基于CNN+LSTM和脑电信号的疼痛分类的研究

Research on Pain Classification Based on CNN+LSTM and EEG Signal

脑电图是脑神经细胞的电生理活动在大脑皮层或头皮表面的总体反映,包含大量的生理和病理信息。近年来,与疼痛相关脑电信号的研究是当前脑认知和临床治疗领域的研究热点和难点问题之一。使用卷积神经网络(CNN)和循环神经网络(RNN)结合的CNN+LSTM网络算法对疼痛和不痛的脑电信号进行二分类,准确率达到96%,与此同时Precision、Recall、F1-score分别达到96%、96%、96%,证明两种网络结合对研究疼痛的脑电信号是可行的。

Electroencephalogram(EEG)is the overall reflection of the electrophysiological activity of brain nerve cells on the cerebral cortex or scalp surface,and contains a lot of physiological and pathological information.In recent years,the research of pain-related EEG signals is one of the current hotspots and difficult problems in the field of brain cognition and clinical treatment.In this paper,the CNN+LSTM network com⁃bined with Convolutional Neural Network(CNN)and Recurrent Neural Network(RNN)is used to classify painful and non-painful EEG signals with an accuracy of 96%.At the same time Precision,Recall,and F1-score reached 96%,96%,and 96%respectively.