Search for: All records

Due to the industry’s high-risk nature, construction workers often encounter hazardous conditions. Past studies have shown that recognizing near-miss incidents is crucial for minimizing injuries, yet predicting workers’ near-miss recognition performance remains a research gap. Therefore, this study aims to develop models using psychological factors (Big 5 personality traits), physiological measures (heart rate and electrodermal activity), and eye-tracking metrics (time to first fixation and fixation duration) to predict near-miss recognition. A total of 35 participants with eye-tracking glasses, a heart rate sensor, and an E4 wristband underwent an experiment to identify near-miss incidents from stimulus images. Some statistical models were trained on their recognition performance. The results show that random forest (70%), KNN (69%), and decision tree (65%) showcased high test accuracy, while logistic regression (59%) had the lowest performance. These findings inform the development of pre-employment safety assessments and guide workforce management in effectively distributing individuals with efficient near-miss recognition attributes. 

The physical workload evaluation of construction activities will help to prevent excess physical fatigue or overexertion. The workload determination involves measuring physiological responses such as oxygen uptake (VO2) while performing the work. The objective of this study is to develop a procedure for automatic oxygen uptake prediction using the worker’s forearm muscle activity and motion data. The fused IMU and EMG data were analyzed to build a bidirectional long-short-term memory (BiLSTM) model to predict VO2. The results show a strong correlation between the IMU and EMG features and oxygen uptake (R = 0.90, RMSE = 1.257 mL/kg/min). Moreover, measured (9.18 ± 1.97 mL/kg/min) and predicted (9.22 ± 0.09 mL/kg/min) average oxygen consumption to build one scaffold unit are significantly the same. This study concludes that the fusion of IMU and EMG features resulted in high model performance compared to IMU and EMG alone. The results can facilitate the continuous monitoring of the physiological status of construction workers and early detection of any potential occupational risks. 

Despite the introduction of preventive safety measures, such as near-miss reporting, to mitigate accidents and minimize fatalities, construction workers are constantly exposed to stressful situations that negatively affect their safety behavior and reporting efficiency. Occupational stress is induced by various factors, with mental stress and auditory stress being common workplace stressors that impact workers on the job site. While previous studies have demonstrated the effect of stressor conditions on workers’ hazard recognition and safety performance, research gaps persist regarding the direct impact of workplace stressors on workers’ stress levels and near-miss recognition performance. This study investigates workers’ near-miss recognition ability through an eye-tracking experiment conducted in a controlled environment under mental and auditory stress conditions. The findings from this study reveal that workplace stressors triggered by mental and auditory stress can adversely affect worker stress levels, safety behavior, and cognitive processing toward near-miss recognition. Visual attention towards near-miss scenarios was reduced by 26% for mental stress conditions and by 46% for auditory stress conditions compared to baseline. The results may potentially open avenues for developing wearable stress prediction and safety intervention models using bio-sensing technology and personalized safety training programs tailored to individuals with low identification abilities.