Detection of alertness-related EEG signals based on decision fused BP neural network

Alertness detection has been used to monitor operators in key positions to avoid accidents. The widely used methods (such as machine vision) are susceptible to external factors and cannot quantify alertness. In contrast, EEG has the advantages of intuitively reflecting brain activities and not being easily affected. Based on EEG signals, an alertness detection method using decision fused BP (back propagation, BP) neural network was presented. In this paper, we analyzed the EEG changes of 20 participants while performing tasks. During PVT (Psychomotor Vigilance Task, PVT), EEG signals were collected through the acquisition platform we designed, and KSS (Karolinska Sleepiness Scale, KSS) was completed. AR (autoregressive model, AR) and PSD (power spectral density, PSD) were applied to extract frequency domain features of EEG signals. The extracted features were then input into BP neural network separately. Afterwards, we used DS (Dempster-Shafer, DS) method to fuse output results of BP neural network. When comparing results of the proposed classification methods, we concluded that BP-DS method had the finest classification results (including AUC-ROC curve, accuracy, precision, and recall rate) with the accuracy increasing considerably from 0.661 to 0.911. In addition, among six EEG indices, R beta, (alpha + theta)/beta, alpha/beta presented prominent changes during alertness variation. The proposed alertness classification algorithm monitors alertness continuously and avoids potential catastrophes caused by decreased alertness. It can be applied in monitoring systems to prevent mental fatigue and declined work efficiency of air traffic controllers, medical staff and other fields.