Search Results (80)

In the construction industry, occupational health and safety plays a critical role in preventing occupational accidents and increasing productivity. In recent years, computer vision and artificial intelligence-based systems have made significant contributions to improving these processes through automatic detection and tracking of objects. The aim of this study was to fine-tune object detection models and integrate them with Large Language Models for (i). accurate detection of personal protective equipment (PPE) by specifically focusing on helmets and (ii). providing real-time recommendations based on the detections for supporting the use of helmets in construction sites. For achieving the first objective of the study, large YOLOv8/v11/v12 models were trained using a helmet dataset consisting of 16,867 images. The dataset was divided into two classes: “Head (No Helmet)” and “Helmet”. The model, once trained, was able to analyze an image from a construction site and detect and count the people with and without helmets. A tool with the aim of providing advice to workers in real time was developed to fulfil the second objective of the study. The developed tool provides the counts of the people based on video feeds or analyzing a series of images and provides recommendations on occupational safety (based on the detections from the video feed and images) through an OpenAI GPT-3.5-turbo Large Language Model and with a Streamlit-based GUI. The use of YOLO enables quick and accurate detections; in addition, the use of the OpenAI model API serves the exact same purpose. The combination of the YOLO model and OpenAI model API enables near-real-time responses to the user over the web. The paper elaborates on the fine tuning of the detection model with the helmet dataset and the development of the real-time advisory tool. Full article

During the COVID-19 pandemic, a significant increase in the spread of healthcare-associated infections (HAIs) and antimicrobial resistance (AMR) was observed. Acinetobacter baumannii, particularly carbapenem-resistant strains, poses a serious threat in intensive care units (ICUs). This study aimed to genetically characterize A. baumannii isolates from the ICU of an infectious diseases hospital repurposed for COVID-19 patient treatment. Whole-genome sequencing (WGS) was performed on 56 A. baumannii isolates from patients and environmental surfaces using the Illumina MiSeq platform. Bioinformatic analysis included multi-locus sequence typing (MLST), core-genome MLST (cgMLST), phylogenetic analysis, and in silico detection of antimicrobial resistance genes. Three sequence types (STs) were identified: ST2 (35.7%), ST78 (30.4%), and ST19 (3.5%); while 30.4% of the isolates were non-typeable. Phylogenetic analysis revealed clustering of ST2 with isolates from East Africa, ST78 with European isolates, and ST19 with isolates from Germany and Spain. Resistance genes to eight classes of antimicrobials were detected. All isolates were resistant to aminoglycosides and β-lactams. The blaOXA-23 carbapenemase gene was present in all ST2 isolates. cgMLST analysis (cgST-1746) showed significant heterogeneity among ST2 isolates (24–583 allele differences), indicating microevolution within the hospital. A novel synonymous SNP (T2220G) in the rpoB gene was identified. Environmental sampling highlighted the role of contaminated personal protective equipment (PPE) in transmission, with 47.0% of ST2 and 64.3% of ST78 isolates found on PPE. The study underscores the high resolution of WGS and cgMLST for epidemiological surveillance and confirms the critical role of infection control measures in preventing the spread of multidrug-resistant A. baumannii. Full article

With the rapid advancement of industrial intelligence, ensuring occupational safety has become an increasingly critical concern. Among the essential personal protective equipment (PPE), safety helmets play a vital role in preventing head injuries. There is a growing demand for real-time detection of helmet chinstrap wearing status during industrial operations. However, existing detection methods often encounter limitations such as user discomfort or potential privacy invasion. To overcome these challenges, this study proposes a non-intrusive approach for detecting the wearing state of helmet chinstraps, inspired by the mechanosensory hair arrays found on spider legs. The proposed method utilizes multiple MEMS inertial sensors to emulate the sensory functionality of spider leg hairs, thereby enabling efficient acquisition and analysis of helmet wearing states. Unlike conventional vibration-based detection techniques, posture signals reflect spatial structural characteristics; however, their integration from multiple sensors introduces increased signal complexity and background noise. To address this issue, an improved adaptive convolutional neural network (ICNN) integrated with a long short-term memory (LSTM) network is employed to classify the tightness levels of the helmet chinstrap using both single-sensor and multi-sensor data. Experimental validation was conducted based on data collected from 20 participants performing wall-climbing robot operation tasks. The results demonstrate that the proposed method achieves a high recognition accuracy of 96%. This research offers a practical, privacy-preserving, and highly effective solution for helmet-wearing status monitoring in industrial environments. Full article

