多频带频域深度置信网络脑电特征识别算法

doi:10.13973/j.cnki.robot.180083

摘要
图/表
参考文献
相关文章 (4)

全文: PDF (712 KB) HTML ( ) 输出: BibTeX \| EndNote (RIS)
引用本文:
蔡军, 胡洋揆, 张毅, 尹春林. 多频带频域深度置信网络脑电特征识别算法[J]. 机器人, 2018, 40(4): 510-517.DOI: 10.13973/j.cnki.robot.180083. CAI Jun, HU Yangkui, ZHANG Yi, YIN Chunlin. Multi-band FDBN Algorithm for Extracting EEG Features. ROBOT, 2018, 40(4): 510-517. DOI: 10.13973/j.cnki.robot.180083.

摘要针对DBN（深度置信网络）脑电信号识别率不高的问题，提出了多频带频域深度置信网络（multi-band FDBN）算法进行特征提取.不同频带存在个体性差异，它们对于分类结果的贡献不完全相同，本文利用带通滤波器将原始的脑电信号分成多个频段，再采用FFT（快速傅里叶变换）将时域信号转换为频域信号并作归一化处理，最后将每个频段的频域数据输入DBN进行训练识别.线下实验证明，相比FDBN（频域深度置信网络）算法，多频带FDBN的平均准确率提高了3.25%，且标准差更小，鲁棒性更好.最后，在智能轮椅平台上，利用多频带FDBN算法基于左右手运动想象脑电信号控制轮椅完成了"8"字形路径，证明了该算法在脑电信号特征提取中的有效性.

	服务

	把本文推荐给朋友
	加入我的书架
	加入引用管理器
	E-mail Alert
	RSS
	作者相关文章
	蔡军
	胡洋揆
	张毅
	尹春林

关键词 ：脑电信号, 特征识别, 频域深度置信网络, 智能轮椅

Abstract：In order to solve the problem of low recognition rate of electroencephalogram (EEG) signal by deep belief network (DBN), multi-band frequency domain deep belief network (multi-band FDBN) algorithm is presented for feature extraction. Due to the individual differences of different bands, their contributions to the classification results aren't exactly the same. In this paper, the band-pass filter is used to divide the original EEG signal into multiple frequency bands, and then the FFT (fast Fourier transform) is used to convert the time domain signals into frequency domain signals which are normalized. Finally, the frequency domain data of each frequency band is input into DBN for training and identification. Offline experiments show that compared with frequency domain deep belief network (FDBN), the accuracy of multi-band FDBN increases by 3.25% in average, the variance is smaller, and the robustness is better. Also, the multi-band FDBN algorithm is used to control an intelligent wheelchair platform to perform "8" trajectory with motion imaginary EEG signals of the left and right hands, which proves the effectiveness of the algorithm in EEG feature extraction.

Key words： electroencephalogram (EEG) feature extraction frequency deep belief network (FDBN) intelligent wheelchair

收稿日期: 2018-01-29 录用日期: 2018-03-27

TP242.6

基金资助:国家自然科学基金（61673079）；重庆市科委重点项目（cstc2015jcyjBX0066）

通讯作者: 胡洋揆,hyk08@foxmail.com E-mail: hyk08@foxmail.com

作者简介: 蔡军(1977-),男,副教授,硕士生导师.研究领域:模式识别,机器人技术及应用.
胡洋揆(1992-),男,硕士生.研究领域:脑电信号模式识别和人机交互.
张毅(1966-),男,教授,博士生导师.研究领域:机器人及应用,信息无障碍技术.

链接本文:

https://robot.sia.cn/CN/10.13973/j.cnki.robot.180083 或 https://robot.sia.cn/CN/Y2018/V40/I4/510

[1] 王行愚,金晶,张宇,等.脑控:基于脑-机接口的人机融合控制[J].自动化学报,2013,39(3); 208-221. Wang X Y, Jin J, Zhang Y, et al. Brain control:Human-computer integration control based on brain-computer interface[J]. Acta Automatica Sinica, 2013, 39(3):208-221.
[2] Minguillon J, Angel Lopez-Gordo M, Pelayo F. Trends in EEGBCI for daily-life:Requirements for artifact removal[J]. Biomedical Signal Processing & Control, 2017, 31:407-418.
[3] Iturrate I, Antelis J M, Kübler A, et al. A noninvasive brain-actuated wheelchair based on a P300 neurophysiological protocol and automated navigation[J]. IEEE Transactions on Robotics, 2009, 25(3):614-627.
[4] Lotte F, Guan C. Regularizing common spatial patterns to improve BCI designs:Unified theory and new algorithms[J]. IEEE Transactions on Biomedical Engineering, 2011, 58(2):355-362.
[5] Zhang Y, Ji X M, Zhang Y T. Classification of EEG signals based on AR model and approximate entropy[C]//IEEE International Joint Conference on Neural Networks. Piscataway, USA:IEEE, 2015.
[6] Hsu W Y. EEG-based motor imagery classification using neurofuzzy prediction and wavelet fractal features[J]. Journal of Neuroscience Methods, 2010, 189(2):295-302.
[7] Li P, Jiang W H, Su F. Single-channel EEG-based mental fatigue detection based on deep belief network[C]//38th Annual International Conference of the IEEE-Engineering-in-Medicineand-Biology-Society. Piscataway, USA:IEEE, 2016:367-370.
[8] Chai R, Ling S H, San P P, et al. Improving EEG-based driver fatigue classification using sparse-deep belief networks[J]. Frontiers in Neuroscience, 2017, 11:No.103.
[9] Lu N, Li T F, Ren X D, et al. A deep learning scheme for motor imagery classification based on restricted Boltzmann machines[J]. IEEE Transactions on Neural Systems & Rehabilitation Engineering, 2017, 25(6):566-576.
[10] Li M A, Zhang M, Sun Y J. A novel motor imagery EEG recognition method based on deep learning[C]//International Forum on Management, Education and Information Technology Application. Paris, France:Atlantis Press, 2016:728-733.
[11] Hinton G E. A practical guide to training restricted Boltzmann machines[M]//Lecture Notes in Computer Science, Vol.7700. Berlin, Germany:Springer, 2012:599-619.
[12] 刘建伟,刘媛,罗雄麟.玻尔兹曼机研究进展[J].计算机研究与发展,2014,51(1):1-16. Liu J W, Liu Y, Luo X L. Research and development on Boltzmann machine[J]. Journal of Computer Research and Development, 2014, 51(1):1-16.
[13] Ilyas M Z, Saad P, Ahmad M I, et al. Classification of EEG signals for brain-computer interface applications:Performance comparison[C]//International Conference on Robotics, Automation and Sciences. Piscataway, USA:IEEE, 2016.
[14] Chamanzar A, Shabany M, Malekmohammadi A, et al. Efficient hardware implementation of real-time low-power movement intention detector system using FFT and adaptive wavelet transform[J]. IEEE Transactions on Biomedical Circuits and Systems, 2017, 11(3):585-596.
[15] Jain A, Nandakumar K, Ross A. Score normalization in multimodal biometric systems[J]. Pattern Recognition, 2005, 38(12):2270-2285.
[16] Sudirman R, Seow S C. Electroencephalographic based hearing identification using back-propagation algorithm[C]//IEEE Toronto International Conference on Science and Technology for Humanity. Piscataway, USA:IEEE, 2009:991-995.
[17] Blankertz B. BCI Competition Ⅲ[EB/OL].[2018-01-15]. http://www.bbci.de/competition/iii/.