Search Results (283)

Background: Seafarers are highly susceptible to work-related injuries, which can result in serious consequences or permanent disabilities. Understanding the frequency and characteristics of occupational injuries is crucial for developing effective prevention strategies and identifying their underlying patterns and causes. This study aimed to determine the frequency and characteristics of telemedicine-assisted work-related injuries among seafarers on board Italian-flagged vessels. Methods: A retrospective descriptive study was conducted to analyze occupational injuries using medical data recorded in the Centro Internazionale Radio Medico (C.I.R.M.) database from 1 January 2010 to 31 December 2022. Injuries in the database were coded according to the 10th revision of the International Classification of Diseases (ICD-10) by the World Health Organization (WHO). Variables extracted from the database included injury type, seafarers’ age, rank, nationality, worksite, gender, date of injury, affected body region, clinical outcomes, and other demographic and occupational characteristics. Injury frequency and characteristics (e.g., location, type, and cause) were analyzed and stratified by seafarers’ rank and worksite groups. Results: The analysis included 793 seafarers who sustained injuries. Their average age was 39.15 ± 10.49 years (range: 21 to 70 years). Deck ratings and engine officers accounted for 27.9% and 20% of those who claimed injuries, respectively. 39.2% of injured seafarers were aged between 30 and 40 years. In terms of affected body parts, the most reported injuries were to the hand/wrist (33.3%), followed by the knee/lower legs (21%), and the head/eye (19%). Open wounds (38%) and burns/abrasions (14%) were the most common types of injury. Slips/falls (32%), burns/explosions (16.6%), and overexertion while lifting or carrying (14.8%) were the leading causes of injury during the study period. Nearly 35% of injuries affected workers on the deck and were due mainly to slips/falls, 19% in the engine room were due to being caught in machinery or equipment, and 32.5% in the catering department were due to burns/explosions. Conclusions: One-third of seafarers who suffered work-related injuries sustained hand and/or wrist injuries, with slips/falls being a significant cause. The results of this study emphasize the need for preventative measures in the marine sector, particularly to reduce risks associated with slips and falls, overexertion, and other injury-causing factors. Campaigns for the larger use of protective equipment are desirable to reduce occupational accidents at sea and provide better health protection for seafarers. Full article

Air compressors are vital across various sectors—automotive, manufacturing, buildings, and healthcare—as they provide pressurized air for air suspension systems in vehicles, supply power pneumatic machines throughout industrial production lines, and support non-clinical infrastructure within hospital environments, including pneumatic control systems, isolation room pressurization, and laboratory equipment operation. Ensuring that such components are reliable is critical, as unexpected failures can disrupt facility functions and compromise patient safety. Predictive maintenance (PdM) has emerged as a key factor in enhancing the reliability and operational efficiency of medical devices by leveraging sensor data and artificial intelligence (AI)-based algorithms to detect component degradation before functional failures occur. In this paper, a predictive maintenance solution for condition monitoring and fault prediction for the exhaust valve, bearings, water pump, and radiator of an air compressor is presented, by comparing a hybrid deep neural network (DNN) as a feature extractor and a support vector machine (SVM) for condition classification: a pure DNN classifier as well as a standalone SVM model. Additionally, each model was trained and validated on three devices—NVIDIA T4 GPU, Raspberry Pi 4 Model B, and NVIDIA Jetson Nano—and performance reports in terms of latency, energy consumption, and CO₂ emissions are presented. Moreover, three model agnostic explainable AI (XAI) methods were employed to increase the transparency of the hybrid model’s final decision: Shapley additive explanations (SHAP), local interpretable model-agnostic explanations (LIME) and partial dependence plots (PDP). The hybrid model achieves on average 98.71%, 99.25%, 98.78%, and 99.01% performance in terms of accuracy, precision, recall, and F1-score across all devices Additionally, the DNN baseline and SVM model achieve on average 93.2%, 88.33%, 90.45%, and 89.37%, as well as 93.34%, 88.11%, 95. 41%, and 91.62% performance in terms of accuracy, precision, recall, and F1-score across all devices. The integration of XAI methods within the PdM pipeline offers enhanced transparency, interpretability, and trustworthiness of predictive outcomes, thereby facilitating informed decision-making among maintenance personnel. Full article

