Search Results (136)

The study investigates repetitive and time-consuming professional activities performed by occupational health and safety (OHS) specialists in the construction sector in Poland and their attitudes toward the use of modern digital tools, including solutions based on artificial intelligence (AI). The research was conducted using a questionnaire survey, with a purposive sample and a snowball method. A total of 102 individuals participated in the study, of whom 94 valid responses were included in the analysis. The data were examined using descriptive statistics and chi-square tests. The results showed that the most repetitive and time-consuming activities include documentation analysis, report preparation, inspections, and communication. Nearly 46% of respondents indicated that selected elements of their work could be automated or supported by digital tools, while 33% reported using AI-based solutions in everyday practice. Statistically significant relationships were identified between respondents’ age and both their level of concern about new technologies and their perception of technological support potential. No significant relationships were found for enterprise ownership or size. The findings indicate substantial potential for the implementation of digital and AI-supported tools in routine OHS activities. Future research should involve larger and more homogeneous samples, incorporate probabilistic sampling, and explore organisational and competence-related factors influencing technology adoption. Full article

To ensure the safety of vehicles and occupants under failures or functional limitations of ego vehicles, a minimum risk maneuver (MRM) has been proposed as a key automated driving system (ADS) function. However, executing an MRM may pose certain potential risks when sensor failures occur. This study proposed an MRM strategy designed to enhance highway-driving safety during MRM execution under multiple sensor-failure conditions. A hazard and operability study analysis, based on an ADS behavior model, is conducted to systematically identify hazards, determine potential hazardous events, and categorize the associated safety risks arising from sensor failures. Within the proposed strategy, virtual objects are generated to account for potential hazards and support risk assessments. Adaptive MRM behavior is determined in real time by analyzing surrounding objects and evaluating time-to-collision and time headway. The strategy is verified by using a MATLAB–CARLA co-simulation environment across three representative highway scenarios with combined sensor failures. The result demonstrates that the proposed MRM strategy can mitigate collision risk in hazardous scenarios while effectively leveraging the remaining functional sensors to guide the ego vehicle toward an appropriate minimum risk condition during MRM execution. Full article

Currently, in influenza vaccine production via the chicken embryo splitting method, embryo viability detection is a pivotal quality control step—non-viable embryos are prone to microbial contamination, directly endangering the vaccine batch quality. However, the predominant manual candling method suffers from unstable accuracy and occupational visual health risks. To address this challenge, we developed a novel real-time embryo viability detection system based on photoplethysmography (PPG) technology, comprising a hardware circuit for chicken embryo PPG signal collection and customized software for real-time signal filtering and time–frequency-domain analysis. Based on this system, we conducted three pivotal experiments: (1) impact of the source–detector spatial arrangement on PPG signal acquisition, (2) viable/non-viable embryo discrimination, and (3) embryo PPG signal detection performance for days 10–14. The experimental results show that within the sample size (15 viable, 5 non-viable embryos), the system achieved a 100% discrimination accuracy; meanwhile, it realized 100% successful multi-day (days 10–14) PPG signal capture for the 15 viable embryos, with consistent performance across the developmental stages. This PPG-based system overcomes limitations of traditional and existing automated methods, provides a non-invasive alternative for embryo viability detection, and presents significant implications for standardizing vaccine production quality control and advancing optical biosensing for biological viability detection. Full article

In an increasingly technologized and automated world, workplace safety and health remain a major global challenge. After decades of regulatory frameworks and substantial technical and organizational advances, the expanding interaction between humans and machines and the growing complexity of work systems are gaining importance. In parallel, the digitalization of Industry 4.0/5.0 is generating unprecedented volumes of safety-relevant data and new opportunities to move from reactive analysis to proactive, data-driven prevention. This review maps how artificial intelligence (AI), with a specific focus on natural language processing (NLP) and large language models (LLMs), is being applied to occupational risk prevention across sectors. A structured search of the Web of Science Core Collection (2013–October 2025), combined OSH-related terms with AI, NLP and LLM terms. After screening and full-text assessment, 123 studies were discussed. Early work relied on text mining and traditional machine learning to classify accident types and causes, extract risk factors and support incident analysis from free-text narratives. More recent contributions use deep learning to predict injury severity, potential serious injuries and fatalities (PSIF) and field risk control program (FRCP) levels and to fuse textual data with process, environmental and sensor information in multi-source risk models. The latest wave of studies deploys LLMs, retrieval-augmented generation and vision–language architectures to generate task-specific safety guidance, support accident investigation, map occupations and job tasks and monitor personal protective equipment (PPE) compliance. Together, these developments show that AI-, NLP- and LLM-based systems can exploit unstructured OSH information to provide more granular, timely and predictive safety insights. However, the field is still constrained by data quality and bias, limited external validation, opacity, hallucinations and emerging regulatory and ethical requirements. In conclusion, this review positions AI and LLMs as tools to support human decision-making in OSH and outlines a research agenda centered on high-quality datasets and rigorous evaluation of fairness, robustness, explainability and governance. Full article

