Programs
- M. Tech. in Automotive Engineering -
- Clinical Fellowship in Laboratory Genetics & Genomics - Fellowship
Publication Type : Conference Paper
Publisher : 10th WSEAS International Conference on Wavelet Analysis and Multirate Systems, WAMUS '10, 9th WSEAS International Conference on Non-Linear Analysis, Non-Linear Systems and Chaos, NOLASC '10
Source : 10th WSEAS International Conference on Wavelet Analysis and Multirate Systems, WAMUS '10, 9th WSEAS International Conference on Non-Linear Analysis, Non-Linear Systems and Chaos, NOLASC '10, Sousse, p.83-88 (2010)
ISBN : 9789604741892
Keywords : Artifact removal, Brain computer interface, Chaotic systems, Common spatial patterns, Conventional schemes, Data sets, Dimensionality reduction, Discriminant analysis, EEG signals, General tensor discriminant analysis, General Tensor Discriminant Analysis (GTDA), Hand movement, Interfaces (computer), Linear discriminant analysis, Linear systems, Mental task classification, Muscular communication, Nonlinear systems, Pre-processing, Support vector machines, Tensors, Training sample, Under-sampling, Wavelet analysis, Wavelet transforms
School : Centre for Cybersecurity Systems and Networks
Department : cyber Security
Year : 2010
Abstract : Brain Computer Interface (BCI) is a system that provides a non-muscular communication between men and machines. This paper aims at classification of motor (hand movement) imagery to facilitate control for physically challenged persons using EEG signals. The work involves a scheme based on tensors. Advantages of this scheme over conventional schemes like Common Spatial Patterns (CSP), Linear Discriminant Analysis (LDA) are that 1. The number of parameters required to model the data is reduced, 2. This scheme works well without pre-processing (filtering, artifact removal etc.) of EEG signals, 3. Undersampling problem (number of training samples is less than dimension of data) is reduced. The work employs wavelet transform for representing EEG signals as tensors, General Tensor Discriminant Analysis (GTDA) for dimensionality reduction and Support Vector Machines for classification. Applications to datasets show the efficiency of this scheme compared to CSP and LDA. The work is expected to open new and higher levels of control for BCI since preprocessing is not needed.
Cite this Research Publication : C. Vab Nagendhiran, Kumar, Mab Ashok, Kharthigeyan, S. Sab, Naveen, Lab, and Prasanna, Sab Sai, “Tensor scheme using GTDA for EEG mental task classification”, in 10th WSEAS International Conference on Wavelet Analysis and Multirate Systems, WAMUS '10, 9th WSEAS International Conference on Non-Linear Analysis, Non-Linear Systems and Chaos, NOLASC '10, Sousse, 2010, pp. 83-88.