Discriminative tandem features for hmm-based EEG classification

We investigate the use of discriminative feature extractors in tandem configuration with generative EEG classification system. Existing studies on dynamic EEG classification typically use hidden Markov models (HMMs) which lack discriminative capability. In this paper, a linear and a non-linear class...

Full description

Bibliographic Details
Main Authors: Ting, Chee-Ming, King, Simon, Salleh, Sh-Hussain, Ariff, A. K.
Format: Conference or Workshop Item
Published: 2013
Subjects:
_version_ 1796859553276493824
author Ting, Chee-Ming
King, Simon
Salleh, Sh-Hussain
Ariff, A. K.
author_facet Ting, Chee-Ming
King, Simon
Salleh, Sh-Hussain
Ariff, A. K.
author_sort Ting, Chee-Ming
collection ePrints
description We investigate the use of discriminative feature extractors in tandem configuration with generative EEG classification system. Existing studies on dynamic EEG classification typically use hidden Markov models (HMMs) which lack discriminative capability. In this paper, a linear and a non-linear classifier are discriminatively trained to produce complementary input features to the conventional HMM system. Two sets of tandem features are derived from linear discriminant analysis (LDA) projection output and multilayer perceptron (MLP) class-posterior probability, before appended to the standard autoregressive (AR) features. Evaluation on a two-class motor-imagery classification task shows that both the proposed tandem features yield consistent gains over the AR baseline, resulting in significant relative improvement of 6.2% and 11.2% for the LDA and MLP features respectively. We also explore portability of these features across different subjects.
first_indexed 2024-03-05T19:28:52Z
format Conference or Workshop Item
id utm.eprints-50993
institution Universiti Teknologi Malaysia - ePrints
last_indexed 2024-03-05T19:28:52Z
publishDate 2013
record_format dspace
spelling utm.eprints-509932017-07-11T04:18:24Z http://eprints.utm.my/50993/ Discriminative tandem features for hmm-based EEG classification Ting, Chee-Ming King, Simon Salleh, Sh-Hussain Ariff, A. K. QH Natural history We investigate the use of discriminative feature extractors in tandem configuration with generative EEG classification system. Existing studies on dynamic EEG classification typically use hidden Markov models (HMMs) which lack discriminative capability. In this paper, a linear and a non-linear classifier are discriminatively trained to produce complementary input features to the conventional HMM system. Two sets of tandem features are derived from linear discriminant analysis (LDA) projection output and multilayer perceptron (MLP) class-posterior probability, before appended to the standard autoregressive (AR) features. Evaluation on a two-class motor-imagery classification task shows that both the proposed tandem features yield consistent gains over the AR baseline, resulting in significant relative improvement of 6.2% and 11.2% for the LDA and MLP features respectively. We also explore portability of these features across different subjects. 2013 Conference or Workshop Item PeerReviewed Ting, Chee-Ming and King, Simon and Salleh, Sh-Hussain and Ariff, A. K. (2013) Discriminative tandem features for hmm-based EEG classification. In: 2013 35TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC). http://apps.webofknowledge.com.ezproxy.utm.my/full_record.do?product=WOS&search_mode=GeneralSearch&qid=5&SID=R2bDzISyUVdV24ggHTF&page=1&doc=1
spellingShingle QH Natural history
Ting, Chee-Ming
King, Simon
Salleh, Sh-Hussain
Ariff, A. K.
Discriminative tandem features for hmm-based EEG classification
title Discriminative tandem features for hmm-based EEG classification
title_full Discriminative tandem features for hmm-based EEG classification
title_fullStr Discriminative tandem features for hmm-based EEG classification
title_full_unstemmed Discriminative tandem features for hmm-based EEG classification
title_short Discriminative tandem features for hmm-based EEG classification
title_sort discriminative tandem features for hmm based eeg classification
topic QH Natural history
work_keys_str_mv AT tingcheeming discriminativetandemfeaturesforhmmbasedeegclassification
AT kingsimon discriminativetandemfeaturesforhmmbasedeegclassification
AT sallehshhussain discriminativetandemfeaturesforhmmbasedeegclassification
AT ariffak discriminativetandemfeaturesforhmmbasedeegclassification