To address the high incidence of work-related musculoskeletal disorders (WMSDs) at manual edge-banding workstations in furniture factories, and in an effort to tackle the existing research challenges of poor cumulative risk quantification and inconsistent evaluations, this paper proposes a three-stage system for continuous, automated, non-invasive WMSD risk monitoring. First, MediaPipe 0.10.11 is used to extract 33 key joint coordinates, compute seven types of joint angles, and resolve missing joint data, ensuring biomechanical data integrity for subsequent analysis. Second, joint angles are converted into graded parameters via RULA, REBA, and OWAS criteria, enabling automatic calculation of posture risk scores and grades. Third, an Adaptive Pooling Convolutional Neural Network (CNN) and Long Short-Term Memory Network (LSTM) dual-branch hybrid model based on the Efficient Channel Attention (ECA) mechanism is built, which takes nine-dimensional features as the input to predict expert-rated fatigue states. For validation, 32 experienced female workers performed manual edge-banding tasks, with smartphones capturing videos of the eight work steps to ensure authentic and representative data. The results show the following findings: (1) system ratings strongly correlate with expert evaluations, verifying its validity for posture risk assessment; (2) the hybrid model successfully captures the complex mapping of expert-derived fatigue patterns, outperforming standalone CNN and LSTM models in fatigue prediction—by integrating CNN-based spatial feature extraction and LSTM-based temporal analysis—and accurately maps fatigue indexes while generating intervention recommendations. This study addresses the limitations of traditional manual evaluations (e.g., subjectivity, poor temporal resolution, and inability to capture cumulative risk), providing an engineered solution for WMSD prevention at these workstations and serving as a technical reference for occupational health management in labor-intensive industries. Full article

Stress is a pervasive global health concern that adversely contributes to morbidity and reduced productivity, yet it often remains unquantified due to its subjective and variant presentation. Although artificial intelligence offers an encouraging path toward automated monitoring of mental states, current state-of-the-art approaches are challenged by the reliance on single-source data, sparsity of labeled samples, and significant class imbalance. This paper proposes NeuroStrainSense, a novel deep multimodal stress detection model that integrates three complementary datasets—WESAD, SWELL-KW, and TILES—through a Transformer-based feature fusion architecture combined with a Variational Autoencoder for generative data augmentation. The Transformer architecture employs four encoder layers with eight multi-head attention heads and a hidden dimension of 512 to capture complex inter-modal dependencies across physiological, audio, and behavioral modalities. Our experiments demonstrate that NeuroStrainSense achieves a state-of-the-art performance with accuracies of 87.1%, 88.5%, and 89.8% on the respective datasets, with F1-scores exceeding 0.85 and AUCs greater than 0.89, representing improvements of 2.6–6.6 percentage points over existing baselines. We propose a robust evaluation framework that quantifies discrimination among stress types through clustering validity metrics, achieving a Silhouette Score of 0.75 and Intraclass Correlation Coefficient of 0.76. Comprehensive ablation experiments confirm the utility of each modality and the VAE augmentation module, with physiological features contributing most significantly (average performance decrease of 5.8% when removed), followed by audio (2.8%) and behavioral features (2.1%). Statistical validation confirms all findings at the p < 0.01 significance level. Beyond binary classification, the model identifies five clinically relevant stress profiles—Cognitive Overload, Burnout, Acute Stress, Psychosomatic, and Low-Grade Chronic—with an expert concordance of Cohen’s κ = 0.71 (p < 0.001), demonstrating the strong ecological validity for personalized well-being and occupational health applications. External validation on the MIT Reality Mining dataset confirms the generalizability with minimal performance degradation (accuracy: 0.785, F1-score: 0.752, AUC: 0.849). This work underlines the potential of integrated multimodal learning and demographically aware generative AI for continuous, precise, and fair stress monitoring across diverse populations and environmental contexts. Full article

