Impact Factor 3.566

The Frontiers in Neuroscience journal series is the 1st most cited in Neurosciences

Original Research ARTICLE Provisionally accepted The full-text will be published soon. Notify me

Front. Neurosci. | doi: 10.3389/fnins.2018.00272

Improving Generalization based on l1-norm Regularization for EEG-based Motor Imagery Classification

 Yuwei Zhao1, Jiuqi Han1, Yushu Chen1, Hongji Sun1,  Ang Ke2, Yao Han3,  Peng Zhang2, Yi Zhang1, Jin Zhou1 and  Changyong Wang1*
  • 1Tissue Engineering Research Center, Beijing Institute of Basic Medical Sciences, China
  • 2Huazhong University of Science and Technology, China
  • 3Stem Cell and Tissue Engineering Lab, Beijing Institute of Transfusion Medicine, China

Multichannel electroencephalography (EEG) is widely used in typical brain-computer interface (BCI) systems. In general, a number of parameters are essential for a EEG classification algorithm due to redundant features involved in EEG signals. However, the generalization of the EEG method is often adversely affected by the model complexity, considerably coherent with its number of undetermined parameters, further leading to heavy overfitting. To decrease the complexity and improve the generalization of EEG method, we present a novel $l_1$-norm-based approach to combine the decision value obtained from each EEG channel directly. By extracting the information from different channels on independent frequency bands (FB) with l1-norm regularization, the method proposed fits the training data with much less parameters compared to common spatial pattern (CSP) methods in order to reduce overfitting. Moreover, an effective and efficient solution to minimise the optimization object is proposed. The experimental results on dataset IVa of BCI competition III and dataset I of BCI competition IV show that, the proposed method contributes to high classification accuracy and increases generalization performance for the classification of MI EEG. As the training set ratio decreased from 80% to 20%, the average classification accuracy on the two datasets changed from 85.86% and 86.13% to 84.81% and 76.59%, respectively. The classification performance and generalization of the proposed method contribute to the practical application of MI based BCI systems.

Keywords: Motor Imagery, Electroencephalography (EEG), Classification, L1-norm regularization, generalization

Received: 05 Jan 2018; Accepted: 09 Apr 2018.

Edited by:

Ioan Opris, University of Miami, United States

Reviewed by:

Dezhong Yao, University of Electronic Science and Technology of China, China
Zhong Yin, University of Shanghai for Science and Technology, China  

Copyright: © 2018 Zhao, Han, Chen, Sun, Ke, Han, Zhang, Zhang, Zhou and Wang. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence: Prof. Changyong Wang, Tissue Engineering Research Center, Beijing Institute of Basic Medical Sciences, Beijing, China,