Extraction subject-specific motor imagery time-frequency patterns for single trial EEG classification
PubMedID: 17010962 We introduce a new adaptive time-frequency plane feature extraction strategy for the segmentation and classification of electroencephalogram (EEG) corresponding to left and right hand motor imagery of a brain-computer interface task. The proposed algorithm adaptively segments the...
Published in: | Computers in Biology and Medicine |
---|---|
Main Authors: | , , |
Other Authors: | |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
2007
|
Subjects: | |
Online Access: | https://hdl.handle.net/20.500.12605/15090 https://doi.org/10.1016/j.compbiomed.2006.08.014 |
id |
ftcukurovauniv:oai:openaccess.cu.edu.tr:20.500.12605/15090 |
---|---|
record_format |
openpolar |
institution |
Open Polar |
collection |
Çukurova University Institutional Repository |
op_collection_id |
ftcukurovauniv |
language |
English |
topic |
Brain-computer interface Cosine packets Local discriminant bases Motor imagery Time-frequency analysis |
spellingShingle |
Brain-computer interface Cosine packets Local discriminant bases Motor imagery Time-frequency analysis Ince N.F. Tewfik A.H. Arica S. Extraction subject-specific motor imagery time-frequency patterns for single trial EEG classification |
topic_facet |
Brain-computer interface Cosine packets Local discriminant bases Motor imagery Time-frequency analysis |
description |
PubMedID: 17010962 We introduce a new adaptive time-frequency plane feature extraction strategy for the segmentation and classification of electroencephalogram (EEG) corresponding to left and right hand motor imagery of a brain-computer interface task. The proposed algorithm adaptively segments the time axis by dividing the EEG data into non-uniform time segments over a dyadic tree. This is followed by grouping the expansion coefficients in the frequency axis in each segment. The most discriminative features are selected from the segmented time-frequency plane and fed to a linear discriminant for classification. The proposed algorithm achieved an average classification accuracy of 84.3% on six subjects by selecting the most discriminant subspaces for each one. For comparison, classification results based on an autoregressive model are also presented where the mean accuracy of the same subjects turned out to be 79.5%. Interestingly the subjects and two hemispheres of each subject are represented by distinct segmentations and features. This indicates that the proposed method can handle inter-subject variability when constructing brain-computer interfaces. © 2006 Elsevier Ltd. All rights reserved. National Council for Scientific Research This project was supported by The National Scientific Research Council of Turkey (TUBITAK). Nuri F. Ince received his Ph.D. degree in Electrical and Electronics Engineering from Cukurova University, Adana, Turkey in 2005. During his Ph.D. he was supported by the National Scientific Research Council of Turkey with International Joint Ph.D. scholarship. Currently he is a Post-Doc Associate at the University of Minnesota. His research interest include neural engineering, wearable medical sensors, adaptive time frequency analysis and classification of biomedical signals. Ahmed H. Tewfik received his B.Sc. degree from Cairo University, Cairo Egypt, in 1982 and his M.Sc., E.E. and Sc.D. degrees from the Massachusetts Institute of Technology, Cambridge, MA, in 1984, 1985 and 1987 respectively. Dr. Tewfik has worked at Alphatech, Inc., Burlington, MA in 1987. He is the E. F. Johnson professor of Electronic Communications with the department of Electrical Engineering at the University of Minnesota. He served as a consultant to MTS Systems, Inc., Eden Prairie, MN and Rosemount, Inc., Eden Prairie, MN and worked with Texas Instruments and Computing Devices International. From August 1997 to August 2001, he was the President and CEO of Cognicity, Inc., an entertainment marketing software tools publisher that he co-founded, on partial leave of absence from the University of Minnesota. Prof. Tewfik is a Fellow of the IEEE. He was a Distinguished Lecturer of the IEEE Signal Processing Society in 1997–1999. He received the IEEE third Millennium award in 2000. His research interest include Genomics and bioinformatics; Brain Computer Interfaces, Analysis and Classification of EEG/MEG with adaptive time frequency bases, Wearable Medical Sensors; food inspection; programmable wireless networks; sparse signal representations and data centric computing. In the past, He made seminal contributions to low power multimedia communications, adaptive search and data acquisition strategies for world wide web applications, radar and dental/medical imaging, monitoring of machinery via acoustic emissions, industrial measurements, wavelet signal processing and fractals. Sami Arica received his Ph.D. degree in Electrical and Electronics Engineering from Cukurova University, Adana, Turkey in 1999. Currently he is a Assistant Professor at the Department of Electrical and Electronics Engineering of Cukurova University. His research interest include signal / image processing, filter banks and wavelets. |
author2 |
Çukurova Üniversitesi |
format |
Article in Journal/Newspaper |
author |
Ince N.F. Tewfik A.H. Arica S. |
author_facet |
Ince N.F. Tewfik A.H. Arica S. |
author_sort |
Ince N.F. |
title |
Extraction subject-specific motor imagery time-frequency patterns for single trial EEG classification |
title_short |
Extraction subject-specific motor imagery time-frequency patterns for single trial EEG classification |
title_full |
Extraction subject-specific motor imagery time-frequency patterns for single trial EEG classification |
title_fullStr |
Extraction subject-specific motor imagery time-frequency patterns for single trial EEG classification |