Despite advances in YOLO-based PPE detection, existing approaches primarily focus on architectural modifications. However, these approaches overlook second-order optimization methods for navigating complex loss landscapes in object detection. This study introduces SC-YOLO, integrating CSPDarknet backbone with Sophia optimization (leveraging efficient Hessian estimates for curvature-aware updates) for enhanced PPE detection on construction sites. The proposed methodology includes three key steps: (1) systematic evaluation of EfficientNet, DINOv2, and CSPDarknet backbones, (2) integration of Sophia second-order optimizer with CSPDarknet for curvature-aware updates, and (3) cross-dataset validation in diverse construction scenarios. Traditional manual PPE inspection exhibits operational limitations, including high error rates (12–15%) and labor-intensive processes. SC-YOLO addresses these challenges through automated detection with potential for real-time deployment in construction safety applications. Experiments on VOC2007-1 and ML-31005 datasets demonstrate improved performance, achieving 96.3–97.6% mAP@0.5 and 63.6–68.6% mAP@0.5:0.95. Notable gains include a 9.03% improvement in detecting transparent objects. The second-order optimization achieves faster convergence with 7% computational overhead compared to baseline methods, showing enhanced robustness over conventional YOLO variants in complex construction environments. Full article

In the coal industry, miner safety is increasingly challenged by growing mining depths and complex environments. The failure to wear Personal Protective Equipment (PPE) is a frequent issue in accidents, threatening lives and reducing operational efficiency. Additionally, existing PPE datasets are inadequate for model training due to their small size, lack of diversity, and poor labeling. Current methods often struggle with the complexity of multi-scenario and multi-type PPE detection, especially under varying environmental conditions and with limited training data. In this paper, we propose a novel minersPPE dataset and an improved algorithm based on YOLOv8, enhanced with Dilated-CBAM (Dilated Convolutional Block Attention Module) and DBB (Diverse Branch Block) Detection Block (YOLOv8-DCDB), to address these challenges. The minersPPE dataset constructed in this paper includes 14 categories of protective equipment needed for various body parts of miners. To improve detection performance under complex lighting conditions and with varying PPE features, the algorithm incorporates the Dilated-CBAM module. Additionally, a multi-branch structured detection head is employed to effectively capture multi-scale features, especially enhancing the detection of small targets. To mitigate the class imbalance issue caused by the long-tail distribution in the dataset, we adopt a K-fold cross-validation strategy, optimizing the detection results. Compared to standard YOLOv8-based models, experiments on the minersPPE dataset demonstrate an 18.9% improvement in detection precision, verifying the effectiveness of the proposed YOLOv8-DCDB model in multi-scenario, multi-type PPE detection tasks. Full article

Background: Parkinson’s disease (PD) is the second most common neurodegenerative disorder after Alzheimer’s disease, affecting countless individuals worldwide. PD is characterized by the onset of a marked motor symptomatology in association with several non-motor manifestations. The clinical phase of the disease is usually preceded by a long prodromal phase, devoid of overt motor symptomatology but often showing some conditions such as sleep disturbance, constipation, anosmia, and phonatory changes. To date, speech analysis appears to be a promising digital biomarker to anticipate even 10 years before the onset of clinical PD, as well serving as a useful prognostic tool for patient follow-up. That is why, the voice can be nominated as the non-invasive method to detect PD from healthy subjects (HS). Methods: Our study was based on cross-sectional study to analysis voice impairment. A dataset comprising 81 voice samples (41 from healthy individuals and 40 from PD patients) was utilized to train and evaluate common machine learning (ML) models using various types of features, including long-term (jitter, shimmer, and cepstral peak prominence (CPP)), short-term features (Mel-frequency cepstral coefficient (MFCC)), and non-standard measurements (pitch period entropy (PPE) and recurrence period density entropy (RPDE)). The study adopted multiple machine learning (ML) algorithms, including random forest (RF), K-nearest neighbors (KNN), decision tree (DT), naïve Bayes (NB), support vector machines (SVM), and logistic regression (LR). Cross-validation technique was applied to ensure the reliability of performance metrics on train and test subsets. These metrics (accuracy, recall, and precision), help determine the most effective models for distinguishing PD from healthy subjects. Result: Among all the algorithms used in this research, random forest (RF) was the best-performing model, achieving an accuracy of 82.72% with a ROC-AUC score of 89.65%. Although other models, such as support vector machine (SVM), could be considered with an accuracy of 75.29% and a ROC-AUC score of 82.63%, RF was by far the best one when evaluated across all metrics. The K-nearest neighbor (KNN) and decision tree (DT) performed the worst. Notably, by combining a comprehensive set of long-term, short-term, and non-standard acoustic features, unlike previous studies that typically focused on only a subset, our study achieved higher predictive performance, offering a more robust model for early PD detection. Conclusions: This study highlights the potential of combining advanced acoustic analysis with ML algorithms to develop non-invasive and reliable tools for early PD detection, offering substantial benefits for the healthcare sector. Full article

