一种运动想象脑电信号半监督算法
|
摘要
针对脑机接口中两类左右手运动想象任务,提出一种依据迭代训练次数不断更新训练集样本的半监督算法.使用多重自相关分析算法,选择置信度较高的脑电信号样本并加入初始训练集;分别使用公共平均参考法与共空域模式算法,对样本进行预处理及特征提取;最后使用支持向量机对样本进行测试,根据迭代学习次数按照递进方式移除置信度较低的样本,并利用剩余样本继续训练模型,从而优化特征提取器及分类器参数.通过对标准脑电竞赛数据库BCI IV Dataset IIa中左右手运动想象数据的测试表明,该算法与其他算法相比,在训练样本数目较少的情况下,具有较高的分类正确率.
A sequential updating semi-supervised classification based on training iterations was proposed for the two-class motor imagery task in brain-computer interface.Firstly,making use of multiple autocorrelation analysis,the training samples with high confidence were selected as initial training set.Then common average reference and common spatial pattern were used for pre-processing and feature extraction,respectively.Lastly,support vector machine was applied to test new samples.The samples with low confidence were removed successively according to the iterations.The remains were used to retrain the model to optimize the parameters of both feature extractor and classifier.The proposed method was applied to Dataset IIa of BCI Competition IV to verify its validity.The results show that the classification accuracy is higher than other algorithms on the occasion where training samples are not enough.It can provide a new solution for the real-time BCIs.
A sequential updating semi-supervised classification based on training iterations was proposed for the two-class motor imagery task in brain-computer interface.Firstly,making use of multiple autocorrelation analysis,the training samples with high confidence were selected as initial training set.Then common average reference and common spatial pattern were used for pre-processing and feature extraction,respectively.Lastly,support vector machine was applied to test new samples.The samples with low confidence were removed successively according to the iterations.The remains were used to retrain the model to optimize the parameters of both feature extractor and classifier.The proposed method was applied to Dataset IIa of BCI Competition IV to verify its validity.The results show that the classification accuracy is higher than other algorithms on the occasion where training samples are not enough.It can provide a new solution for the real-time BCIs.
引文
[1]Wang Y,Berg P,Scherg M.Common spatial subspace decomposition applied to analysis of brain responses under multiple task conditions:a simulation study[J].Clinical Neurophysiology,1999,110(4):604-614.
[2]Cortes C,Vapnik V.Support-vector networks[J].Machine Learning,1995,20(3):273-297.
[3]Abdel-Hadi M E A,El-Khoribi R A,Shoman M I,et al.Classification of motor imagery tasks with LS-SVM in EEG-based self-paced BCI[C]∥Proceedings of the Fifth International Conference on Digital Information Processing and Communications.[S.l]:IEEE,2015.
[4]Zhu Xiaojin.Semi-supervised learning[M].[S.l.]:Springer US,2010.
[5]Rosenberg C,Hebert M,Schneiderman H.Semi-supervised self-training of object detection models[C]∥Proceedings of IEEE Workshop on Applications of Computer Vision/IEEE Workshop on Motion and Video Computing.[S.l.]:IEEE,2005:29-36.
[6]Nigam K,Mccallum A,Mitchell T M.Semi-supervised text classification using EM[J].AIAA Journal,2006,36(36):62-68.
[7]Ren Y,Wu Y,Ge Y.A co-training algorithm for EEG classification with biomimetic pattern recognition and sparse representation[J].Neurocomputing,2014,137(15):212-222.
[8]Nie F,Xiang S,Liu Y,et al.A general graph-based semi-supervised learning with novel class discovery[J].Neural Computing&Applications,2010,19(4):549-555.
[9]Tian X,Gasso G,Canu S.A multiple kernel framework for inductive semi-supervised SVM learning[J].Neurocomputing,2012,90(8):46-58.
[10]Guan G,Hu Y,He Q,et al.Joint rayleigh coefficient maximization and graph based semi-supervised for the classification of motor imagery EEG[C]∥Proceedings of IEEE International Conference on Information and Automation.[S.l.]:IEEE,2013:379-383.
[11]Li Y,Guan C,Li H,et al.A self-training semi-supervised SVM algorithm and its application in an EEGbased brain computer interface speller system[J].Pattern Recognition Letters,2008,29(9):1285-1294.
[12]Pfurtscheller G,Neuper C,Flotzinger D,et al.EEGbased discrimination between imagination of right and left hand movement[J].Electroencephalography&Clinical Neurophysiology,1997,103(6):642-51.
[13]Fukunaga K.Introduction to statistical pattern recognition[M].[S.l.]:Academic Press,2013.