We present an inverse designed metalens for long-wave infrared (LWIR) imaging tailored to consumer and Internet of Things (IoT) platforms. Conventional LWIR optics either rely on costly specialty materials or suffer from low efficiency and narrow fields of view (FoV), limiting scalability. Our approach integrates adjoint-based inverse design with fabrication-aware constraints and a cone-shaped source model that efficiently captures oblique incidence during optimization. The resulting multi-level metalens achieves a wide FoV up to 100° while maintaining robust focusing efficiency and stable angle-to-position mapping on low-power $4\times 4$ microbolometer arrays representative of edge devices. We further demonstrate application-level imaging on $4\times 4$ microbolometer arrays, showing that the proposed metalens delivers a substantially wider FoV than a commercial narrow FoV lens while meeting low-resolution, low-cost, and low-power constraints for edge LWIR modules. By eliminating bulky multi-element stacks and reducing cost and form factor, the proposed design provides a practical pathway to compact, energy-efficient LWIR modules for consumer applications such as occupancy analytics, smart-building automation, mobile sensing, and outdoor fire surveillance. Full article

The three key design criteria for nearly zero-energy buildings (nZEBs) and climate-neutral buildings are minimizing energy use, ensuring high occupant comfort, and reducing environmental impact. Thermal comfort is one of the main components of indoor environmental quality (IEQ), strongly affecting occupants’ health, well-being, and productivity. As energy-efficiency requirements become more demanding, the appropriate selection of heating systems, their automated control, and the management of solar heat gains are becoming increasingly important. This study investigates the influence of two low-temperature radiant heating systems—underfloor and wall-mounted—and the use of Venetian blinds on perceived thermal comfort in a highly glazed public nZEB building located in a densely built urban area within a temperate climate zone. The assessment was based on the PMV (Predicted Mean Vote) index, commonly used in IEQ research. The results show that both heating systems maintained indoor conditions corresponding to comfort or slight thermal stress under steady state operation. However, during periods of strong solar exposure in the room without blinds, PMV values exceeded 2.0, indicating substantial heat stress. In contrast, external Venetian blinds significantly stabilized the indoor microclimate—reducing PMV peaks by an average of 50.2% and lowering the number of discomfort hours by 94.9%—demonstrating the crucial role of solar protection in highly glazed spaces. No significant whole-body PMV differences were found between underfloor and wall heating. Overall, the findings provide practical insights into the control of thermal conditions in radiant-heated spaces and highlight the importance of solar shading in mitigating heat stress. These results may support the optimization of HVAC design, control, and operation in both residential and non-residential nZEB buildings, contributing to improved occupant comfort and enhanced energy efficiency. Full article

Indoor air quality (IAQ) in high-rise residential buildings is an increasing concern, especially in hot and humid climates where prolonged indoor exposure elevates health risks. This study evaluates the performance of Fresh Air Handling Units (FAHUs) using two complementary approaches: (1) real-time sensor data to quantify IAQ conditions and (2) occupant survey responses to capture perceived comfort and pollution indicators. The results show that floor level did not predict satisfaction, even though AQI data revealed clear differences between flats, suggesting perceptions are driven more by sensory cues than by actual pollutant levels. Longer weekday exposure emerged as a stronger predictor of dissatisfaction. These gaps between perceived and measured IAQ highlight the need for improved ventilation scheduling and greater occupant awareness. FAHUs were found to be inefficient, consuming 21–26% of total building energy while lacking pollutant-specific monitoring capabilities. To address these issues, the study recommends the integration of IoT-enabled sensors for real-time pollutant detection, enhanced facade sealing to minimize external infiltration, and the upgrade of filtration systems with HEPA filters and UV purification. Additionally, AI-driven predictive maintenance and automated ventilation optimization through Building Management Systems (BMS) are suggested. These findings offer valuable insights for improving IAQ management in high-rise buildings, with future research focusing on AI-based predictive modeling for dynamic air quality control. Full article

