Simultaneous Channel and Feature Selection of Fused EEG Features Based on Sparse Group Lasso

Feature extraction and classification of EEG signals are core parts of brain computer interfaces (BCIs). Due to the high dimension of the EEG feature vector, an effective feature selection algorithm has become an integral part of research studies. In this paper, we present a new method based on a wrapped Sparse Group Lasso for channel and feature selection of fused EEG signals. The high-dimensional fused features are firstly obtained, which include the power spectrum, time-domain statistics, AR model, and the wavelet coefficient features extracted from the preprocessed EEG signals. The wrapped channel and feature selection method is then applied, which uses the logistical regression model with Sparse Group Lasso penalized function. The model is fitted on the training data, and parameter estimation is obtained by modified blockwise coordinate descent and coordinate gradient descent method. The best parameters and feature subset are selected by using a 10-fold cross-validation. Finally, the test data is classified using the trained model. Compared with existing channel and feature selection methods, results show that the proposed method is more suitable, more stable, and faster for high-dimensional feature fusion. It can simultaneously achieve channel and feature selection with a lower error rate. The test accuracy on the data used from international BCI Competition IV reached 84.72%.

[1]  Vahid Abootalebi,et al.  Selection of an efficient feature space for EEG-based mental task discrimination , 2014 .

[2]  Cheolsoo Park,et al.  Classification of Motor Imagery BCI Using Multivariate Empirical Mode Decomposition , 2013, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[3]  Yong Xu,et al.  Sparse group LASSO based uncertain feature selection , 2013, International Journal of Machine Learning and Cybernetics.

[4]  Niels Richard Hansen,et al.  Sparse group lasso and high dimensional multinomial classification , 2012, Comput. Stat. Data Anal..

[5]  Yuanqing Li,et al.  Channel selection by Rayleigh coefficient maximization based genetic algorithm for classifying single-trial motor imagery EEG , 2013, Neurocomputing.

[6]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[7]  E Donchin,et al.  Brain-computer interface technology: a review of the first international meeting. , 2000, IEEE transactions on rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society.

[8]  Fernando José Von Zuben,et al.  Automatic feature selection for BCI: An analysis using the davies-bouldin index and extreme learning machines , 2012, The 2012 International Joint Conference on Neural Networks (IJCNN).

[9]  Izabela Rejer,et al.  EEG Feature Selection for BCI Based on Motor Imaginary Task , 2012 .

[10]  Amit Konar,et al.  Automatic feature selection of motor imagery EEG signals using differential evolution and learning automata , 2013, Medical & Biological Engineering & Computing.

[11]  P. Bühlmann,et al.  The group lasso for logistic regression , 2008 .

[12]  Isabelle Bloch,et al.  Subject-specific channel selection for classification of motor imagery electroencephalographic data , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[13]  Aleksandra Vučković,et al.  A two-stage four-class BCI based on imaginary movements of the left and the right wrist. , 2012, Medical engineering & physics.

[14]  Pedro J. García-Laencina,et al.  Efficient feature selection and linear discrimination of EEG signals , 2013, Neurocomputing.

[15]  Cuntai Guan,et al.  Optimizing the Channel Selection and Classification Accuracy in EEG-Based BCI , 2011, IEEE Transactions on Biomedical Engineering.

[16]  Cuntai Guan,et al.  Robust EEG channel selection across sessions in brain-computer interface involving stroke patients , 2012, The 2012 International Joint Conference on Neural Networks (IJCNN).

[17]  Trevor Hastie,et al.  Regularization Paths for Generalized Linear Models via Coordinate Descent. , 2010, Journal of statistical software.

[18]  Izabela Rejer,et al.  Genetic algorithm and forward method for feature selection in EEG feature space , 2013 .

[19]  Noah Simon,et al.  A Sparse-Group Lasso , 2013 .

[20]  C.W. Anderson,et al.  Multivariate autoregressive models for classification of spontaneous electroencephalographic signals during mental tasks , 1998, IEEE Transactions on Biomedical Engineering.

[21]  Yu-Chiang Frank Wang,et al.  A Novel Multiple Kernel Learning Framework for Heterogeneous Feature Fusion and Variable Selection , 2012, IEEE Transactions on Multimedia.

[22]  Isao Nambu,et al.  EEG Channel Selection Using Particle Swarm Optimization for the Classification of Auditory Event-Related Potentials , 2014, TheScientificWorldJournal.