基于LSTM-Attention的P300事件相关电位识别分类研究

doi:10.16180/j.cnki.issn1007-7820.2022.12.002

摘要/Abstract

摘要：

针对脑电信号中P300事件相关电位识别分类准确率较低的问题,文中提出了一种基于LSTM-Attention网络的P300事件相关电位的识别分类方法。在数据处理阶段使用SMOTE对脑电信号中P300电位数据进行数据增广,并基于DBSCAN聚类算法剔除合成数据中的无关噪声。在识别分类阶段,通过在LSTM网络后加入注意力机制和Dropout层搭建LSTM-Attention分类识别网络,并使用Sigmoid函数输出P300事件相关电位的识别分类结果。实验结果表明,文中方法能够有效对脑电信号中的P300事件相关电位进行识别分类,准确率和Dice系数均值分别达到了91.9%和91.7%,与传统方法相比准确性更高、泛化性能更强。

Abstract:

In view of the problem of low recognition and classification accuracy of P300 event-related potentials in EEG signals, a recognition and classification method of P300 event-related potentials based on LSTM-Attention network is proposed in this study. In the data processing stage, SMOTE is utilized to augment P300 potential data in EEG signals, and irrelevant noise in synthetic data is eliminated based on DBSCAN clustering algorithm. In the identification and classification stage, an LSTM-Attention classification and identification network is built by adding an attention mechanism and a Dropout layer after the LSTM network, and the Sigmoid function is used to output the identification and classification results of the P300 event-related potential. The experimental results show that the proposed method can effectively recognize and classify P300 event-related potentials in EEG signals, and the average accuracy and Dice coefficient are up to 91.9% and 91.7%, respectively. Compared with traditional methods, the accuracy is higher and the generalization performance is stronger.

Key words: P300 event-related potential, EEG, LSTM, attention mechanism, data processing, SMOTE, DBSCAN, recognition and classification

中图分类号:

TP391

王夏霖,阚秀,范艺璇. 基于LSTM-Attention的P300事件相关电位识别分类研究[J]. 电子科技, 2022, 35(12): 10-16.

WANG Xialin,KAN Xiu,FAN Yixuan. Classification and Recognition of P300 Event-Related Potential Based on LSTM-Attention Network[J]. Electronic Science and Technology, 2022, 35(12): 10-16.

图/表 11

图1

图2

图3

图4

图5

图6

图7

表1

表2

表3

图8

参考文献 18

[1]	孟小飞. P300脑电信号的特征提取与分类研究[D]. 杭州: 杭州电子科技大学, 2020.
	Meng Xiaofei. Feature extraction and classification of P300 signal[D]. Hangzhou: Hangzhou Dianzi University, 2020.
	孔丽文, 薛召军, 陈龙, 等. 基于虚拟现实环境的脑机接口技术研究进展[J]. 电子测量与仪器学报, 2015, 29(3):317-327.
	Kong Liwen, Xue Zhaojun, Chen Long, et al. Review of brain-computer interface technology based on virtual reality environment[J]. Journal of Electronic Measurement and Instrumentation, 2015, 29(3):317-327.
[2]	王根, 方慧娟, 罗登. 基于事件相关电位的BCI新型输入系统研究[J]. 信息技术与网络安全, 2013, 32(7):66-68.
	Wang Gen, Fang Huijuan, Luo Deng. Study on the new input of BCI system based on ERP[J]. Information Technology and Network Security, 2013, 32(7):66-68.
[3]	闫秘. 基于P300-EEG分类的多域融合技术研究[D]. 长春: 长春理工大学, 2020.
	Yan Mi. Research on multi-domain fusion technology based on P300 EEG classification[D]. Changchun: Changchun University of Science and Technology, 2020.
[4]	马征, 邱天爽. 视觉ERP脑机接口中实验范式的研究进展[J]. 中国生物医学工程学报, 2016, 35(1):96-104.
	Ma Zheng, Qiu Tianshuang. A review of experimental paradigms in visual event-related potential-based brain computer interfaces[J]. Chinese Journal of Biomedical Engineering, 2016, 35(1):96-104.
[5]	Bostanov V. BCI competition 2003-data sets Ib and IIb:Feature extraction from event-related brain potentials with the continuous wavelet transform and the t-value scalogram[J]. IEEE Transactions on Biomedical Engineering, 2004, 51(6):1057-1061. doi: 10.1109/TBME.2004.826702
[6]	Xu N, Gao X R, Hong B, et al. BCI Competition 2003-data set IIb: Enhancing P300 wave detection using ICA-based subspace projections for BCI applications[J]. IEEE Transactions on Biomedical Engineering, 2004, 51(6):1067-1072. doi: 10.1109/TBME.2004.826699
[7]	潘家辉, 冯宝. 脑机接口中脑电信号的特征提取和模式分类[J]. 计算机系统应用, 2015, 24(8):268-272.
	Pan Jiahui, Feng Bao. Feature extraction and pattern classification for EEG in brain-computer interface[J]. Computer Systems and Applications, 2015, 24(8):268-272.
[8]	Chawla N V, Bowyer K W, Hall L O, et al. SMOTE: Synthetic minority over-sampling technique[J]. Journal of Artificial Intelligence Research, 2002(16):321-357.
[10]	Farwell L A, Donchin E. Talking off the top of your head: Toward a mental prosthesis utilizing event-related brain potentials[J]. Electroencephalography & Clinical Neurophysiology, 1988, 70(6):510-523.
[11]	Blankertz B, Müller K R, Krusienski D J, et al. The BCI competition III: Validating alternative approaches to actual BCI problems[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2006, 14(2):153-159. pmid: 16792282
[12]	贺玲, 吴玲达, 蔡益朝. 数据挖掘中的聚类算法综述[J]. 计算机应用研究, 2007(1):10-13.
	He Ling, Wu Lingda, Cai Yichao. Survey of clustering algorithms in data mining[J]. Application Research of Computers, 2007(1):10-13.
[13]	祁鑫, 王福忠, 张丽, 等. 基于SVD-LSTM的高校学生宿舍空调负荷预测[J]. 电子科技, 2020, 33(11):59-66.
	Qi Xin, Wang Fuzhong, Zhang Li, et al. Air conditioning load forecast of university students' dormitory based on SVD-LSTM[J]. Electronic Science and Technology, 2020, 33(11):59-66.
[14]	刘嘉琛, 秦小麟, 朱润泽. 基于LSTM-Attention的RFID移动对象位置预测[J]. 计算机科学, 2021, 48(3):188-195. doi: 10.11896/jsjkx.200600134
	Liu Jiachen, Qin Xiaolin, Zhu Runze. Prediction of RFID mobile object location based on LSTM-Attention[J]. Computer Science, 2021, 48(3):188- 195. doi: 10.11896/jsjkx.200600134
[15]	葛靖, 刘子龙. 基于CNN和LSTM的睡眠呼吸暂停检测算法[J]. 电子科技, 2021, 34(2):21-26.
	Ge Jing, Liu Zilong. The algorithm based on CNN and LSTM for sleep apnea syndrome detection[J]. Electronic Science and Technology, 2021, 34(2):21-26.
[16]	Srivastava N, Hinton G, Krizhevsky A, et al. Dropout: A simple way to prevent neural networks from overfitting[J]. Journal of Machine Learning Research, 2014, 15(1):1929-1958.
[17]	魏华栋, 陶媛, 蔡昌春, 等. 基于改进长短期记忆神经网络的短期负荷预测[J]. 电测与仪表, 2020, 57(19):93-98.
	Wei Huadong, Tao Yuan, Cai Changchun, et al. Short-term load forecasting based on improved long short-term memory neural network[J]. Electrical Measurement & Instrumentation, 2020, 57(19):93-98.
[18]	赵兵, 王增平, 纪维佳, 等. 基于注意力机制的CNN-GRU短期电力负荷预测方法[J]. 电网技术, 2019, 43(12):4370-4376.
	Zhao Bing, Wang Zengping, Ji Weijia, et al. A short-term power load forecasting method based on attention mechanism of CNN-GRU[J]. Power System Technology, 2019, 43(12): 4370-4376.