This study evaluates and compares the sustainability performance of selected historic, commercial, and institutional buildings in Istanbul to identify effective climate-responsive and energy-efficient design strategies. The objectives are to assess performance using LEED-based criteria, examine variations across building typologies, and outline implications for future sustainable design. Using an evaluation matrix, responses from 175 experts were analysed across key LEED categories for seven case study buildings. The comparative assessment reveals notable variations in sustainability performance across the seven evaluated buildings. ERKE Green Academy consistently achieved the highest mean scores (≈4.40–4.60), particularly in Sustainable Sites, Water Efficiency, Energy and Atmosphere, and Indoor Environmental Quality. This strong performance reflects its integration of advanced green technologies, optimised daylighting strategies, biophilic elements, and smart system controls. Modern commercial towers, such as the Allianz Tower and Sapphire Tower, recorded strong mean scores (≈4.20–4.50) across categories related to Integrative Design, Energy Efficiency, and Materials and Resources. Their performance is largely driven by intelligent façade systems, double-skin envelopes, automated shading, and high-performance mechanical systems that enhance operational efficiency. In contrast, heritage buildings including Hagia Sophia and Sultan Ahmed Mosque demonstrated moderate yet stable performance levels (≈4.00–4.40). Their strengths were most evident in Indoor Environmental Quality, where passive systems such as thermal mass, natural ventilation, and inherent spatial configurations contribute significantly to occupant comfort. Overall, the findings underscore the complementary value of combining traditional passive strategies with modern smart technologies to achieve resilient, low-energy, and user-responsive architecture. This study is novel as it uniquely demonstrates how traditional passive design strategies and modern smart technologies can be integrated to enhance climate-responsive and energy-efficient performance across diverse building typologies. The study recommends enhanced indoor air quality strategies, occupant education on system use, and stronger policy alignment with LEED standards. Full article

The continuous tightening of European regulatory requirements, particularly under the General Safety Regulation (GSR), has considerably increased the scope and cost of proving ground testing required for the validation of Advanced Driver Assistance Systems (ADASs) and Automated Driving Systems (ADSs). This study presents a methodology for constructing complex proving ground test scenarios aimed at supporting early-stage functional validation and cost-efficient preparation for type approval. The method is based on the systematic analysis of proving ground–relevant ADAS regulations and the classification of test case variations according to sensing, actuation, and execution complexity. By filtering and combining representative test cases, minimum and maximum complexity scenarios were developed and evaluated on the ZalaZONE proving ground in Hungary. The results demonstrate that the proposed approach can substantially reduce test duration, facility occupancy, and overall validation costs, while maintaining the representativeness and credibility of results. Beyond cost savings, the methodology offers a scalable and practical framework for physical validation, supporting manufacturers in achieving regulatory compliance with reduced time and expenditure. Full article

The mining industry places high priority on occupational safety, process quality and operational efficiency. Roadheaders are widely deployed in coal mines to support fully automated excavation, reducing workers’ physical strain and improving overall safety. This article examines an automatic control system for a roadheader cutting head designed to increase mining efficiency, reduce energy consumption and maintain stable performance under varying coal and rock conditions. The system integrates advanced control algorithms with geological strength index (GSI) analysis and asynchronous motor control strategies. GSI-based adaptive speed control conserves energy and increases cutting efficiency compared to manual control. By reducing dynamic load fluctuations, transitions between different cutting zones become smoother, which decreases equipment wear. The proposed control system incorporates speed feedback loops that use a proportional–integral (PI) controller with field-oriented control (FOC), as well as super-twisted sliding mode control (STSMC) with FOC. FOC with STSMC improves roadheader productivity by applying advanced control strategies, adaptive speed regulation and precise geological strength analysis. It is also better able to handle disturbances and sudden loads thanks to STSMC’s nonlinear control robustness. The result is safer, more efficient, and more cost-effective mining that can be implemented across a wide range of underground mining scenarios. Full article

