Neural Network-Based Feature Extraction for Multi-Class Motor Imagery Classification

TL;DR

This paper introduces a novel EEG feature extraction method using autoencoder weight vectors to improve multi-class motor imagery classification accuracy in brain-computer interfaces.

Contribution

It proposes transforming EEG signals into autoencoder weight vectors for enhanced feature extraction, demonstrating superior classification performance on public datasets.

Findings

Achieved 95.33% accuracy on BCI-III dataset.

Achieved 97% accuracy on BCI-IV dataset.

Outperformed previous methods in multi-class MI classification.

Abstract

Decoding of motor imagery (MI) from Electroencephalogram (EEG) is an important component of the Brain-Computer Interface (BCI) system that helps motor-disabled people interact with the outside world via external devices. The main issue in developing the EEG based BCI is the informative confusion due to the non-stationary characteristics of EEG data. In this work, an innovative idea of transforming an EEG signal into the weight vector of an unsupervised neural network called the autoencoder is proposed for the first time to solve that problem. Separate autoencoders are trained for the individual EEG data. The weight vectors are then optimized for the individual EEG signals. The EEG signals are thus represented in a new domain that is in the form of weight vectors of the individual autoencoder. The weight vectors are then used to extract features such as autoregressive coefficients (ARs), Shannon entropy (SE), and wavelet leader. A window-based feature extraction technique is implemented to capture the local features of the EEG data. Finally, extracted features are classified using a classifier network. The proposed approach is tested on two publicly accessible EEG datasets (BCI competition-III and Competition-IV) to ensure that it is as successful as and superior to the previously published methods. The proposed technique achieves a mean accuracy of 95.33 % for dataset-IIIa from BCI-III and a mean accuracy of 97% for dataset-IIa from BCI-IV for four-class EEG-based MI classification. The experimental outcomes show that the proposed approach is a promising way to increase BCI performance.