Multi-band FDBN Algorithm for Extracting EEG Features
CAI Jun1, HU Yangkui1, ZHANG Yi2, YIN Chunlin1
1. School of Automation, Chongqing University of Posts and Telecommunications, Chongqing 404100, China;
2. School of Advanced Manufacturing Engineering, Chongqing University of Posts and Telecommunications, Chongqing 404100, China
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.
[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/.