to discover hidden adoption factors. The findings show that smart safety vests and helmets receive the highest level of recognition. On the other hand, advanced monitoring systems, including fatigue and environmental sensors, are not used enough. Group differences in device adoption were investigated in terms of years of experience, academic qualification, job role, and project budget. The findings from factor analysis show that three main factors determine adoption rates, which include (1) safety and operational effectiveness, (2) worker acceptance and support structures, and (3) technical and adoption barriers. A data-driven system is created to help policymakers and industry leaders accelerate construction safety digitalization efforts. 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

Despite the agricultural sector’s consistently high injury rates, formal reporting is often limited, leading to sparse national datasets that hinder effective safety interventions. To address this, our study introduces a comprehensive framework leveraging advanced ensemble machine learning (ML) models to predict and interpret the severity of agricultural injuries. We use a unique, manually curated dataset of over 2400 agricultural incidents from AgInjuryNews, a public repository of news reports detailing incidents across the United States. We evaluated six ensemble models, including Gradient Boosting (GB), eXtreme Grading Boosting (XGB), Light Gradient Boosting Machine (LightGBM), Adaptive Boosting (AdaBoost), Histogram-based Gradient Boosting Regression Trees (HistGBRT), and Random Forest (RF), for their accuracy in classifying injury outcomes as fatal or non-fatal. A key contribution of our work is the novel integration of explainable artificial intelligence (XAI), specifically SHapley Additive exPlanations (SHAP), to overcome the “black-box” nature of complex ensemble models. The models demonstrated strong predictive performance, with most achieving an accuracy of approximately 0.71 and an F1-score of 0.81. Through global SHAP analysis, we identified key factors influencing injury severity across the dataset, such as the presence of helmet use, victim age, and the type of injury agent. Additionally, our application of local SHAP analysis revealed how specific variables like location and the victim’s role can have varying impacts depending on the context of the incident. These findings provide actionable, context-aware insights for developing targeted policy and safety interventions for a range of stakeholders, from first responders to policymakers, offering a powerful tool for a more proactive approach to agricultural safety. Full article

Maintaining a safe working environment for construction workers is critical to the improvement of urban areas. Several issues plague the present safety helmet detection technologies utilized on construction sites. Some of these issues include low accuracy, expensive deployment of edge devices, and complex backgrounds. To overcome these obstacles, this paper introduces a detection method that is both efficient and based on an improved version of YOLOv8n. Three components make up the superior algorithm: the C2f-SCConv architecture, the Partial Convolutional Detector (PCD), and Coordinate Attention (CA). Detection, redundancy reduction, and feature localization accuracy are all improved with coordinate attention. To further enhance feature quality, decrease computing cost, and make corrections more effective, a Partial Convolution detector is subsequently constructed. Feature refinement and feature representation are made more effective by using C2f-SCConv instead of the bottleneck C2f module. In comparison to its predecessor, the upgraded YOLOv8n is superior in every respect. It reduced model size by 2.21 MB, increased frame rate by 12.6 percent, decreased FLOPs by 49.9 percent, and had an average accuracy of 94.4 percent. This method is more efficient, quicker, and cheaper to set up on-site than conventional helmet-detection algorithms. Full article

Background/Objectives: In recent years, electric scooters have gained widespread popularity as an easy and affordable mode of transport in urban areas worldwide. Simultaneously, trauma centers have observed an increasing number of associated injuries to users. While injury patterns associated with other vehicles are now well-researched, electric-scooter-related injuries are a new topic in the literature. Our study aims to investigate the differences in injury patterns and other critical crash characteristics among riders of bicycles, electric scooters, and scooters. Methods: This one-year retrospective observational study examined patients who sustained injuries while riding bicycles, electric scooters, or scooters between April 2021 and March 2022 at Hungary’s largest trauma center in Budapest. During this one-year period, we identified 1938 patients, 1378 cyclists, 370 electric scooter users, and 190 scooter users. Basic demographic information, recorded injury type and severity, time of day the injury occurred, and alcohol usage were recorded as outcome measures. Results: While 4.6% of cyclists and 5.8% of scooter riders had consumed alcohol, 26.8% of electric scooter riders were under the influence of alcohol at the time of their crash. Of electric-scooter-related injuries, 45.8% occurred at night, compared to only 9.2% and 14.1% of bike and scooter-related injuries, respectively. E-scooter crashes constituted 19.1% of total cases but surged to 52.3% at night. Patients under the influence of alcohol were much more likely to experience mild head injuries (p < 0.0001) and severe head injuries (p < 0.0001), but less likely to suffer mild limb injuries (p < 0.0001) and severe limb injuries (p < 0.0001) compared with sober patients. Cyclists had significantly 3 times fewer cases of severe head trauma than those injured while using electric scooters (p = 0.0166). Conclusions: The study highlights a significant risk of severe craniofacial injuries in e-scooter users after consuming alcohol, exceeding that in sober riders and cyclists. Predominantly occurring at night, these injuries are closely linked with alcohol use. The findings advocate for mandatory helmet laws and stricter regulations on e-scooter use to enhance safety, especially at night. Full article