Residential courtyards serve as critical mediators between architecture and nature in contemporary high-density urban environments. However, extant scholarship predominantly examines isolated courtyard typologies, lacking comprehensive systemic analysis, while contemporary designs frequently suffer from functional diminishment. This study investigates 72 representative Japanese detached residential projects (2015–2024) to systematically analyze spatial configurations, compositional characteristics, and functional interrelationships between courtyards and interior spaces. The methodological framework incorporates typological classification based on spatial positioning and constituent elements, coupled with analytical examination of aperture connections, interpreted through the lens of pattern language theory. Findings reveal a distinct hierarchical organization and a set of recurrent design patterns: front courtyards predominantly employ “partially walkable” surfaces with symbol trees to reconcile circulatory and esthetic functions, establishing a transitional sequence; central courtyards achieve daylight optimization and spatial extension through compact dimensions and non-paved surfaces, creating intimate outdoor rooms; side courtyards demonstrate scale-dependent adaptive strategies for privacy and microclimate regulation. The predominant living room-courtyard interface configuration features “group-planted trees with large openings,” creating vertically stratified visual experiences. This tripartite system translates traditional nature concepts into evidence-based spatial patterns, providing a transferable design matrix and pattern language for human-centered courtyard design in high-density contexts. Full article

The precise identification, classification, sorting, and rapid and accurate quality assessment of soybean seeds are extremely important in terms of the continuity of agricultural production, varietal purity, seed processing, protein extraction, and food safety. Currently, commonly used methods for the identification and quality assessment of soybean seeds include morphological analysis, chemical analysis, protein electrophoresis, liquid chromatography, spectral analysis, and image analysis. The use of image analysis and artificial intelligence is the aim of the presented research, in which a method for the automatic classification of soybean varieties, the assessment of the degree of damage, and the identification of geometric features of soybean seeds based on numerical models obtained using a 3D scanner has been proposed. Unlike traditional two-dimensional images, which only represent height and width, 3D imaging adds a third dimension, allowing for a more realistic representation of the shape of the seeds. The research was conducted on soybean seeds with a moisture content of 13%, and the seeds were stored in a room with a temperature of 20–23 °C and air humidity of 60%. Individual soybean seeds were scanned to create 3D models, allowing for the measurement of their geometric parameters, assessment of texture, evaluation of damage, and identification of characteristic varietal features. The developed 3D-CNN network model comprised an architecture consisting of an input layer, three hidden layers, and one output layer with a single neuron. The aim of the conducted research is to design a new, three-dimensional 3D-CNN architecture, the main task of which is the classification of soybean seeds. For the purposes of network analysis and testing, 22 input criteria were defined, with a hierarchy of their importance. The training, testing, and validation database of the SB3D-NET network consisted of 3D models obtained as a result of scanning individual soybean seeds, 100 for each variety. The accuracy of the training process of the proposed SB3D-NET model for the qualitative classification of 3D models of soybean seeds, based on the adopted criteria, was 95.54%, and the accuracy of its validation was 90.74%. The relative loss value during the training process of the SB3D-NET model was 18.53%, and during its validation process, it was 37.76%. The proposed SB3D-NET neural network model for all twenty-two criteria achieves values of global error (GE) of prediction and classification of seeds at the level of 0.0992. Full article

