視認する単純な画像の形と色を反映する脳波信号特徴量とその判別の研究

抄録

In this study, as a basic investigation for EEG-based visual image reconstruction, we investigated whether EEG signal features reflect shapes and colors of simple visual images which subjects viewed and whether the features can be discriminated. First, we investigated how the shapes and the colors are reflected in event-related potentials (ERP), the event-related spectrum perturbations (ERSP), and the inter-trial phase synchronization (ITC). The results showed statistically significant differences in ERP among the colors and ERP, ERSP and ITC among the shapes depending on time periods, frequency bands and electrodes. Second, based on the results, we explored learnable input data sets. Then, learnability for discriminating the shapes were shown in EEG waveforms on 100ms time periods in single trials at all channels and phase of time frequency analysis on the limited time-frequency domain and electrodes. Finally, we investigated whether two discriminators using LSTM and CNN discriminate the shapes from the learnable data for each subject. Then, it was found that accuracies of discrimination of the shapes were over a chance level with all the learnable data sets, subjects, and discriminators. We concluded that the distinct shapes can be discriminated from EEG signals by exploring appropriate features of input signals for discriminators.