The first author of the article is Shuaishuai Bai, title：“Research on Single Trial EEG Decoding-based Class Bootstrap Method for Lie Prediction”

Abstract ：Lie prediction techniques based on EEG rely on the effective decoding of event-related potential (ERP). At present,manual design features are mainly used for EEG analysis. In recent years, single-trial EEG classification method has made progress.End-to-End EEG classification methods can automatically extract features from EEG and classify, which has been widely studied and applied in brain-computer interface. In this study, EEG of 18 subjects were collected in the autobiographical-based face recognition task based on complex trial protocol (CTP) paradigm. The application of five ERP classification methods including traditional machine learning method and neural network method in lie prediction is studied. A class bootstrap method is proposed to solve the problem that the single trial EEG classification method cannot applied into practical directly. The class bootstrap method based on the assumption of data distribution, the probe stimulus was deduced by comparing the classification performance of classifier in the testing when each categories of stimulus images was set as probe stimuli to train the classifier. The experimental results show that the neural network-based single test EEG decoding method is superior to the traditional machine learning algorithm in lie prediction based on the self-face information CTP paradigm. The proposed class bootstrap method outperforms the traditional lie prediction method and can accurately predict lies when only a small amount of EEG data is used.