基于纹理特征的脑电信号识别研究

s a physiological signal closely related to brain activity, EEG can respond to some physiological activities of people, and is often used in brain-computer interface research, human emotion recognition, fatigue driving, epilepsy, sleep quality monitoring, etc. to solve these problems. The key is how to improve the recognition accuracy of EEG signals. Inspired by image texture features, the histogram-based EEG texture features and EEG signal texture features based on amplitude co-occurrence matrix are used to improve the recognition accuracy of EEG signals, and the BCI challenge is managed in Kaggle . Experiment on the data set. The experimental results show that the EEG signal texture features designed in this paper are added on the basis of the first scheme , which improves the recognition accuracy of the task from 87.56% to 89.54%. It can be obtained from the experimental results that the EEG signal texture features designed in this paper can effectively improve the recognition accuracy of EEG signals.