Classification of Motor Imagery Using Combination of Feature Extraction and Reduction Methods for Brain-Computer Interface

The motor imagery (MI) based brain-computer interface systems (BCIs) can help with new communication ways. A typical electroencephalography (EEG)-based BCI system consists of several components including signal acquisition, signal pre-processing, feature extraction and feature classification. This paper focuses on the feature extraction step and proposes to use a combination of different feature extraction and feature reduction methods. The research presented in the paper explores the methods of band power, time domain parameters, fast Fourier transform and channel variance for feature extraction. These methods are investigated by combining them in pairs. The application of two feature extraction methods increases the number of selected features that can be redundant or irrelevant. The utilization of too many features can lead to wrong classification results. Therefore, the methods of feature reduction have to be applied. The following feature reduction methods are investigated: principal component analysis, sequential forward selection, sequential backward selection, locality preserving projections and local Fisher discriminant analysis. The combination of the methods of fast Fourier transform, channel variance and principal component analysis performed the best among the combinations of methods. The obtained classification accuracy of the above-mentioned combination of the methods is much higher than that of the individual feature extraction method. The novelty of the approach is based on consolidated sequence of methods for feature extraction and feature reduction.

Download Full-text

Efficient Classification of Motor Imagery Electroencephalography Signals Using Deep Learning Methods

Sensors ◽

10.3390/s19071736 ◽

2019 ◽

Vol 19 (7) ◽

pp. 1736 ◽

Cited By ~ 11

Author(s):

Ikhtiyor Majidov ◽

Taegkeun Whangbo

Keyword(s):

Feature Extraction ◽

Particle Swarm Optimization ◽

Deep Learning ◽

Motor Imagery ◽

Riemannian Geometry ◽

Brain Computer Interface ◽

Extraction Methods ◽

Covariance Matrices ◽

Computer Interface ◽

Swarm Optimization

Single-trial motor imagery classification is a crucial aspect of brain–computer applications. Therefore, it is necessary to extract and discriminate signal features involving motor imagery movements. Riemannian geometry-based feature extraction methods are effective when designing these types of motor-imagery-based brain–computer interface applications. In the field of information theory, Riemannian geometry is mainly used with covariance matrices. Accordingly, investigations showed that if the method is used after the execution of the filterbank approach, the covariance matrix preserves the frequency and spatial information of the signal. Deep-learning methods are superior when the data availability is abundant and while there is a large number of features. The purpose of this study is to a) show how to use a single deep-learning-based classifier in conjunction with BCI (brain–computer interface) applications with the CSP (common spatial features) and the Riemannian geometry feature extraction methods in BCI applications and to b) describe one of the wrapper feature-selection algorithms, referred to as the particle swarm optimization, in combination with a decision tree algorithm. In this work, the CSP method was used for a multiclass case by using only one classifier. Additionally, a combination of power spectrum density features with covariance matrices mapped onto the tangent space of a Riemannian manifold was used. Furthermore, the particle swarm optimization method was implied to ease the training by penalizing bad features, and the moving windows method was used for augmentation. After empirical study, the convolutional neural network was adopted to classify the pre-processed data. Our proposed method improved the classification accuracy for several subjects that comprised the well-known BCI competition IV 2a dataset.

Download Full-text