Lung disease diagnosis from chest X-ray images is a critical task in clinical care, especially in resource-constrained settings where access to radiology expertise and computational infrastructure is limited. Recent advances in deep learning have shown promise, yet most studies focus solely on either classification or detection in isolation, rarely exploring their combined potential in an embedded, real-world setting. To address this, we present a dual deep learning approach that combines five-class disease classification and multi-label thoracic abnormality detection, optimized for embedded edge deployment. Specifically, we evaluate six state-of-the-art CNN architectures—ResNet101, DenseNet201, MobileNetV3-Large, EfficientNetV2-B0, InceptionResNetV2, and Xception—on both base (2020 images) and augmented (9875 images) datasets. Validation accuracies ranged from 55.3% to 70.7% on the base dataset and improved to 58.4% to 72.0% with augmentation, with MobileNetV3-Large achieving the highest accuracy on both. In parallel, we trained a YOLOv8n model for multi-label detection of 14 thoracic diseases. While not deployed in this work, its lightweight architecture makes it suitable for future use on embedded platforms. All classification models were evaluated for end-to-end inference on a Raspberry Pi 4 using a high-resolution chest X-ray image (2566 × 2566, PNG). MobileNetV3-Large demonstrated the fastest latency at 429.6 ms, and all models completed inference in under 2.4 s. These results demonstrate the feasibility of combining classification for rapid triage and detection for spatial interpretability in real-time, embedded clinical environments—paving the way for practical, low-cost AI-based decision support systems for surgery rooms and mobile clinical environments. Full article

Stroke is a major global cause of death and disability and necessitates both quick diagnosis and treatment within narrow windows of opportunity. CT scanning is still the first-line imaging in the acute phase, but correct interpretation may not always be readily available and may not be resource-available in poor and rural health systems. Automated stroke classification systems can offer useful diagnostic assistance, but clinical application demands high accuracy and explainable decision-making to maintain physician trust and patient safety. In this paper, a ResNet-18 model was trained on 6653 CT brain scans (hemorrhagic stroke, ischemia, normal) with two-phase fine-tuning and transfer learning, XRAI explainability analysis, and web-based clinical decision support system integration. The model performed with 95% test accuracy with good performance across all classes. This system has great potential for emergency rooms and resource-poor environments, offering quick stroke evaluation when specialists are not available, particularly by rapidly excluding hemorrhagic stroke and assisting in the identification of ischemic stroke, which are critical steps in considering tissue plasminogen activator (tPA) administration within therapeutic windows in eligible patients. The combination of classification, explainability, and clinical interface offers a complete framework for medical AI implementation. Full article

The COVID-19 pandemic highlighted the need for a scientific framework that enables quantitative assessment and control of airborne infection risks in indoor environments. This study identifies limitations in the traditional Wells–Riley model—specifically its assumptions of perfect mixing and steady-state conditions—and addresses these shortcomings by adopting the REHVA (Federation of European Heating, Ventilation and Air Conditioning Associations) infection risk assessment model. We propose a five-tier risk classification system (Monitor, Caution, Alert, High Risk, Critical) based on two key metrics: the probability of infection (Pₙ) and the event reproduction number (R_event). Unlike the classical model, our approach integrates airborne virus removal mechanisms—such as natural decay, gravitational settling, and filtration—with occupant dynamics to reflect realistic contagion scenarios. Simulations were conducted across 10 representative indoor settings—such as classrooms, hospital waiting rooms, public transit, and restaurants—considering ventilation rates and activity-specific viral emission patterns. The results quantify how environmental variables (ventilation, occupancy, time) impact each setting’s infection risk level. Our findings indicate that static mitigation measures such as mask-wearing or physical distancing are insufficient without dynamic, model-based risk evaluation. We emphasize the importance of incorporating real-time crowd density, occupancy duration, and movement trajectories into risk scoring. To support this, we propose integrating computer vision (CCTV-based crowd detection) and entry/exit counting sensors within a live airborne risk assessment framework. This integrated system would enable proactive, science-driven epidemic control strategies, supporting real-time adaptive interventions in indoor spaces. The proposed platform could serve as a practical tool for early warning and management during future airborne disease outbreaks. Full article

The introduction of Renewable Energy Sources (RESs) into the electricity grid is changing the price dynamics of the electricity market and creating room for flexibility on the consumption side. This paper investigates different aspects of the interaction between the RES share, electricity spot prices, and electric vehicle (EV) charging strategies. Based on empirical data from Germany, France, and the Czech Republic for the period 2015–2025, four research hypotheses are tested using correlation and regression analysis, cost simulations, and classification algorithms. The results confirm a negative correlation between the RES share and electricity prices, as well as the effectiveness of smart charging in reducing costs. At the same time, it is shown that the occurrence of negative prices is significantly affected by a high RES share. The correlation analysis further suggests that higher production from RESs increases the potential for price optimisation through smart charging. The findings have implications for policymaking aimed at flexible consumption and efficient RES integration. Full article

