EEG-based work experience prediction using hazard recognition

Abstract

Extraction of individual characteristics promotes intuitive human-machine collaboration (HMC) for hazard recognition. Despite the essential role of work experience in hazard recognition, HMC techniques require ways for efficient individual characteristic identification with physiological signals. We proposed a measure that extracts implicit electroencephalography (EEG) signals to predict workers' experience as a proxy for hazard recognition ability. First, we hypothesized that work experience is potentially related to EEG signals. Second, an experiment was conducted to collect brain activity signals during hazard recognition from construction workers. Third, the brain activity signals (event-related potentials) were extracted to train a sparse regression model for experience prediction with the nested leave-one-out cross-validation approach. EEG-based prediction results were significantly correlated with years of work experience (r = 0.6455), and the model achieved good external validity and out-of-sample reliability. The proposed model could serve as a viable basis to identify individual characteristics during HMC.