Ensuring that electrical workers use personal protective equipment (PPE) correctly is critical to electrical safety, but existing detection methods face significant limitations when applied in the electrical industry. This paper introduces MRC-DETR (Multi-Scale Re-calibration Detection Transformer), a novel framework for detecting Power Engineering Personal Protective Equipment (PEPPE) in complex electrical operating environments. Our method introduces two technical innovations: a Multi-Scale Enhanced Boundary Attention (MEBA) module, which significantly improves the detection of small and occluded targets through optimized feature representation, and a knowledge distillation strategy that enables efficient deployment on edge devices. We further contribute a dedicated PEPPE dataset to address the lack of domain-specific training data. Experimental results demonstrate superior performance compared to existing methods, particularly in challenging power industry scenarios. Full article

A total of 1.6 million tons of personal protective equipment (PPE) waste has been generated daily since 2019 and this production has not abated since that time. Within PPEs, isolation gowns make up the largest percentage by weight of landfill waste. This study aimed to evaluate the effectiveness of rapid, reproducible disinfection protocols to help facilitate safe reuse and minimize risks from microbial contamination. Disinfection of isolation gowns via fogging with hydrogen peroxide (HP) and hypochlorous acid (HC) were evaluated in the present study compared to standard ethylene oxide (EO) sterilization. This study was conducted at VCA West Coast Specialty and Emergency Animal Hospital in the United States. Ten isolation gowns (control) were cultured on tryptic soy agar contact plates in 10 predetermined areas to determine microbial load and morphology/types on non-sterile gowns before use. Following this, 10 gowns were fogged with 12% HP, and then once drying was complete, they were cultured in the predetermined areas for microbial load and morphology/types. This procedure was repeated with another set of 10 gowns fogged with 500 ppm HC. Lastly, 10 gowns were sterilized with EO using standard protocol and cultures were performed similarly. Median CFU (colony-forming unit) counts at 48 h for control, EO, HP, and HC were 4.5, 0, 0, and 0; at 72 h, they were 107, 0, 0, and 0, respectively. No significant difference was noted between the disinfection groups; post hoc pairwise analysis showed that the CFU counts for the disinfection groups were significantly lower than those for the control. The median percent reduction at 48 h for EO, HP, and HC was 100, 100, and 100; at 72 h, it was 100, 100, and 100, respectively. No significant difference was detected among the groups. The median number of microbe types for control, EO, HP, and HC was 2.5, 0, 0, and 0; there was no difference between the disinfection groups, but the number of microbe types was significantly higher for the control than for the disinfection groups. EO is environmentally toxic, expensive, and carcinogenic; it requires prolonged disinfection cycle times, expensive equipment, and trained personnel. This study suggests that HP and HC provide a cost-effective, relatively nontoxic, environmentally safe, and comparatively short disinfection time option for the disinfection and reuse of isolation gowns that does not require trained personnel or specialized equipment. Full article

Background/Objectives: The leakage of 5-fluorouracil (5-FU) from elastomeric infusion pumps used in cancer therapy poses a potential risk of unintentional exposure to multiple individuals, including patients’ relatives and healthcare professionals, and may also compromise the accurate administration of 5-FU dosages to patients. This study aimed to develop, validate, and apply an analytical method to detect and quantify 5-FU residues on the external surfaces of infusion pumps. Methods: A high-performance liquid chromatography with diode-array detection (HPLC-DAD) method was optimized for the quantification of 5-FU contamination across different components of the infusion pump, including the hard casing, infusion tubing, and catheter connection port. A mobile phase containing 5% acetic acid was used to obtain more efficient separation of 5-FU and the detection was performed at 260 nm. The method was evaluated for linearity, sensitivity, precision, accuracy, selectivity, robustness, and stability. Results: The method demonstrated linearity within the range of 0.150 to 3.000 µg/cm², with limits of detection and quantification of 0.05 µg/cm² and 0.14 µg/cm², respectively. Relative standard deviations ranged from 1.8% to 12.7%, and accuracy exceeded 85%. In real sample analysis, detectable residues were found around the catheter connection port. Conclusions: This screening-oriented method addresses an existing gap, as previous contamination reports were based solely on self-reported user observations. The detection of 5-FU residues highlights the critical need for safe handling practices and the consistent use of personal protective equipment (PPE) to protect healthcare workers, especially nursing staff involved in the removal of the infusion pumps, after treatment. Full article