title_full_unstemmed |
Extraction subject-specific motor imagery time-frequency patterns for single trial EEG classification |
title_sort |
extraction subject-specific motor imagery time-frequency patterns for single trial eeg classification |
publishDate |
2007 |
url |
https://hdl.handle.net/20.500.12605/15090 https://doi.org/10.1016/j.compbiomed.2006.08.014 |
long_lat |
ENVELOPE(-56.015,-56.015,49.750,49.750) |
geographic |
Burlington |
geographic_facet |
Burlington |
genre |
sami |
genre_facet |
sami |
op_relation |
10.1016/j.compbiomed.2006.08.014 Computers in Biology and Medicine Makale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı 0010-4825 https://dx.doi.org/10.1016/j.compbiomed.2006.08.014 https://hdl.handle.net/20.500.12605/15090 37 4 499 508 |
op_rights |
info:eu-repo/semantics/closedAccess |
op_doi |
https://doi.org/10.1016/j.compbiomed.2006.08.014 |
container_title |
Computers in Biology and Medicine |
container_volume |
37 |
container_issue |
4 |
container_start_page |
499 |
op_container_end_page |
508 |
_version_ |
1766186914686173184 |
spelling |
ftcukurovauniv:oai:openaccess.cu.edu.tr:20.500.12605/15090 2023-05-15T18:14:11+02:00 Extraction subject-specific motor imagery time-frequency patterns for single trial EEG classification Ince N.F. Tewfik A.H. Arica S. Çukurova Üniversitesi 2007 https://hdl.handle.net/20.500.12605/15090 https://doi.org/10.1016/j.compbiomed.2006.08.014 English eng 10.1016/j.compbiomed.2006.08.014 Computers in Biology and Medicine Makale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı 0010-4825 https://dx.doi.org/10.1016/j.compbiomed.2006.08.014 https://hdl.handle.net/20.500.12605/15090 37 4 499 508 info:eu-repo/semantics/closedAccess Brain-computer interface Cosine packets Local discriminant bases Motor imagery Time-frequency analysis article 2007 ftcukurovauniv https://doi.org/10.1016/j.compbiomed.2006.08.014 2020-02-16T10:42:30Z PubMedID: 17010962 We introduce a new adaptive time-frequency plane feature extraction strategy for the segmentation and classification of electroencephalogram (EEG) corresponding to left and right hand motor imagery of a brain-computer interface task. The proposed algorithm adaptively segments the time axis by dividing the EEG data into non-uniform time segments over a dyadic tree. This is followed by grouping the expansion coefficients in the frequency axis in each segment. The most discriminative features are selected from the segmented time-frequency plane and fed to a linear discriminant for classification. The proposed algorithm achieved an average classification accuracy of 84.3% on six subjects by selecting the most discriminant subspaces for each one. For comparison, classification results based on an autoregressive model are also presented where the mean accuracy of the same subjects turned out to be 79.5%. Interestingly the subjects and two hemispheres of each subject are represented by distinct segmentations and features. This indicates that the proposed method can handle inter-subject variability when constructing brain-computer interfaces. © 2006 Elsevier Ltd. All rights reserved. National Council for Scientific Research This project was supported by The National Scientific Research Council of Turkey (TUBITAK). Nuri F. Ince received his Ph.D. degree in Electrical and Electronics Engineering from Cukurova University, Adana, Turkey in 2005. During his Ph.D. he was supported by the National Scientific Research Council of Turkey with International Joint Ph.D. scholarship. Currently he is a Post-Doc Associate at the University of Minnesota. His research interest include neural engineering, wearable medical sensors, adaptive time frequency analysis and classification of biomedical signals. Ahmed H. Tewfik received his B.Sc. degree from Cairo University, Cairo Egypt, in 1982 and his M.Sc., E.E. and Sc.D. degrees from the Massachusetts Institute of Technology, Cambridge, MA, in 1984, 1985 and 1987 respectively. Dr. Tewfik has worked at Alphatech, Inc., Burlington, MA in 1987. He is the E. F. Johnson professor of Electronic Communications with the department of Electrical Engineering at the University of Minnesota. He served as a consultant to MTS Systems, Inc., Eden Prairie, MN and Rosemount, Inc., Eden Prairie, MN and worked with Texas Instruments and Computing Devices International. From August 1997 to August 2001, he was the President and CEO of Cognicity, Inc., an entertainment marketing software tools publisher that he co-founded, on partial leave of absence from the University of Minnesota. Prof. Tewfik is a Fellow of the IEEE. He was a Distinguished Lecturer of the IEEE Signal Processing Society in 1997–1999. He received the IEEE third Millennium award in 2000. His research interest include Genomics and bioinformatics; Brain Computer Interfaces, Analysis and Classification of EEG/MEG with adaptive time frequency bases, Wearable Medical Sensors; food inspection; programmable wireless networks; sparse signal representations and data centric computing. In the past, He made seminal contributions to low power multimedia communications, adaptive search and data acquisition strategies for world wide web applications, radar and dental/medical imaging, monitoring of machinery via acoustic emissions, industrial measurements, wavelet signal processing and fractals. Sami Arica received his Ph.D. degree in Electrical and Electronics Engineering from Cukurova University, Adana, Turkey in 1999. Currently he is a Assistant Professor at the Department of Electrical and Electronics Engineering of Cukurova University. His research interest include signal / image processing, filter banks and wavelets. Article in Journal/Newspaper sami Çukurova University Institutional Repository Burlington ENVELOPE(-56.015,-56.015,49.750,49.750) Computers in Biology and Medicine 37 4 499 508 |