A Framework for EEG-Based Ubiquitous Hazard Identification and Proactive Safety Management: Fid-Bau Portal

A Framework for EEG-Based Ubiquitous Hazard Identification and Proactive Safety Management

Jeon, JungHo / Cai, Hubo

Construction hazards and workers’ unsafe behavior are two critical factors contributing to fatalities and injuries at construction sites. Current hazard identification practice mostly relies on safety managers’ prior knowledge and experience, which leaves numerous hazards unidentifed. In addition, many workers engage in risk-taking behaviors, although they correctly recognize hazards, which can lead to severe accidents. Therefore, it is important to help workers better identify hazards and engage in safe behavior for proactive and preventive safety management. Previous studies revealed that analyzing workers’ electroencephalogram (EEG) signals provides an opportunity to identify dynamic construction hazards, and behavior intervention can modify workers’ unsafe behavior. However, it still remains unclear how the identified relationship between EEG signals and hazards can be incorporated into proactive and preventive safety management. This paper proposes an EEG-based ubiquitous hazard identification and proactive safety management framework that comprises the following three steps: (1) development of immersed EEG hazard classifier, (2) multi-sensor, real-time hazard mapping, and (3) behavior intervention. The feasibility of the proposed framework was demonstrated by focusing on the first component (immersed EEG hazard classifier) based on indoor laboratory experiments. It was found that the binary classifier classified the hazard-related EEG signals with 93.7% accuracy, and the multiclass classifier was able to classify the EEG signals into five different hazard types with 79.3% accuracy. It is expected that the use of the framework can advance the current safety management practice by providing a toolbox that can better identify construction hazards.