基于CSP和GBDT运动想象脑电模式识别研究The EEG Pattern Recognition Based on CSP and GBDT Movement Imagination
冯建奎
摘要(Abstract)：
为了提高运动想象脑机接口系统的性能，基于脑-机接口竞赛数据比较了不同空间滤波器下获得的CSP特征，在支持向量(线性核和高斯核)(linear kernel support vector machine, LSVM and(gaussian kernel support vector machine, GSVM)),线性判别分析(linear discrimination analysis, LDA),梯度提升决策树(gradient boosting descrision tree, GBDT)下的分类效果.比较结果表明，GBDT获得了比其它分类器更优的分类效果.进一步把最小绝对收缩和选择算法(the Least Absolute Shrinkage and Selectionator operator, LASSO)与以上四种分类器进行结合使用，发现其与GBDT结合使用后得到的平均分类准确率最高，比结合LSVM,GSVM和LDA分别提高了5.57%, 4.57%, 3.16%.
关键词(KeyWords)： 脑机接口;运动想象;梯度提升决策树;共空间模式
基金项目(Foundation):
作者(Author): 冯建奎
DOI: 10.16393/j.cnki.37-1436/z.2023.02.001
参考文献(References)：
- [1]WOLPAW J R,BIRBAUMER N,HEETDERKS W J.Brain computer interface technology:A review of the first international meeting[J].IEEE Transactions on Rehabilitation Engineering,2000,8(2):164-173.
- [2]Wang Xing-Yu,Jin Jing,Zhang Yu,et al.Brain Control:Human-Machine Fusion Control Based on Brain-Machine Interface[J].Journal of Automation,2013,39(3):208-221.
- [3]Kauhanen L ,Nykopp T ,Lehtonen J ,et al.EEG and MEG brain-computer interface for tetraplegic patients[J].IEEE Transactions on Neural Systems & Rehabilitation Engineering,2006,14(2):190-193.
- [4]Kaiser V ,Daly I ,Pichiorri F ,et al.Relationship between electrical brain responses to motor imagery and motor impairment in stroke[J].Stroke,2012,43(10):2735.
- [5]Nicolas-Alonso L F ,Gomez-Gil J .Brain Computer Interfaces,a Review[J].Sensors,2012,12(2):1211-1279.
- [6]Zeng H ,Song A ,Yan R ,et al.EOG Artifact Correction from EEG Recording Using Stationary Subspace Analysis and Empirical Mode Decomposition[J].Sensors,2013,13(11):14839-14859.
- [7]Feng J,Yin E,Jin J,et al.Towards correlation-based time window selection method for motor imagery BCIs[J].Neural Networks,2018,102:87-95.
- [8]Nicolas-Alonso L F ,Corralejo R ,Gomez-Pilar J ,et al.Adaptive semi-supervised classification to reduce intersession non-stationarity in multiclass motor imagery-based brain-computer interfaces[J].Neurocomputing,2015,159(2):186-196.
- [9]Tu W,Sun S.Spatial filter selection with LASSO for EEG classification[J].Lecture Notes in Computer Science,2010:142-149.
- [10]Salazar-Varas R,Gutiérrez D.An optimized feature selection and classification method for using electroencephalographic coherence in brain–computer interfaces[J].Biomedical Signal Processing and Control,2015,18:11-18.
- [11]Mo H,Zhao Y.Motor imagery electroencephalograph classification based on optimized support vector machine by magnetic bacteria optimization algorithm[J].Neural Processing Letters,2016,44:185-197.
- [12]Qiu Z,Jin J,Lam H K,et al.Improved SFFS method for channel selection in motor imagery based BCI[J].Neurocomputing,2016,207(C):519-527.
- [13]Gareis I E,Acevedo R C,Atum Y V,et al.Determination of an optimal training strategy for a BCI classification task with LDA[C]//2011 5th International IEEE/EMBS Conference on Neural Engineering.IEEE,2011:286-289.
- [14]Fukunaga K.Introduction to statistical pattern recognition[M].Elsevier,2013.
- [15]孙会文，伏云发，熊馨，等.基于HHT运动想象脑电模式识别研究[J].自动化学报，2015,41(9):1686-1692.
- [16]Zhang C,Liu C,Zhang X,et al.An Up-to-Date Comparison of State-of-the-Art Classification Algorithms[J].Expert Systems with Applications,2017,82(C):128-150.