[1]樊　楷　李丛煊　刘海燕.基于CNN+Bi-LSTM和脑电信号的疼痛分类的研究[J].大众科技,2020,22(11):12-15.
　Research on Pain Classification Based on CNN+Bi-LSTM and EEG Signal[J].Popular Science & Technology,2020,22(11):12-15.
点击复制

基于CNN+Bi-LSTM和脑电信号的疼痛分类的研究()
分享到：

《大众科技》[ISSN:1008-1151/CN:45-1235/N]

卷:
22
期数:
2020年11
页码:
12-15
栏目:
信息技术与通信
出版日期:
2020-11-20

文章信息/Info

Title:
Research on Pain Classification Based on CNN+Bi-LSTM and EEG Signal
作者:
樊　楷　李丛煊　刘海燕
（北华航天工业学院，河北 廊坊 065000）
关键词:
疼痛分类; 脑电图; CNN; Bi-LSTM
Keywords:
pain classification electroencephalogram(EEG) CNN Bi-LSTM
文献标志码:
A
摘要:
脑电图（Electroencephalogram, EEG）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，包含了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。文章使用卷积神经网络（Convolutional Neural Network，CNN）和循环神经网络（Recurrent Neural Network，RNN）结合的CNN+Bi-LSTM网络算法对疼痛和不痛的脑电信号进行二分类，准确率达到了97.1%，与此同时precision、recall、f1-score分别达到了97%、97%、97%。证明了两种网络结合对研究疼痛的脑电信号是可行的。
Abstract:
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+Bi-LSTM network combined with Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) is used to classify painful and non-painful EEG signals with an accuracy of 97.1%. At the same time, Precision, recall, and f1-score reached 97%, 97%, and 97% respectively. It is proved that the combination of the two networks is feasible for studying the EEG signals of pain.

参考文献/References:

[1]　Ahmadlou M, Adeli H, Adeli A. Fractality analysis of frontal brain in major depressive disorder[J]. International Journal of Psychophysiology, 2012, 85(2): 206-211. [2]　Liu R, WangY, Newman G I, et al. EEG classification with a sequential decision-making method in motor imagery BCI[J]. International Journal of Neural Systems, 2017, 27(8): 1750046. [3]　Cogan D, Birjandtalab J, Nourani M. Multi-biosignal analysis for epileptic seizure monitoring[J]. International Journal of Neural Systems, 2017, 27(1): 1650031. [4]　Mammone N, Bonanno L, de Salvo S, et al. Permutation disalignment index as an indirect, EEG-based, measure of brain connectivity in MCI and AD patients[J]. International Journal of Neural Systems, 2017, 27(5): 1750020. [5]　Bruder J C, Dümpelmann M, Piza D L, et al. Physiological ripples associated with sleep spindles differ in waveform morphology from epileptic ripples[J]. International Journal of Neural Systems, 2017, 27(7): 1750011. [6]　Tonoyan Y, Looney D, Mandic D P, et al. Discriminating multiple emotional states from EEG using a data-adaptive, multiscale information-theoretic approach[J]. International Journal of Neural Systems, 2016, 26(2): 1650005. [7]　N.Z.N. Jenny, O. Faust, W. Yu, Automated classification of normal and premature ventricular contractions in electrocardiogram signals[J]. Journal of Medical Imaging and Health Informatics, 2014, 4(6): 886-892. [8]　李冬. 基于EEG的信号处理与疼痛识别研究[D]. 杭州:浙江大学，2019. [9]　赵颀. 基于脑电信号分析客观评估慢性腰背痛患者的研究[D]. 合肥: 安徽医科大学，2018. [10] 耿惠惠. 基于双通道时空特征深度学习的新生儿疼痛表情识别[D]. 南京: 南京邮电大学，2019. [11] 尹兵. 脑电波信号的去伪迹研究[D]. 南京: 南京邮电大学，2014. [12] 杨秋红. 运动想象脑电信号的伪迹剔除算法及在线应用研究[D]. 昆明: 昆明理工大学，2016. [13] Zhang C, Tong L, Zeng Y, et al. Automatic artifact removal from electroencephalogram data based on a priori artifact information[J]. Biomed Research International, 2015, 2015: 720450. [14] Zachariah A, Jai J, Titus G. Automatic EEG artifact removal by independent component analysis using critical EEG rhythms[C]// International Conference on Control Communication and Computing. IEEE, 2014. [15] DelormeA, Makeig S. EEGLAB: an open Source toolbox for analysis of single-trial EEG dynamics including independent dent component analysis[J]. Journal of Neuroscience Methods, 2004, 134(1): 9-21. [16] Siddique N, Adeli H. Computational intelligence-synergies of fuzzy logic, neural networks and evolutionary computing[M]. West Sussex: Wiley, ,2013. [17] Fukushima K. Neocognitron: a self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position[J]. Biological Cybernetics, 1980, 36(4): 193-202. [18] Goodfellow I, Bengio Y, Courville A. Deep Learning[M]. London: MIT Press, 2016. [19] He K, Zhang X, Ren S, et al. Delving deep into rectifiers: surpassing humanlevel performance on image net classification[C]// CVPR, 2015: 1026-1034. [20] Hochreiter S, Schmidhuber J. Long Short-Term Memory[J]. Neural Computation, 1997, 9(8): 1735-1780.

备注/Memo

备注/Memo:
【收稿日期】2020-09-05 【基金项目】国家自然科学基金联合重点项目（61401454、71532014）。 【作者简介】樊楷（1993－），男，河南安阳人，北华航天工业学院在读硕士研究生，研究方向为人工智能和大数据分析。 【通信作者】刘海燕，女，河北廊坊人，北华航天工业学院副教授，研究方向为计算机网络和安全。
更新日期/Last Update: 2020-12-16