Smart thermostats are a key technology for reducing residential energy consumption in smart cities, but their real-world effectiveness depends on the interaction between automation, occupant behavior, and the design of behavioral interventions. This study presents a physics-informed assessment of thermostat strategies across Luxembourg’s single-family home stock, using an aggregate thermal model calibrated to eight years of hourly national heating demand and meteorological data. We simulate five categories of behavioral scenarios: dynamic thermostat adjustments, heat-wasting window-opening behavior, flexible comfort models, occupancy-based automation, and a portfolio of four probabilistic nudges (social comparison, real-time feedback, pre-commitment, and gamification). Results show that occupancy-based automation delivers the largest energy savings at 12.9%, by aligning heating with presence. In contrast, behavioral savings are highly fragile, as a stochastic window-opening behavior significantly erodes the 9.8% savings from eco-nudges, reducing the net gain to 7.6%. Among nudges, only social comparison yields significant savings, with a mean reduction of 7.6% (90% confidence interval: 5.3% to 9.8%), by durably lowering the thermal baseline. Real-time feedback and pre-commitment fail, achieving less than 0.5% savings, because they are misaligned with high-consumption periods. Thermal comfort, the psychological state of satisfaction with the thermal environment drives a large share of residential energy use. These findings demonstrate that effective smart thermostat design must prioritize robust, presence-responsive automation and interventions that reset default comfort norms, offering scalable, policy-ready pathways for residential energy reduction in urban energy systems. Full article

Background: The increasing prevalence of dementia and mild cognitive impairment (MCI) underscores the need for reliable and scalable digital cognitive screening tools. Although several studies have validated smartphone- or tablet-based assessments in community-dwelling older adults, few have examined their reliability in clinical populations with neurological disorders. This study aimed to evaluate the intra- and inter-rater reliability and agreement between the traditional paper-based Mini-Mental State Examination-Korean version (MMSE-K) and a tablet PC-based MMSE-K kit in patients with neurologic diseases undergoing rehabilitation. Methods: A total of 32 patients with neurological conditions—including stroke-related, encephalitic, and myelopathic disorders—participated in this study. Two occupational therapists (OT-A and OT-B) independently administered both the paper- and tablet-based MMSE-K versions following standardized digital instructions and fixed response rules. The intra- and inter-rater reliabilities of the tablet version were analyzed using intraclass correlation coefficients (ICCs) with a two-week retest interval, while Bland–Altman plots were used to assess agreement between the paper and tablet scores. Results: The tablet-based MMSE-K showed strong agreement with the paper-based version (r = 0.969, 95% CI 0.936–0.985, p = 1.05 × 10⁻¹⁹). Intra- and inter-rater reliabilities were excellent, with ICCs ranging from 0.89 to 0.98 for domain scores and 0.98 for the total score, and the Bland–Altman plots showing acceptable agreement without systematic bias. Minor variability was observed in the Attention/Calculation and Comprehension/Judgment domains. Conclusions: The tablet PC-based MMSE-K kit provides a standardized, examiner-independent, and reliable alternative to the traditional paper version for assessing cognitive function in patients with neurologic diseases. These findings highlight the tool’s potential for clinical deployment in hospital and rehabilitation settings, bridging the gap between traditional paper assessments and automated digital screening. Future multicenter studies with larger, disease-diverse cohorts are warranted to establish normative data and validate its diagnostic precision for broader clinical use. Full article

The global drive toward sustainability and energy efficiency has accelerated the development of smart buildings integrating the Internet of Things (IoT) and Artificial Intelligence (AI). These technologies optimise energy use, enhance occupant comfort, and advance building management systems. This study examines the integration of IoT and AI in energy-efficient smart buildings, emphasising applications and challenges. A qualitative methodology, combining systematic literature review, case study analysis, and systems analysis, underpins the research. Findings indicate that IoT enables smart metering, real-time energy monitoring, automated lighting and HVAC, occupancy-based energy optimisation, and renewable energy integration. AI complements these functions through predictive maintenance, energy forecasting, demand-side management, intelligent climate control, indoor air quality automation, and behaviour-driven analytics. Together, they reduce carbon emissions, lower operational costs, and improve occupant well-being. However, challenges remain, including data security and privacy risks, interoperability gaps, scalability and cost constraints, and retrofitting difficulties. To address these, the paper proposes a systems thinking-enabled conceptual framework structured around three pillars: adopting IoT and AI as enabling technologies, overcoming integration barriers, and identifying application areas that advance sustainability in smart buildings. This framework supports strategic decision-making toward net-zero and resilient building design. Full article