Object detection in complex scenarios such as construction sites, electric power operations, and resource exploration often suffers from low accuracy and frequent missed or false detections. To address these challenges, this study proposes a modified You Only Look Once version 8 nano (YOLOv8n)-based algorithm, termed YOLOv8n-ASA, for safety-helmet-wearing detection. The proposed method introduces structural asymmetry into the network to enhance feature representation and detection robustness. Specifically, an Adaptive Kernel Convolution (AKConv) module is incorporated into the backbone, in which asymmetric kernels are used to better capture features of irregularly shaped objects. The Simple Attention Module (SimAM) further sharpens the focus on critical regions, while the Asymptotic Feature Pyramid Network (AFPN) replaces the symmetric top–down fusion pathway of the traditional FPN with a progressive and asymmetric feature integration strategy. These asymmetric designs mitigate semantic gaps between non-adjacent layers and enable more effective multi-scale fusion. Extensive experiments demonstrate that YOLOv8n-ASA achieves superior accuracy and robustness compared to several benchmarks, validating its effectiveness for safety-helmet-wearing detection in complex real-world scenarios. Full article

Intelligent personnel safety management is a critical component of smart manufacturing infrastructure. This paper presents an integrated framework combining a structurally optimized neural network (enhanced with spatial and channel feature fusion mechanisms for multi-scale detection) with an agent-based large language model (LLM) enhanced with retrieval-augmented generation (RAG) capabilities for factory safety monitoring. The visual detection component employs the Similarity-Aware Channel Pruning (SACP) method for automated, performance-preserving compression by identifying and suppressing redundant channels based on similarity and norm regularization, while the agent-based LLM with RAG capabilities dynamically integrates real-time violation data with established safety management protocols to generate precise diagnostic reports and operational recommendations. The optimized network achieves real-time violation detection in parallel video streams, and the LLM-powered assistant facilitates intelligent decision-making through natural language querying. Extensive evaluations on multiple benchmark datasets and a real-world safety helmet detection dataset demonstrate the scheme’s superior performance in both accuracy and practical applicability for industrial deployment. Full article

Three-dimensional (3D) reconstruction is increasingly being adopted in construction site management. While most existing studies rely on auxiliary equipment such as LiDAR and depth cameras, monocular depth estimation offers broader applicability under typical site conditions, yet it has received limited attention due to the inherent scale ambiguity in monocular vision. To address this limitation, this study proposes a safety helmet-based scale recovery framework that enables low-cost, monocular 3D reconstruction for construction site monitoring. The method utilizes safety helmets as exemplary scale carriers due to their standardized dimensions and frequent appearance in construction scenes. A Standard Template Library (STL) comprising multi-angle safety helmet masks and dimensional information is established and linked to site imagery through template matching. Following three-dimensional scale recovery, multi-frame fusion is applied to optimize the scale factors. Experimental results on multiple real construction videos demonstrate that the proposed method achieves high reconstruction accuracy, with a mean relative error below 10% and outliers not exceeding 5%, across diverse construction environments without site-specific calibration. This work aims to contribute to the practical application of monocular vision in engineering management by leveraging ubiquitous site objects as metrological references. Full article

Construction sites are complex environments, and unsafe behaviors by workers, such as not wearing safety helmets or reflective vests, can easily lead to accidents. When using target detection technology to detect unsafe behaviors, the results are often unsatisfactory due to the complexity of the background and the small size of the targets. This paper proposes an unsafe behavior detection algorithm based on dual adaptive feature fusion. The algorithm is based on YOLOv5, introducing a front-end adaptive feature fusion module (FE-AFFM) at the head of the backbone network for deep data processing, improving the model’s feature extraction capability in complex backgrounds. Simultaneously, a back-end adaptive feature fusion module (BE-AFFM) is introduced at the tail of the network to strengthen feature fusion. In the experimental verification phase, this paper selects a self-made laboratory dataset and verifies the effectiveness of the improved algorithm through ablation experiments, algorithm comparisons, and heatmap analysis. The average accuracy of the improved algorithm is 3.6% higher than the baseline model, and the detection effect on small targets is significantly improved, meeting the actual needs of construction sites. This paper also selects the publicly available dataset SHWD for algorithm comparison experiments. The results show that the improved algorithm still has a significant advantage over mainstream algorithms, verifying the generalization ability of the improved model. Full article

Despite preventive measures, the construction industry continues to exhibit high accident rates. In response, visual detection system was developed to support safety management on construction sites and promote sustainable working environments. The solution integrates the YOLOv8 algorithm with asynchronous video processing, incident registration, an open API, and a web-based interface. The system detects the absence of safety helmets (NHD) and worker falls (FD). Its low hardware requirements make it suitable for small and medium-sized construction enterprises, contributing to resource efficiency and digital transformation in line with sustainable development goals. This study advances practice by providing an integrated, low-resource solution that unites multi-hazard detection, event documentation, and system interoperability, addressing a key gap in existing research and implementations. The contribution includes an operational architecture proven to run in real time, addressing a gap between model-centred research and deployable, OHS applications. The system was validated using two independent test datasets, each comprising 100 images: one for NHD and one for FD. For NHD, the system achieved a precision of 0.93, an accuracy of 0.88, and an F1-score of 0.79. For FD, a precision of 1.00, though with a limited recall of 0.45. The results demonstrate the system’s potential for sustainable construction site safety monitoring. Full article

