Search Results (3)

Smoke detection is crucial for early fire prevention and the protection of lives and property. Unlike generic object detection, smoke detection faces unique challenges due to smoke’s semitransparent, fluid nature, which often leads to false positives in complex backgrounds and missed detections—particularly around smoke edges and small targets. Moreover, high computational overhead further restricts real-world deployment. To tackle these issues, we propose RT-DETR-Smoke, a specialized real-time transformer-based smoke-detection framework. First, we designed a high-efficiency hybrid encoder that combines convolutional and Transformer features, thus reducing computational cost while preserving crucial smoke details. We then incorporated an uncertainty-minimization strategy to dynamically select the most confident detection queries, further improving detection accuracy in challenging scenarios. Next, to alleviate the common issue of blurred or incomplete smoke boundaries, we introduced a coordinate attention mechanism, which enhances spatial-feature fusion and refines smoke-edge localization. Finally, we propose the WShapeIoU loss function to accelerate model convergence and boost the precision of the bounding-box regression for multiscale smoke targets under diverse environmental conditions. As evaluated on our custom smoke dataset, RT-DETR-Smoke achieves a remarkable 87.75% mAP@0.5 and processes images at 445.50 FPS, significantly outperforming existing methods in both accuracy and speed. These results underscore the potential of RT-DETR-Smoke for practical deployment in early fire-warning and smoke-monitoring systems. Full article

The firefighting protective suits (FPSs) of firefighters at fire scenes affect their health and safety. However, the association between firefighters’ health awareness of occupational exposure risks and the FPS use, washing and management remains unclear. Therefore, this study aimed to evaluate the association between firefighters’ health awareness of occupational exposure risks and their recognition, behaviors regarding the use, washing and management of FPSs. This study design is a cross-sectional study and used a web-based survey of the Seoul Metropolitan Government’s electronic survey system. The survey was conducted on metropolitan firefighters performing shift work in charge of fire and rescue work for 21 days from 1 to 22 April 2019, with 1097 (40.3%) respondents. Characteristics of FPS use, washing and management and the association between thoughts and behaviors thereof and health awareness of occupational exposure risks were evaluated. Data of 1097 firefighters were analyzed using the SAS 9.4 statistical package, chi-square test and logistic regression analysis. Firefighters’ fire scene awareness rate of possible carcinogens was 94.4%. There was an association between public health thinking of occupational exposure risks and the correct use of an FPS for one’s own safety (AOR 1.97. 95% CI 1.02–3.80). However, no association was shown between correct FPS use (AOR 1.49, 95% CI 0.48–4.59), washing (AOR 2.50, 95% CI 0.93–6.68) and management (AOR 1.38, 95% CI 0.75–2.50) behaviors. This study analyzed the relationship between the use, washing and management of personal protective equipment called firefighting clothing and firefighters perceived occupational exposure risks. This study found an association between the health awareness of occupational exposure risks and recognition of the correct use of FPSs at fire scenes but not between using, washing and managing behaviors of FPSs. This study is the first to analyze the relationship between firefighting clothing and occupational health awareness level. The results confirm that future interventions are required to help firefighters practice desirable behaviors toward FPSs and provided evidenced data for preventing occupational diseases among firefighters. Therefore, this study can be used to develop a firefighter occupational health curriculum and establish health and safety plans from mid- to long-term perspectives for firefighters’ safety against occupational exposure risks. Full article

The article presents the results of an investigation of water composition and quality in sprinkler installations, as well as the influence of temperature changes on the corrosion process. The physical and chemical components of the water were measured to ascertain the influence of its properties on the corrosion process in a wet pipe sprinkler system operating in significantly changing ambient temperature conditions. The article presents the results of measurements of the wall thickness of galvanized pipes and changes in the chemical composition of water occurring under the influence of variable ambient temperature. The range and variability of temperatures corresponded to the seasons of the year: spring and summer in a temperate climate. Changes in the corrosive aggressiveness of water were assessed using the Langelier saturation index (LSI), the Ryznar stability index (RSI), and the general acidity intensity index (I). The tests revealed that the tap water used demonstrated strong corrosive properties for galvanized pipes. The calculated indices showed the tendency of water to cause corrosion (−1.1 > LSI < 1.0; RSI = 7.1–12.8). The chemical parameters that significantly influenced the corrosion of galvanized pipes are chloride (Cl⁻), sulphate (SO₄²⁻), and bicarbonate (HCO³⁻) ions. An important factor contributing to the intensification of corrosion is the roughness and heterogeneity of the pipe surface. Full article