Improving Classification of Slow Cortical Potential Signals for BCI Systems With Polynomial Fitting and Voting Support Vector Machine

Classification of slow cortical potential (SCP) signals is crucial for brain–computer interface (BCI) systems. This letter presents a new scheme to improve the classification performance of SCP signals. It consists of two parts: first, by fitting the wavelet coefficients of SCP signals with a second-order polynomial, the SCP trends are extracted; and second, a voting system based on the optimal training parameters of the support vector machines is developed to enhance the classification accuracy (CA). Experimental results reveal that the proposed scheme outperforms the state-of-the-art methods. The CA improvements for the dataset Ia of the BCI competition II and the TJU dataset (the dataset was collected in Tianjin University, termed TJU dataset) are reported.

[1]  Lijuan Duan,et al.  Motor Imagery EEG Classification Based on Kernel Hierarchical Extreme Learning Machine , 2017, Cognitive Computation.

[2]  Yan Guozheng,et al.  EEG feature extraction based on wavelet packet decomposition for brain computer interface , 2008 .

[3]  N. Birbaumer,et al.  Brain–computer interfaces for communication and rehabilitation , 2016, Nature Reviews Neurology.

[4]  N. Birbaumer,et al.  Self-regulation of Slow Cortical Potentials: A New Treatment for Children With Attention-Deficit/Hyperactivity Disorder , 2006, Pediatrics.

[5]  Jason Farquhar,et al.  Detection of attempted movement from the EEG during neuromuscular block: proof of principle study in awake volunteers , 2015, Scientific Reports.

[6]  Zhen Yang,et al.  A Voting Optimized Strategy Based on ELM for Improving Classification of Motor Imagery BCI Data , 2014, Cognitive Computation.

[7]  Guang Li,et al.  EEG Recognition Based on Multiple Types of Information by Using Wavelet Packet Transform and Neural Networks , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[8]  Yi Li,et al.  EEG Nonlinear Feature Detection in Brain-Computation Interface , 2009, 2009 3rd International Conference on Bioinformatics and Biomedical Engineering.

[9]  Eric W. Sellers,et al.  Noninvasive brain-computer interface enables communication after brainstem stroke , 2014, Science Translational Medicine.

[10]  Justin Werfel,et al.  BCI competition 2003-data set Ia: combining gamma-band power with slow cortical potentials to improve single-trial classification of electroencephalographic signals , 2004, IEEE Transactions on Biomedical Engineering.

[11]  Li Lin,et al.  Bilinear Grid Search Strategy Based Support Vector Machines Learning Method , 2014, Informatica.

[12]  Katherine Ellen Foley.  Ideas in movement: The next wave of brain-computer interfaces , 2016, Nature Medicine.

[13]  Mustafa Ulutas,et al.  Classification of EEG signals using time domain features , 2015, 2015 23nd Signal Processing and Communications Applications Conference (SIU).

[14]  Yanhui Xu,et al.  Classification Based on Multilayer Extreme Learning Machine for Motor Imagery Task from EEG Signals , 2016, BICA.

[15]  Onder Aydemir,et al.  A polynomial fitting and k-NN based approach for improving classification of motor imagery BCI data , 2010, Pattern Recognit. Lett..

[16]  Shiliang Sun,et al.  Assessing features for electroencephalographic signal categorization , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..