Detecting voluntary gait intention of chronic stroke patients towards top-down gait rehabilitation using EEG

Junhyuk Choi, Hyolim Kang, Sang Hun Chung, Yeonghun Kim, Ung Hee Lee, Jong Min Lee, Seung-Jong Kim, Min Ho Chun, Hyungmin Kim

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

One of the recent trends in gait rehabilitation is to incorporate bio-signals, such as electromyography (EMG) or electroencephalography (EEG), for facilitating neuroplasticity, i.e. top-down approach. In this study, we investigated decoding stroke patients' gait intention through a wireless EEG system. To overcome patient-specific EEG patterns due to impaired cerebral cortices, common spatial patterns (CSP) was employed. We demonstrated that CSP filter can be used to maximize the EEG signal variance-ratio of gait and standing conditions. Finally, linear discriminant analysis (LDA) classification was conducted, whereby the average accuracy of 73.2% and the average delay of 0.13 s were achieved for 3 chronic stroke patients. Additionally, we also found out that the inverse CSP matrix topography of stroke patients' EEG showed good agreement with the patients' paretic side.

Original languageEnglish
Title of host publication2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1560-1563
Number of pages4
ISBN (Electronic)9781457702204
DOIs
Publication statusPublished - 2016 Oct 13
Externally publishedYes
Event38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016 - Orlando, United States
Duration: 2016 Aug 162016 Aug 20

Publication series

NameProceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS
Volume2016-October
ISSN (Print)1557-170X

Conference

Conference38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016
CountryUnited States
CityOrlando
Period16/8/1616/8/20

Fingerprint

Electroencephalography
Gait
Patient rehabilitation
Rehabilitation
Stroke
Electromyography
Neuronal Plasticity
Discriminant Analysis
Discriminant analysis
Cerebral Cortex
Topography
Decoding

ASJC Scopus subject areas

  • Signal Processing
  • Biomedical Engineering
  • Computer Vision and Pattern Recognition
  • Health Informatics

Cite this

Choi, J., Kang, H., Chung, S. H., Kim, Y., Lee, U. H., Lee, J. M., ... Kim, H. (2016). Detecting voluntary gait intention of chronic stroke patients towards top-down gait rehabilitation using EEG. In 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016 (pp. 1560-1563). [7591009] (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS; Vol. 2016-October). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EMBC.2016.7591009

Detecting voluntary gait intention of chronic stroke patients towards top-down gait rehabilitation using EEG. / Choi, Junhyuk; Kang, Hyolim; Chung, Sang Hun; Kim, Yeonghun; Lee, Ung Hee; Lee, Jong Min; Kim, Seung-Jong; Chun, Min Ho; Kim, Hyungmin.

