Skip to main content

Neural network classification of autoregressive features from electroencephalogram signals for brain-computer interface design

Huan, N.-J., Palaniappan, Ramaswamy (2004) Neural network classification of autoregressive features from electroencephalogram signals for brain-computer interface design. Journal of Neural Engineering, 1 (3). pp. 142-150. ISSN 1741-2560. (doi:10.1088/1741-2560/1/3/003) (The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided)

The full text of this publication is not currently available from this repository. You may be able to access a copy if URLs are provided. (Contact us about this Publication)
Official URL
https://doi.org/10.1088/1741-2560/1/3/003

Abstract

In this paper, we have designed a two-state brain-computer interface (BCI) using neural network (NN) classification of autoregressive (AR) features from electroencephalogram (EEG) signals extracted during mental tasks. The main purpose of the study is to use Keirn and Aunon's data to investigate the performance of different mental task combinations and different AR features for BCI design for individual subjects. In the experimental study, EEG signals from five mental tasks were recorded from four subjects. Different combinations of two mental tasks were studied for each subject. Six different feature extraction methods were used to extract the features from the EEG signals: AR coefficients computed with Burg's algorithm, AR coefficients computed with a least-squares (LS) algorithm and adaptive autoregressive (AAR) coefficients computed with a least-mean-square (LMS) algorithm. All the methods used order six applied to 125 data points and these three methods were repeated with the same data but with segmentation into five segments in increments of 25 data points. The multilayer perceptron NN trained by the back-propagation algorithm (MLP-BP) and linear discriminant analysis (LDA) were used to classify the computed features into different categories that represent the mental tasks. We compared the classification performances among the six different feature extraction methods. The results showed that sixth-order AR coefficients with the LS algorithm without segmentation gave the best performance (93.10%) using MLP-BP and (97.00%) using LDA. The results also showed that the segmentation and AAR methods are not suitable for this set of EEG signals. We conclude that, for different subjects, the best mental task combinations are different and proper selection of mental tasks and feature extraction methods are essential for the BCI design.

Item Type: Article
DOI/Identification number: 10.1088/1741-2560/1/3/003
Additional information: Unmapped bibliographic data: LA - English [Field not mapped to EPrints] J2 - J. Neural Eng. [Field not mapped to EPrints] C2 - 15876633 [Field not mapped to EPrints] AD - Faculty of Information Science and Technology, Multimedia University, Melaka, Malaysia [Field not mapped to EPrints] AD - Biomedical Engineering Research Centre, Nanyang Technological University, Singapore [Field not mapped to EPrints] DB - Scopus [Field not mapped to EPrints] M3 - Article [Field not mapped to EPrints]
Uncontrolled keywords: Algorithms, Backpropagation, Data acquisition, Electroencephalography, Feature extraction, Least squares approximations, Adaptive autoregressive (AAP) coefficients, Autoregressive (AR) features, Brain-computer interface (BCI), Linear discriminant analysis (LDA), Neural networks, algorithm, analytic method, article, artificial neural network, brain computer interface, controlled study, discriminant analysis, electroencephalogram, human, human experiment, mental task, priority journal, signal noise ratio, algorithm, automated pattern recognition, brain, clinical trial, cognition, comparative study, computer interface, electroencephalography, evoked response, methodology, physiology, psychomotor performance, regression analysis, reproducibility, sensitivity and specificity, Algorithms, Brain, Cognition, Electroencephalography, Evoked Potentials, Humans, Neural Networks (Computer), Pattern Recognition, Automated, Psychomotor Performance, Regression Analysis, Reproducibility of Results, Sensitivity and Specificity, User-Computer Interface
Divisions: Faculties > Sciences > School of Computing
Faculties > Sciences > School of Computing > Data Science
Depositing User: Palaniappan Ramaswamy
Date Deposited: 15 Dec 2018 18:04 UTC
Last Modified: 30 May 2019 08:29 UTC
Resource URI: https://kar.kent.ac.uk/id/eprint/70755 (The current URI for this page, for reference purposes)
Palaniappan, Ramaswamy: https://orcid.org/0000-0001-5296-8396
  • Depositors only (login required):