This study examines the effects of different stereoscopic technologies on physiological responses in immersive virtual reality (VR) environments. Five participant groups were evaluated: a control group (no stereoscopy) and four groups using anaglyph, passive, active glasses, or VR helmets. Heart rate variability (HRV) was measured in both time (MeanRR, SDNN, RMSSD, pNN50) and frequency (LF, HF, LF/HF) domains to assess autonomic nervous system activity. Active, polarized glasses and VR helmets significantly reduced SDNN and RMSSD compared to the control group (p < 0.01), with VR helmets causing the largest decrease (MeanRR −70%, RMSSD −51%). Anaglyph glasses showed milder effects. Nonlinear analysis revealed reduced entropies and Hurst parameter in highly immersive conditions, indicating impaired fractal heart rate structure and increased physiological load. These results demonstrate a clear relationship between immersion level and cardiovascular response, emphasising that higher immersion increases physiological stress. The scientific contribution lies in the combined application of linear and nonlinear HRV analysis to systematically compare different stereoscopic display types under controlled gaming immersion. The study proposes a practical methodology for assessing HRV in VR settings, which can inform the ergonomic design of VR systems and ensure users’ physiological safety. By highlighting the differential impacts of stereoscopic technologies on HRV, the findings offer guidance for optimising VR visualisation to balance immersive experience with user comfort and health. Full article

Objectives: The aim of this study was to determine the epidemiological characteristics of bicycling-related maxillofacial fractures in a defined population and to identify factors contributing to these injuries. Methods: An 8-year cohort study was carried out, including all patients presenting with bicycling-related maxillofacial fractures at a tertiary care center from 2017 through 2024. Data recorded for each patient included age, gender, date and cause of injury, contributing factors, type of facial fractures, other injuries, hospital stay, and helmet use. Statistical analysis was performed. Continuous variables were assessed for normality (Shapiro–Wilk test) and compared using the Mann–Whitney test. Categorical variables were analyzed with chi-square tests. A p-value ≤ 0.05 was considered statistically significant. Results: Out of 899 cycling accident patients seeking medical treatment, 122 (13%) sustained facial fractures, accounting for 4% of all facial fracture cases in our department during the study period. In our cohort, the male–female ratio was 2.6:1, and the mean age was 29.5 years (SD 12.8, range 13–77). Collision with another object/vehicle was the most common cause (64%), followed by isolated falls (36%). A total of 135 facial fractures were recorded (some patients had multiple fractures). Mandibular fractures were most frequent (49% of patients), followed by zygomatic (32%), orbital (13%), nasal (7%), maxillary (2%) and frontal (2%) fractures. Among mandibular injuries, condylar fractures were the most common subtype (63%). Dental injuries were found in 27% of patients. The most common dental trauma was tooth fracture (43% of those with dental injuries), followed by tooth luxation (32%) and tooth avulsion (25%). In 80% of cases involving dental injuries, the upper anterior teeth were involved. Concomitant injuries were present in 20% of patients, most often orthopedic limb injuries. Only 27% of patients reported always wearing a helmet, whereas 43% reported never having worn one. Conclusions: Bicycling-related facial injuries are a noteworthy subset of facial trauma. Missed or delayed diagnosis can lead to lasting deformities and functional issues. Preventive strategies—especially promoting helmet use and improving helmet design—along with broader safety measures are important to reduce the incidence and severity of these injuries. Full article

Although computer vision methods have advanced in construction helmet detection in recent years, their performance heavily depends on large-scale, class-balanced, and diverse annotated datasets. To address the high cost and labor-intensive nature of traditional data collection and annotation, this study introduces a novel helmet detection dataset named AIGC-HWD (Artificial Intelligence-Generated Content–Helmet Wearing Detection), automatically generated using generative AI tools. The dataset contains five categories of labels, supporting both helmet-wearing detection and color classification tasks. We evaluate the standalone performance of AIGC-HWD, as well as its augmentation effect when combined with the real-world dataset GDUT-HWD, using multiple algorithms, including YOLO v8, YOLO v10, YOLO 11, YOLO v11-MobileNet v4, YOLO v13, Faster R-CNN, and RT-DETR. Experimental results show that models trained solely on AIGC-generated images can achieve mAP@50 scores exceeding 0.7 and 0.8 on real-world images in two separate tests, demonstrating a certain level of generalization. When used for data augmentation alongside real-world images, the performance improves to varying degrees—by approximately 1% on the YOLO series, and by over 10% on the two-stage algorithm Faster R-CNN. These findings validate the potential of generative AI images for safety monitoring in construction scenarios and provide new insights into the integration of synthetic and real-world data. Full article