This review examines the research progress on non-noble-metal-based catalysts for formaldehyde (HCHO) oxidation at room temperature. It begins with an introduction to the hazards of HCHO as an indoor pollutant and the urgency of its removal, comparing several HCHO removal technologies and highlighting the advantages of room-temperature catalytic oxidation. It delves into the classification, preparation methods, and regulation strategies for non-precious metal catalysts, with a focus on manganese-based, cobalt-based, and other transition metal-based catalysts. The effects of catalyst preparation methods, morphological structure, and specific surface area on catalytic performance are discussed, and the catalytic oxidation mechanisms of HCHO, including the Eley–Rideal, Langmuir–Hinshelwood, and Mars–van Krevelen mechanisms, are analyzed. Finally, the challenges faced by non-precious metal catalysts are summarized, such as issues related to the powder form of catalysts in practical applications, lower catalytic activity at room temperature, and insufficient research in the presence of multiple VOC molecules. Suggestions for future research directions are also provided. Full article

Time-series classification remains a critical task across various domains, demanding models that effectively capture both local recurrence structures and global temporal dependencies. We introduce a novel framework that transforms time series into image representations by fusing recurrence plots (RPs) with both Gramian Angular Summation Fields (GASFs) and Gramian Angular Difference Fields (GADFs). This fusion enriches the structural encoding of temporal dynamics. To ensure optimal performance, Bayesian Optimization is employed to automatically select the ideal image resolution, eliminating the need for manual tuning. Unlike prior methods that rely on individual transformations, our approach concatenates RP, GASF, and GADF into a unified representation and generalizes to multivariate data by stacking transformation channels across sensor dimensions. Experiments on seven univariate datasets show that our method significantly outperforms traditional classifiers such as one-nearest neighbor with Dynamic Time Warping, Shapelet Transform, and RP-based convolutional neural networks. For multivariate tasks, the proposed fusion model achieves macro F1 scores of 91.55% on the UCI Human Activity Recognition dataset and 98.95% on the UCI Room Occupancy Estimation dataset, outperforming standard deep learning baselines. These results demonstrate the robustness and generalizability of our framework, establishing a new benchmark for image-based time-series classification through principled fusion and adaptive optimization. Full article

Pneumonia is a respiratory condition caused by various microorganisms, including bacteria, viruses, fungi, and parasites. It manifests with symptoms such as coughing, chest pain, fever, breathing difficulties, and fatigue. Early and accurate detection is crucial for effective treatment, yet traditional diagnostic methods often fall short in reliability and speed. Chest X-rays have become widely used for detecting pneumonia; however, current approaches still struggle with achieving high accuracy and interpretability, leaving room for improvement. PneumoNet, an artificial intelligence assistant for X-ray pneumonia detection, is proposed in this work. The framework comprises (a) a new deep learning-based classification model for the detection of pneumonia, which expands on the AlexNet backbone for feature extraction in X-ray images and a new head in its final layers that is tailored for (X-ray) pneumonia classification. (b) GPT-Neo, a large language model, which is used to integrate the results and produce medical reports. The classification model is trained and evaluated on three publicly available datasets to ensure robustness and generalisability. Using multiple datasets mitigates biases from single-source data, addresses variations in patient demographics, and allows for meaningful performance comparisons with prior research. PneumoNet classifier achieves accuracy rates between 96.70% and 98.70% in those datasets. Full article