网络	Dice系数/%	准确率/%
SVM	75.4	76.8
RNN	82.1	82.4
LSTM-Attention	91.7	91.9

网络	数据增强	Dice系数/%	准确率/%
LSTM		86.3	87.2
LSTM	?	89.1	90.1
LSTM-Attention		90.5	90.9
LSTM-Attention	?	91.7	91.9

[1]	陈劲宏,陈玮,尹钟. 基于改进ExfuseNet模型的街景语义分割[J]. 电子科技, 2022, 35(6): 28-34.
[2]	林潮威,李菲菲,陈虬. 基于深度卷积特征的场景全局与局部表示方法[J]. 电子科技, 2022, 35(4): 20-27.
[3]	纪玲玉,高永彬,赵呈陆,汤先华,徐凯成,徐嘉诚. 基于3D全卷积网络的腹部动脉CTA分割算法[J]. 电子科技, 2022, 35(3): 38-44.
[4]	李辉,王一丞. 基于CNNCIFG-Attention模型的文本情感分类[J]. 电子科技, 2022, 35(2): 46-51.
[5]	于润润,姜晓燕,朱凯赢,蒋光好. 基于上下文注意力机制的实时语义分割[J]. 电子科技, 2022, 35(12): 57-63.
[6]	邓磊,孙培洋. 基于深度学习的网络舆情监测系统研究[J]. 电子科技, 2022, 35(12): 97-102.
[7]	张伟,刘娜,江洋,李清都. 基于YOLO神经网络的垃圾检测与分类[J]. 电子科技, 2022, 35(10): 45-50.
[8]	张仕森,孙宪坤,尹玲,李世玺. 基于神经网络的文本标题生成原型系统设计[J]. 电子科技, 2021, 34(5): 35-41.
[9]	薛永杰,巨志勇. 基于改进AlexNet的鱼类识别算法[J]. 电子科技, 2021, 34(4): 12-17.
[10]	李福鹏,付东翔. 基于Transformer编码器的金融文本情感分析方法[J]. 电子科技, 2020, 33(9): 10-15.
[11]	祁鑫,王福忠,张丽,王瑞,王晓慧. 基于SVD-LSTM的高校学生宿舍空调负荷预测[J]. 电子科技, 2020, 33(11): 59-66.
[12]	郑萌. 基于改进注意力机制模型的智能英语翻译方法研究[J]. 电子科技, 2020, 33(11): 84-87.
[13]	张悦,胡春燕. 基于有记忆递归神经网络的脑电特征情感识别研究[J]. 电子科技, 2020, 33(11): 67-72.
[14]	和文杰,刘敬彪,潘勉,吕帅帅. 基于Attention-CTC的自然场景文本识别算法[J]. 电子科技, 2019, 32(12): 32-36.
[15]	王纪伟. 基于单片机控制的高速数据采集与处理系统研究[J]. 电子科技, 2019, 32(11): 74-77.