[14]Drish J.Obtaining calibrated probability estimates from support vector machines[R].San Diego,CA:Department of Computer Science and Engineering,University of California,2001.
[15]Chen M,Tan X,Zhang L.An iterative sef-training support vector machine algorithm in brain-computer interfaces[J].Intelligent Data Analysis,2016,20(1):67-82.
[16]Ang K K,Chin Z Y,Wang C,et al.Filter bank common spatial pattern algorithm on BCI Competition IV datasets 2a and 2b[J].Frontiers in Neuroscience,2012,6:39-39.
[17]Yang H,Sakhavi S,Kai K A,et al.On the use of convolutional neural networks and augmented CSP features for multi-class motor imagery of EEG signals classification[C]∥Proceedings of International Conference of the IEEE Engineering in Medicine&Biology Society IEEE Embs.[S.l.]:IEEE,2015:2620-2623.
[18]Nicolas-Alonso L F,Corralejo R,Gomez-Pilar J,et al.Adaptive semi-supervised classification to reduce intersession non-stationarity in multiclass motor imagerybased brain-computer interfaces[J].Neurocomputing,2015,159(1):186-196.
[2]Cortes C,Vapnik V.Support-vector networks[J].Machine Learning,1995,20(3):273-297.
[3]Abdel-Hadi M E A,El-Khoribi R A,Shoman M I,et al.Classification of motor imagery tasks with LS-SVM in EEG-based self-paced BCI[C]∥Proceedings of the Fifth International Conference on Digital Information Processing and Communications.[S.l]:IEEE,2015.
[4]Zhu Xiaojin.Semi-supervised learning[M].[S.l.]:Springer US,2010.
[5]Rosenberg C,Hebert M,Schneiderman H.Semi-supervised self-training of object detection models[C]∥Proceedings of IEEE Workshop on Applications of Computer Vision/IEEE Workshop on Motion and Video Computing.[S.l.]:IEEE,2005:29-36.
[6]Nigam K,Mccallum A,Mitchell T M.Semi-supervised text classification using EM[J].AIAA Journal,2006,36(36):62-68.
[7]Ren Y,Wu Y,Ge Y.A co-training algorithm for EEG classification with biomimetic pattern recognition and sparse representation[J].Neurocomputing,2014,137(15):212-222.
[8]Nie F,Xiang S,Liu Y,et al.A general graph-based semi-supervised learning with novel class discovery[J].Neural Computing&Applications,2010,19(4):549-555.
[9]Tian X,Gasso G,Canu S.A multiple kernel framework for inductive semi-supervised SVM learning[J].Neurocomputing,2012,90(8):46-58.
[10]Guan G,Hu Y,He Q,et al.Joint rayleigh coefficient maximization and graph based semi-supervised for the classification of motor imagery EEG[C]∥Proceedings of IEEE International Conference on Information and Automation.[S.l.]:IEEE,2013:379-383.
[11]Li Y,Guan C,Li H,et al.A self-training semi-supervised SVM algorithm and its application in an EEGbased brain computer interface speller system[J].Pattern Recognition Letters,2008,29(9):1285-1294.
[12]Pfurtscheller G,Neuper C,Flotzinger D,et al.EEGbased discrimination between imagination of right and left hand movement[J].Electroencephalography&Clinical Neurophysiology,1997,103(6):642-51.
[13]Fukunaga K.Introduction to statistical pattern recognition[M].[S.l.]:Academic Press,2013.
[14]Drish J.Obtaining calibrated probability estimates from support vector machines[R].San Diego,CA:Department of Computer Science and Engineering,University of California,2001.
[15]Chen M,Tan X,Zhang L.An iterative sef-training support vector machine algorithm in brain-computer interfaces[J].Intelligent Data Analysis,2016,20(1):67-82.
[16]Ang K K,Chin Z Y,Wang C,et al.Filter bank common spatial pattern algorithm on BCI Competition IV datasets 2a and 2b[J].Frontiers in Neuroscience,2012,6:39-39.
[17]Yang H,Sakhavi S,Kai K A,et al.On the use of convolutional neural networks and augmented CSP features for multi-class motor imagery of EEG signals classification[C]∥Proceedings of International Conference of the IEEE Engineering in Medicine&Biology Society IEEE Embs.[S.l.]:IEEE,2015:2620-2623.
[18]Nicolas-Alonso L F,Corralejo R,Gomez-Pilar J,et al.Adaptive semi-supervised classification to reduce intersession non-stationarity in multiclass motor imagerybased brain-computer interfaces[J].Neurocomputing,2015,159(1):186-196.