In practical applications, the utilization of multi-robot systems (MRS) is extensive and spans various domains such as search and rescue operations, mining operations, agricultural tasks, and warehouse management. The surge in demand for MRS has prompted extensive exploration of Multi-Robot Task Allocation (MRTA). Researchers have devised a range of methodologies to tackle MRTA problems, aiming to achieve optimal solutions, yet there remains room for further enhancements in this field. Among the complex challenges in MRTA, the identification of an optimal coalition formation (CF) solution stands out as one of the (Nondeterministic Polynomial) NP-hard problems. CF pertains to the effective coordination and grouping of agents or robots for efficient task execution, achieved through optimal task allocation. In this context, this paper delivers a succinct overview of dynamic task allocation and CF strategies. It conducts a comprehensive examination of diverse strategies employed for MRTA. The analysis encompasses the advantages, disadvantages, and comparative assessments of these strategies with a focus on CF. Furthermore, this study introduces a novel classification system for prominent task allocation methods and compares these methods with simulation analysis. The fidelity and effectiveness of the proposed CF approach are substantiated through comparative assessments and simulation studies. Full article

Molecular electronics studies have advanced from early, simple single-molecule experiments at cryogenic temperatures to complex and multifunctional molecules under ambient conditions. However, room-temperature environments increase the risk of contamination, making it essential to identify and quantify clean and contaminated rupture traces (i.e., conductance versus relative electrode displacement) within large datasets. Given the high throughput of measurements, manual analysis becomes unfeasible. Clustering algorithms offer an effective solution by enabling the automatic classification and quantification of contamination levels. Despite the rapid development of machine learning, its application in molecular electronics remains limited. In this work, we present a methodology based on the DBSCAN (Density-Based Spatial Clustering of Applications with Noise) algorithm to extract representative traces from both clean and contaminated regimes, providing a scalable and objective tool to evaluate environmental contamination in molecular junction experiments. Full article

Earthquakes are sudden-onset disasters requiring rapid, accurate information for effective crisis response. Social media (SM) platforms provide abundant geospatial data but are often unstructured and produced by diverse users, posing challenges in filtering relevant content. Traditional content filtering methods rely on natural language processing (NLP), which underperforms with mixed-language posts or less widely spoken languages. Moreover, these approaches often neglect the spatial proximity of users to the event, a crucial factor in determining relevance during disasters. This study proposes an NLP-free model that assesses the spatial credibility of SM content by analysing users’ spatial trajectories. Using earthquake-related tweets, we developed a machine learning-based classification model that categorises posts as directly relevant, indirectly relevant, or irrelevant. The Random Forest model achieved the highest overall classification accuracy of 89%, while the k-NN model performed best for detecting directly relevant content, with an accuracy of 63%. Although promising overall, the classification accuracy for the directly relevant category indicates room for improvement. Our findings highlight the value of spatial analysis in enhancing the reliability of SM data (SMD) during crisis events. By bypassing textual analysis, this framework supports relevance classification based solely on geospatial behaviour, offering a novel method for evaluating content trustworthiness. This spatial approach can complement existing crisis informatics tools and be extended to other disaster types and event-based applications. Full article

Powdery mildew is one of the most common diseases affecting strawberry yield and quality. Accurate and timely detection is essential to reduce pesticide usage and labor costs. However, recognizing strawberry powdery mildew in complex field environments remains a significant challenge. In this study, an HSV-based image segmentation method was employed to enhance the extraction of disease regions from complex backgrounds. A total of 14 widely used deep learning models—including SqueezeNet, GoogLeNet, ResNet-50, AlexNet, and others—were systematically evaluated for their classification performance. To address sample imbalance, data augmentation was applied to 2372 healthy and 553 diseased leaf images, resulting in 11,860 training samples. Experimental results showed that InceptionV4, DenseNet-121, and ResNet-50 achieved superior performance across metrics such as accuracy, F1-score, recall, and loss. Models such as MobileNetV2, AlexNet, VGG-16, and InceptionV3 demonstrated certain strengths, and models like SqueezeNet, VGG-19, EfficientNet, and even ResNet-50 showed room for further improvement in performance. These findings demonstrate that CNN models originally developed for other crop diseases can be effectively adapted to detect strawberry powdery mildew under complex conditions. Future work will focus on enhancing model robustness and deploying the system for real-time field monitoring. Full article