This study introduces ESPCN-YOLO, an innovative deep learning framework designed to enhance the detection accuracy of Personal Protective Equipment (PPE) under challenging conditions, including low-light environments, long-distance scenarios, and small object detection. The proposed system integrates a YOLOv8-based object detection model with an Efficient Sub-Pixel Convolutional Neural Network (ESPCN) to perform real-time super-resolution enhancement on low-resolution footage. The framework was trained on a custom dataset containing 21,750 annotated images categorized into four PPE classes: helmets, shoes, vests, and persons. Extensive experiments were conducted under varying conditions, including distances ranging from 4 to 14 m, resolutions of 640 × 480 and 1920 × 1080, and brightness levels adjusted from −90% to +70%. The results demonstrate that integrating an ESPCN (3×) with YOLOv8 significantly improves detection accuracy, particularly for small objects and poorly illuminated environments. The model achieved a mean average precision (mAP@0.5) of 0.922 and a stringent mAP@0.5:0.95 of 0.741. Additionally, an automated alert system was implemented to enable real-time PPE compliance monitoring. This study highlights the effectiveness of super-resolution enhancement in increasing detection robustness and provides a practical solution for real-time safety monitoring in industrial environments. Full article

Porcine proliferative enteropathy (PPE) is an infectious disease in pigs, caused by Lawsonia intracellularis (LI), affecting their intestines during growth and finishing stages, leading to higher production costs. Current detection methods for LI face two main challenges, delayed results and high costs, making them impractical for large-scale pig farming epidemiological surveys. This study developed a TaqMan-qPCR method using specific probes and primers based on the LI aspartate ammonia lyase genes from GenBank, completing detection in just 45 min. After optimizing reaction conditions, sensitivity analysis revealed that the detection limit of this method was 4.6 copies/μL targeting standard plasmids. The results of the specificity analysis showed no cross-reactivity with other common porcine pathogens, highlighting its specificity. The inter- and intra-group coefficients of variation were both <1%, indicating high reproducibility. Furthermore, the TaqMan-qPCR demonstrated 100% relative sensitivity, and a 92.50% compliance rate compared to conventional PCR, suggesting it could be a complement to the conventional PCR method. In summary, the TaqMan-qPCR method established in this study is not only suitable for epidemiological investigations and early qualitative and quantitative diagnosis of proliferative enteropathy in pigs, but it is also valuable for studying the biological characteristics of LI. Full article

Background: Electrocardiographic (ECG) screening is crucial in pre-participation evaluations (PPEs) for elite athletes, aiding in the early detection of cardiac adaptations and potential risks. Elite female gymnasts experience unique cardiovascular adaptations due to intensive training, yet limited longitudinal data exist on their ECG evolution. This study introduces Oracle Crystal Ball, a predictive tool for forecasting ECG abnormalities and assessing PPE cost-effectiveness to optimize screening protocols. Methods: This retrospective cohort study analyzed ECG and cardiovascular parameters in twelve elite female gymnasts who underwent up to 14 PPEs over several years at the National Institute of Sports Medicine, Romania. Longitudinal ECG trends, training variables, and biochemical markers were examined using statistical analyses, including logistic regression, repeated measures ANOVA, and time-series forecasting (ARIMA). Monte Carlo simulations assessed the cost-effectiveness of 6-month vs. 12-month PPE schedules. Results: The athletes exhibited significant cardiovascular adaptations, including progressive declines in resting heart rate and training-induced ECG changes. Junctional escape rhythms and T-wave inversions (V1–V3) increased with age, requiring refined ECG interpretation. Predictive modeling demonstrated the feasibility of individualized risk stratification, while a cost-effectiveness analysis revealed that a 12-month PPE schedule was financially advantageous without reducing diagnostic accuracy. Conclusions: Longitudinal ECG monitoring and predictive analytics improve risk assessment in elite gymnasts. Oracle Crystal Ball enhances athlete-specific screening, minimizing unnecessary tests while ensuring early detection of clinically significant ECG changes. A 12-month PPE schedule is a cost-effective alternative for elite athletes. Full article

