Recognition of Riding Feeling From EEG Based on Neural Network

In order to identify the riding feeling in an autonomous vehicle through electroencephalogram (EEG), a recognition model based on multidimensional feature extraction and recurrent neural network (RNN) is proposed. After the effective training of the dataset, the system can realize the recognition of passengers’ riding feelings through real-time acquisition of passengers’ EEG signals and sending them into this recognition model. After preprocessing the collected raw EEG signals, we conducted an in- depth study of the preprocessed EEG data and proposed an algorithm to identify riding feeling from EEG signals. In order to improve the classification ability of RNN, a feature extraction method based on time segments is designed. Applying this method, multidimensional features with spatial, temporal, and frequency-domain features are obtained. The experimental results show that this feature extraction method can effectively suppress the overfitting of the RNN and improve the recognition ability of the network. Finally, the recognition of riding feeling is recognized through the RNN. Through the verification of the a dataset for emotion analysis using EEG, physiological and video signals (DEAP) dataset and the self-built dataset, the average recognition accuracy rate of 89.22% and 94.27% was obtained, respectively, which provides a feasible solution for the recognition of riding feeling based on physiological signals such as EEG.