A Discriminative and Robust Feature Learning Approach for EEG-Based Motor Imagery Decoding (Student Abstract)

Authors

  • Xiuyu Huang Centre for Smart Health, The Hong Kong Polytechnic University
  • Nan Zhou College of Control Engineering, Chengdu University of Information Technology Centre for Smart Health, The Hong Kong Polytechnic University
  • Kup-Sze Choi Centre for Smart Health, The Hong Kong Polytechnic University

DOI:

https://doi.org/10.1609/aaai.v36i11.21622

Keywords:

Correntropy, Center Loss, Convolutional Neural Networks, Motor Imagery

Abstract

Convolutional neural networks (CNNs) have been commonly applied in the area of the Electroencephalography (EEG)-based Motor Imagery (MI) classification, significantly pushing the boundary of the state-of-the-art. In order to simultaneously decode the discriminative features and eliminate the negative effects of non-Gaussian noise and outliers in the motor imagery data, in this abstract, we propose a novel robust supervision signal, called Correntropy based Center Loss (CCL), for CNN training, which utilizes the correntropy induced distance as the objective measure. It is encouraging to see that the CNN model trained by the combination of softmax loss and CCL loss outperforms the state-of-the-art models on two public datasets.

Downloads

Published

2022-06-28

How to Cite

Huang, X., Zhou, N., & Choi, K.-S. (2022). A Discriminative and Robust Feature Learning Approach for EEG-Based Motor Imagery Decoding (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 36(11), 12971-12972. https://doi.org/10.1609/aaai.v36i11.21622