Non-Protective Personal Equipment (PPE) detection is crucial on construction sites. Although deep learning models are adept at identifying such information from on-site cameras, their success relies on large, diverse, and high-quality datasets. Image augmentation offers an alternative for artificially broadening dataset diversity. However, its impact on non-PPE detection in construction environments has not been adequately examined. This study introduces a methodology applying eight distinct augmentation techniques—brightness, contrast, perspective, rotation, scale, shearing, translation, and a combined strategy incorporating all methods. Model performance was assessed by comparing accuracy across different classes and architectures, both with and without augmentation. While most of these augmentations improved accuracy, their effectiveness was found to be task-dependent. Moreover, the most beneficial augmentation varied by non-PPE class and architecture, suggesting that augmentation strategies should be tailored to the unique features of each class and model. Although the primary focus here is on non-PPE, the evaluated techniques could also extend to related tasks on construction sites, such as detecting heavy equipment or identifying hazardous worker behavior. Full article

Background: West Nile virus (WNV) is a mosquito-borne RNA virus, with birds as reservoirs and humans as incidental hosts. WNV often causes asymptomatic infections, but severe neuroinvasive disease occurs in fewer than 1% of human cases. Recent climatic changes and occupational exposure have increased its spread, particularly in Southern Italy. This study aimed to assess WNV seroprevalence and occupational risks among outdoor workers to guide targeted public health interventions. Methods: This cross-sectional study was conducted in the Apulia region, southeastern Italy, from November 2023 to April 2024. Participants completed a detailed questionnaire on socio-demographics, occupational exposure, travel history, and health symptoms. Blood samples were analyzed using enzyme-linked immunosorbent assay (ELISA) and neutralization assays to detect WNV-specific antibodies. Results: 250 outdoor workers in southeastern Italy were recruited, including agricultural workers, veterinarians, forestry workers, and livestock breeders. The latter showed the highest WNV prevalence at 6.5%. Protective measures such as repellent use (β = −0.145, OR = 0.95, p = 0.019) and personal protective equipment (PPE) usage (β = −0.12, OR = 0.94, p = 0.04) significantly reduced the likelihood of WNV infection. Conclusions: The study highlights the significant occupational risk posed by WNV to outdoor workers involved in livestock breeding in Southern Italy, likely due to their frequent exposure to mosquito-prone environments. Tailored public health strategies and education programs are needed to protect high-risk outdoor workers from WNV, amidst the backdrop of changing climatic conditions that favor increased transmission. Full article

Construction projects’ unsatisfactory performance has been linked to factors influencing individuals’ well-being and mental alertness on projects. Drowsiness is a significant indicator of sleep deprivation and fatigue, so being able to identify the cognitive and physical preparedness of workers on site to engage in construction tasks is important. As a consequence of the strenuous nature of the work involved in construction, long work hours, and environmental conditions, drowsiness is commonplace and has received less attention despite being a leading cause of accidents occurring on-site. Detecting drowsiness is essential for determining the safety and well-being of site workers. This study presents a vision-based approach using an improved version of the You Only Look Once (YOLOv8) algorithm for real-time drowsiness exposure among construction workers. The proposed method leverages computer vision techniques to analyze facial and eye features, enabling the early detection of signs of drowsiness, effectively preventing accidents, and enhancing on-site safety. The model showed significant precision and efficiency in detecting drowsiness from the given dataset, accomplishing a drowsiness class with a mean average precision (mAP) of 92%. However, it also exhibited difficulties handling imbalanced classes, particularly the underrepresented ‘Awake with PPE’ class, which was detected with high precision but comparatively lower recall and mAP. This highlighted the necessity of balanced datasets for optimal deep learning performance. The YOLOv8 model’s average mAP of 78% in drowsiness detection compared favorably with other studies employing different methodologies. The system improves productivity and reduces costs by preventing accidents and enhancing worker safety. However, limitations, such as sensitivity to lighting conditions and occlusions, must be addressed in future iterations. Full article