The purpose of this study is to investigate the feasibility of remote-Photoplethysmography (rPPG) for stress detection in construction workers. rPPG signals were collected from six participants performing arithmetic and Stroop tasks under controlled c...
The purpose of this study is to investigate the feasibility of remote-Photoplethysmography (rPPG) for stress detection in construction workers. rPPG signals were collected from six participants performing arithmetic and Stroop tasks under controlled conditions. After preprocessing and applying a sliding window, 67 time, frequency, and nonlinear features were extracted. Five machine learning classifiers were evaluated, among which Quadratic Discriminant Analysis (QDA) achieved the highest accuracy of 83%. These findings demonstrate the potential of rPPG as a contactless method for stress monitoring and its applicability to construction safety management.