Hybrid Kinematic EEG Signal for Workload Monitoring and Evaluation in the Construction Material Mobilization

The construction industry is a typical labor-intensive sector with a high incidence of production accidents and safety risks. Many studies have found that consistently intense workloads could cause workers to lose sufficient vigilance and attention, reduce their risk detection and perception, and lead to the wrong estimation of potential risks and unsafe behaviors. Therefore, monitoring and evaluating the workload of construction personnel will be conducive to assigning, adjusting and controlling the construction process more effectively and safely. Recently, research in many fields has proposed that the EEG signal of employees at work can be obtained through wearable devices in real-time, enabling the quantitative measurement of their workload level. However, the effectiveness of this signal processing framework is often severely affected by EEG “artifacts”. Moreover, the complex construction tasks pose various requirements on the postures and movements of construction workers, making the traditional workload detection method based on static deployment EEG schemes impossible to implement in construction. To address this challenge, this study proposes a new type of hybrid kinematic-EEG signal and corresponding workload indices. This signal preserves the “artifact” triggered by muscle movement in the original signal as a new data feature, creating a more feasible workload monitoring and evaluation scheme for the construction industry. Previous research on occupational accidents in construction has revealed that a significant number of fatalities and injuries are caused by slips, trips, and falls during the mobilization of materials. Therefore, the validation experiments focus on a specific process of material mobilization in construction, aiming to demonstrate the reliability and effectiveness of this approach, which enables a significant advancement in understanding the workload of the construction workers and could have implications for improving overall safety and productivity in the field.