Online multiclass EEG feature extraction and recognition using modified convolutional neural network method

Haider Abdulkarim, Mohammed Z. Al-Faiz

Abstract


Over the past few decades, brain-computer interface (BCI) applications have witnessed major research contributions. Many techniques have been introduced to improve both BCI steps: feature extraction and classification. One of the emerging trends in this field is the implementation of Deep learning algorithms in both feature extraction and classification. There is a limited number of studies that investigated the application of deep learning techniques in electroencephalography (EEG) feature extraction and classification, and most of them are applied to solve two-classes applications. This work is intended to apply deep learning for both stages: feature extraction and classification. The goal is to recognize multi-class EEG gestures. This paper proposes a modified convolutional neural network (CNN) feature extractor-classifier algorithm to recognize four different EEG motor imagery (MI). In addition, the majority voting was used to improve the algorithm performance. In addition, a four-class linear discriminant analysis (LDR) classifier model was built and compared to the proposed CNN model. The paper showed very good results with 92.8% accuracy for one EEG four-class MI set and 85.7% for another set. The results showed that the proposed CNN model outperforms multi-class linear discriminant analysis with an accuracy increase of 28.6% and 17.9% for both MI sets, respectively. Moreover, it has been shown that majority voting for five repetitions introduced an accuracy advantage of 15% and 17.2% for both EEG sets, compared with single trials. This confirms that increasing the number of trials for the same MI gesture improves the recognition accuracy.


Keywords


brain-computer interface; convolutional neural network; deep learning; electroencephalography; linear discriminant analysis; motor imagery;



DOI: http://doi.org/10.11591/ijece.v11i5.pp%25p

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

International Journal of Electrical and Computer Engineering (IJECE)
p-ISSN 2088-8708, e-ISSN 2722-2578