2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 1560-1563 7591009 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS; Vol. 2016-October).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Choi, J, Kang, H, Chung, SH, Kim, Y, Lee, UH, Lee, JM, Kim, S-J, Chun, MH & Kim, H 2016, Detecting voluntary gait intention of chronic stroke patients towards top-down gait rehabilitation using EEG. in 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016., 7591009, Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS, vol. 2016-October, Institute of Electrical and Electronics Engineers Inc., pp. 1560-1563, 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016, Orlando, United States, 16/8/16. https://doi.org/10.1109/EMBC.2016.7591009
Choi J, Kang H, Chung SH, Kim Y, Lee UH, Lee JM et al. Detecting voluntary gait intention of chronic stroke patients towards top-down gait rehabilitation using EEG. In 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 1560-1563. 7591009. (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS). https://doi.org/10.1109/EMBC.2016.7591009
Choi, Junhyuk ; Kang, Hyolim ; Chung, Sang Hun ; Kim, Yeonghun ; Lee, Ung Hee ; Lee, Jong Min ; Kim, Seung-Jong ; Chun, Min Ho ; Kim, Hyungmin. / Detecting voluntary gait intention of chronic stroke patients towards top-down gait rehabilitation using EEG. 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 1560-1563 (Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS).
@inproceedings{41d89f5bae454fabaf1b6307ed29be21,
title = "Detecting voluntary gait intention of chronic stroke patients towards top-down gait rehabilitation using EEG",
abstract = "One of the recent trends in gait rehabilitation is to incorporate bio-signals, such as electromyography (EMG) or electroencephalography (EEG), for facilitating neuroplasticity, i.e. top-down approach. In this study, we investigated decoding stroke patients' gait intention through a wireless EEG system. To overcome patient-specific EEG patterns due to impaired cerebral cortices, common spatial patterns (CSP) was employed. We demonstrated that CSP filter can be used to maximize the EEG signal variance-ratio of gait and standing conditions. Finally, linear discriminant analysis (LDA) classification was conducted, whereby the average accuracy of 73.2{\%} and the average delay of 0.13 s were achieved for 3 chronic stroke patients. Additionally, we also found out that the inverse CSP matrix topography of stroke patients' EEG showed good agreement with the patients' paretic side.",
author = "Junhyuk Choi and Hyolim Kang and Chung, {Sang Hun} and Yeonghun Kim and Lee, {Ung Hee} and Lee, {Jong Min} and Seung-Jong Kim and Chun, {Min Ho} and Hyungmin Kim",
year = "2016",
month = "10",
day = "13",
doi = "10.1109/EMBC.2016.7591009",
language = "English",
series = "Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "1560--1563",
booktitle = "2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016",

}

TY - GEN

T1 - Detecting voluntary gait intention of chronic stroke patients towards top-down gait rehabilitation using EEG

AU - Choi, Junhyuk

AU - Kang, Hyolim

AU - Chung, Sang Hun

AU - Kim, Yeonghun

AU - Lee, Ung Hee

AU - Lee, Jong Min

AU - Kim, Seung-Jong

AU - Chun, Min Ho

AU - Kim, Hyungmin

PY - 2016/10/13

Y1 - 2016/10/13

N2 - One of the recent trends in gait rehabilitation is to incorporate bio-signals, such as electromyography (EMG) or electroencephalography (EEG), for facilitating neuroplasticity, i.e. top-down approach. In this study, we investigated decoding stroke patients' gait intention through a wireless EEG system. To overcome patient-specific EEG patterns due to impaired cerebral cortices, common spatial patterns (CSP) was employed. We demonstrated that CSP filter can be used to maximize the EEG signal variance-ratio of gait and standing conditions. Finally, linear discriminant analysis (LDA) classification was conducted, whereby the average accuracy of 73.2% and the average delay of 0.13 s were achieved for 3 chronic stroke patients. Additionally, we also found out that the inverse CSP matrix topography of stroke patients' EEG showed good agreement with the patients' paretic side.

AB - One of the recent trends in gait rehabilitation is to incorporate bio-signals, such as electromyography (EMG) or electroencephalography (EEG), for facilitating neuroplasticity, i.e. top-down approach. In this study, we investigated decoding stroke patients' gait intention through a wireless EEG system. To overcome patient-specific EEG patterns due to impaired cerebral cortices, common spatial patterns (CSP) was employed. We demonstrated that CSP filter can be used to maximize the EEG signal variance-ratio of gait and standing conditions. Finally, linear discriminant analysis (LDA) classification was conducted, whereby the average accuracy of 73.2% and the average delay of 0.13 s were achieved for 3 chronic stroke patients. Additionally, we also found out that the inverse CSP matrix topography of stroke patients' EEG showed good agreement with the patients' paretic side.

UR - http://www.scopus.com/inward/record.url?scp=85009110681&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85009110681&partnerID=8YFLogxK

U2 - 10.1109/EMBC.2016.7591009

DO - 10.1109/EMBC.2016.7591009

M3 - Conference contribution

C2 - 28268625

AN - SCOPUS:85009110681

T3 - Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS

SP - 1560

EP - 1563

BT - 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBC 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -