|
|
Research on EEG Feature Extraction Method in Boundary Avoidance Task Based on Non-Negative CP Decomposition Model |
Fu Rongrong1*, Yu Bao1, Sun Jiedi2 |
1(School of Electrical Engineering, Yanshan University, Qinhuangdao 066004,Hebei, China) 2(School of Information Science and Engineering, Yanshan University, Qinhuangdao 066004, Hebei, China) |
|
|
Abstract This study aimed to improve the subjects' EEG arousal by establishing a “bowl-ball” model and performing visually guided boundary avoidance tasks. In the process of interacting with the “bowl-ball” model, the EEG data of 10 healthy subjects about the left and right-hand motor tasks were collected, and the optimized features of the EEG were classified to realize the decoding of the exercise intention. The EEG signal induced by the boundary avoidance task is subjected to 8-13Hz band-pass filtering to obtain data of a specific frequency band, and the frequency components of EEG were obtained through continuous wavelet transform to generate EEG tensor. We used the non-negative CP decomposition model to extract the time component features of the EEG tensor, then used the two-dimensional principal component analysis to optimize the features, used the support vector machine (SVM) to classify the features, and compared with the method of feature extraction and feature classification using common spatial pattern (CSP) and SVM. The results of all subjects showed that the general best component number of CP decomposition was 16, based on the feature extraction method of non-negative CP decomposition model, the accuracy of SVM classification was 95.5%±3.0%, and the AUC value was 0.978 2±0.012 1. The classification accuracy was better than CSP+SVM (93.7%±3.1%). The discriminant score of the classification result was tested by t-test, and the classification result had 95% confidence (P<0.05). In conclusion, the motor intention classification based on features extracted from the non-negative CP decomposition model reflected the differences in different states in boundary avoidance tasks and improve classification performance.
|
Received: 06 August 2019
|
|
Corresponding Authors:
*E-mail: frr1102@aliyun.com
|
|
|
|
[1] Pfurtscheller G. Motor imagery activates primary sensorimotor area in humans[J]. Neuroence Letters, 1997, 239: 65-68. [2] Guillot A, Collet C, Nguyen V A, et al. Functional neuroanatomical networks associated with expertise in motor imagery[J]. Neuroimage, 2008, 41(4):1471-1483. [3] Kober SE, Grössinger, Doris, Wood G. Effects of motor imagery and visual neurofeedback on activation in the swallowing network: A real-time fMRI study[J]. Dysphagia, 2019, 34(6):879-895. [4] Bian Y, Qi H, Zhao L, et al. Dynamic visual guidance with complex task improves intracortical source activities during motor imagery[J]. Neuroreport, 2019, 30(9):645-652. [5] Sun Y, Wei W, Luo Z, et al. Improving motor imagery practice with synchronous action observation in stroke patients[J]. Topics in Stroke Rehabilitation, 2016, 23(4):245-253. [6] Cervera MA, Soekadar SR, Ushiba J, et al. Brain-computer interfaces for post-stroke motor rehabilitation: A meta-analysis[J]. Annals of Clinical and Translational Neurology, 2018, 5(5):651-663. [7] Blankertz B, Sannelli C, Halder S, et al. Neurophysiological predictor of SMR-based BCI performance[J]. NeuroImage, 2010, 51(4):1303-1309. [8] Allison BZ, Brunner C, Altstätter C, et al. A hybrid ERD/SSVEP BCI for continuous simultaneous two dimensional cursor control[J]. Journal of Neuroence Methods, 2012, 209(2):299-307. [9] Falou WE, Jacques D, Grabisch M, et al. Evaluation of driver discomfort during long-duration car driving[J]. Applied Ergonomics, 2003, 34(3):249-255. [10] Ramoser H, Muller-Gerking J, Pfurtscheller G. Optimal spatial filtering of single trial EEG during imagined hand movement[J]. IEEE Transactions on Rehabilitation Engineering, 2000, 8(4):441-446. [11] Zhao Qibin, Zhang Liqing, Cichocki A. Multilinear generalization of Common Spatial Pattern[C]// Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Taipei: IEEE, 2009:525-528. [12] 王金甲, 杨亮. 脑机接口中多线性主成分分析的张量特征提取[J]. 生物医学工程学杂志, 2015(3):526-530. [13] 高煜妤, 王柏娜. 核张量子空间分解EEG特征提取方法研究[J]. 计算机工程与应用, 2019, 55(7):137-142,149. [14] Cong F, Lin Q H, Kuang L D, et al. Tensor decomposition of EEG signals: A brief review[J]. Journal of Neuroence Methods, 2015, 248:59-69. [15] 赵冬娟, 梁久祯. 融合2DPCA和模糊2DLDA的人脸识别[J]. 计算机应用, 2011, 31(2):420-422. [16] 李钢, 王蔚, 李乐加. 支持向量机在脑电信号分类中的应用[J]. 计算机应用, 2006, 26(6):1431-1433. [17] 赵丽, 郭旭宏, 耿丽清. 多类运动想象脑电信号的处理研究[J]. 中国生物医学工程学报, 2013,32(5):636-640. [18] Shi LC, Li Y, Sun RH, et al. A sparse common spatial pattern algorithm for brain-computer interface [J]. Neural Inf Process, 2011, 7062: 725-733. [19] Arvaneh M, Guan C, Ang KK, et al. Spatially sparsed Common Spatial Pattern to improve BCI performance [C]//2011 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Prague: IEEE, 2011: 2412-2424. [20] Benjamin B. BCI Competition IV: Results. http://www.bbci.de/competition/iv/results/index.html. 2008-12-12/2019-09-09. [21] Meng J, Zhang S, Bekyo A, et al. Noninvasive electroencephalogram based control of a robotic arm for reach and grasp tasks [J]. Nature Scientific Reports, 2016, 6 (1): 1-15. |
[1] |
Wu Ruoyou, Wang Dexing, Yuan Hongchun, Gong Peng, Qin Enqian. Attention State Detection Based on Feature Encoding and Convolutional Neural Networks[J]. Chinese Journal of Biomedical Engineering, 2020, 39(6): 759-763. |
[2] |
Shen Lei, Geng Xinyi, Wang Shouyan. Epileptic States Recognition using Transfer Learning and Dilated CNN[J]. Chinese Journal of Biomedical Engineering, 2020, 39(6): 700-710. |
|
|
|
|