Using EEG to recognize emergency situations for brain-controlled vehicles

This paper proposes a novel method to recognize an emergency situation by translating EEG signals of a disabled driver while he or she uses a brain-machine interface without using his or her limbs to drive a vehicle. EEG signals were first filtered by independent component analysis along with information entropy. And then the sums of powers of theta wave in the power spectrum of EEG signals from 13 channels were used as features of the classifier built by linear discriminant analysis. The pilot experimental results from two participants in a driving simulator indicated that the model recognized emergency situations (e.g., pedestrian sudden occurrence) 400 ms earlier than the response of drivers with a hit rate of 76.4%, suggesting that the proposed method is feasible. The proposed method can be used as a complementary method to the existing ones based on detecting external objects with sensors.