Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/71038
Title: Multi-class motor motion imagery using common spatial patterns based on joint approximate diagonalization
Authors: Liyanage, S.R.
Xu, J.-X. 
Guan, C.
Ang, K.K.
Lee, T.H. 
Keywords: Brain-computer interfaces (BCI)
Common spatial patterns (CSP)
Electroencephalogram (EEG)
Joint approximate diagonalization (JAD)
Motion control
Issue Date: 2010
Source: Liyanage, S.R.,Xu, J.-X.,Guan, C.,Ang, K.K.,Lee, T.H. (2010). Multi-class motor motion imagery using common spatial patterns based on joint approximate diagonalization. Proceedings of the 12th IASTED International Conference on Control and Applications, CA 2010 : 409-415. ScholarBank@NUS Repository.
Abstract: Motion intention can be detected from human EEG signals through BCI, which can facilitate motor motion control for disabled or paralyzed people. However, the design of multiclass BCI is a very challenging task because of the need to extract complex spatial and temporal patterns from noisy multidimensional time series generated from EEG measurements. This paper proposes a multiclass common spatial pattern (MCSP) based on Joint Approximate Diagonalization (JAD) for multiclass BCIs. The proposed method based on fast Frobenius diagonalization (FFDIAG) is compared with one versus rest common spatial patterns (CSP) on the BCI competition IV dataset 2a. The classification accuracies obtained from 10×10-fold cross-validations on the training dataset are compared using K-Nearest Neighbor, Classification Trees and Support Vector Machine classifiers. The classifiers are boosted using Stagewise Additive Modelling using a Multi-class exponential loss function (SAMME) and Adaboost.M1. The proposed MCSP based on FFDIAG yields an averaged accuracy of 54.1% compared to 28.8% given by the one versus rest CSP methods.
Source Title: Proceedings of the 12th IASTED International Conference on Control and Applications, CA 2010
URI: http://scholarbank.nus.edu.sg/handle/10635/71038
ISBN: 9780889868526
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Page view(s)

65
checked on Dec 9, 2017

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.