Toward EEG control of upper limb power-assist exoskeletons: A preliminary study of decoding elbow joint velocities using EEG signals

Thilina Dulantha Lalitharatne, Akihiro Yoshino, Yoshikai Hayashi, Kenbu Teramoto, Kazuo Kiguchi

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

5 Citations (Scopus)

Abstract

It may not an easy task for physically weak elderly, disabled and injured individuals to perform the day to day activities in their life. Therefore, many assistive devices have been developed in order to improve the quality of life of those people in which they may not depend on others. Especially upper-limb power-assist exoskeletons have been developed since the upper limb motions are very important for the daily activities. Electromyography (EMG) signals and/or force sensor based control methods have been identified as the promising methods to control such exoskeleton devices. However, if the user cannot generate sufficient muscle signals or movements, the EMG or force sensor based methods could not be useful to the user. On the other hand, electroencephalography (EEG) signals are also important biological signals to extract the user's motion intention. In this study, the user's elbow joint motion is estimated based on the EEG signals. The measured EEG signals are pre-processed and input to a time-embedded linear model, which is assumed to decode the elbow joint angular velocities. The genetic algorithm (GA) is used to train the model. A six fold cross validation process was performed for each motion segment of each subject. The experimental results suggest that EEG signals with the tested decoding model can be used to continuously decode the elbow joint velocity.

Original languageEnglish
Title of host publication2012 International Symposium on Micro-NanoMechatronics and Human Science, MHS 2012
Pages421-424
Number of pages4
DOIs
Publication statusPublished - Dec 1 2012
Event23rd Annual Symposium on Micro-Nano Mechatronics and Human Science, MHS 2012 - Nagoya, Japan
Duration: Nov 4 2012Nov 7 2012

Publication series

Name2012 International Symposium on Micro-NanoMechatronics and Human Science, MHS 2012

Other

Other23rd Annual Symposium on Micro-Nano Mechatronics and Human Science, MHS 2012
CountryJapan
CityNagoya
Period11/4/1211/7/12

Fingerprint

Electroencephalography
Decoding
Electromyography
Sensors
Angular velocity
Muscle
Genetic algorithms

All Science Journal Classification (ASJC) codes

  • Electrical and Electronic Engineering
  • Mechanical Engineering

Cite this

Lalitharatne, T. D., Yoshino, A., Hayashi, Y., Teramoto, K., & Kiguchi, K. (2012). Toward EEG control of upper limb power-assist exoskeletons: A preliminary study of decoding elbow joint velocities using EEG signals. In 2012 International Symposium on Micro-NanoMechatronics and Human Science, MHS 2012 (pp. 421-424). [6492482] (2012 International Symposium on Micro-NanoMechatronics and Human Science, MHS 2012). https://doi.org/10.1109/MHS.2012.6492482

Toward EEG control of upper limb power-assist exoskeletons : A preliminary study of decoding elbow joint velocities using EEG signals. / Lalitharatne, Thilina Dulantha; Yoshino, Akihiro; Hayashi, Yoshikai; Teramoto, Kenbu; Kiguchi, Kazuo.

2012 International Symposium on Micro-NanoMechatronics and Human Science, MHS 2012. 2012. p. 421-424 6492482 (2012 International Symposium on Micro-NanoMechatronics and Human Science, MHS 2012).

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

Lalitharatne, TD, Yoshino, A, Hayashi, Y, Teramoto, K & Kiguchi, K 2012, Toward EEG control of upper limb power-assist exoskeletons: A preliminary study of decoding elbow joint velocities using EEG signals. in 2012 International Symposium on Micro-NanoMechatronics and Human Science, MHS 2012., 6492482, 2012 International Symposium on Micro-NanoMechatronics and Human Science, MHS 2012, pp. 421-424, 23rd Annual Symposium on Micro-Nano Mechatronics and Human Science, MHS 2012, Nagoya, Japan, 11/4/12. https://doi.org/10.1109/MHS.2012.6492482
Lalitharatne TD, Yoshino A, Hayashi Y, Teramoto K, Kiguchi K. Toward EEG control of upper limb power-assist exoskeletons: A preliminary study of decoding elbow joint velocities using EEG signals. In 2012 International Symposium on Micro-NanoMechatronics and Human Science, MHS 2012. 2012. p. 421-424. 6492482. (2012 International Symposium on Micro-NanoMechatronics and Human Science, MHS 2012). https://doi.org/10.1109/MHS.2012.6492482
Lalitharatne, Thilina Dulantha ; Yoshino, Akihiro ; Hayashi, Yoshikai ; Teramoto, Kenbu ; Kiguchi, Kazuo. / Toward EEG control of upper limb power-assist exoskeletons : A preliminary study of decoding elbow joint velocities using EEG signals. 2012 International Symposium on Micro-NanoMechatronics and Human Science, MHS 2012. 2012. pp. 421-424 (2012 International Symposium on Micro-NanoMechatronics and Human Science, MHS 2012).
@inproceedings{89e44a2a3b234bd188a16c0c51c2b9b9,
title = "Toward EEG control of upper limb power-assist exoskeletons: A preliminary study of decoding elbow joint velocities using EEG signals",
abstract = "It may not an easy task for physically weak elderly, disabled and injured individuals to perform the day to day activities in their life. Therefore, many assistive devices have been developed in order to improve the quality of life of those people in which they may not depend on others. Especially upper-limb power-assist exoskeletons have been developed since the upper limb motions are very important for the daily activities. Electromyography (EMG) signals and/or force sensor based control methods have been identified as the promising methods to control such exoskeleton devices. However, if the user cannot generate sufficient muscle signals or movements, the EMG or force sensor based methods could not be useful to the user. On the other hand, electroencephalography (EEG) signals are also important biological signals to extract the user's motion intention. In this study, the user's elbow joint motion is estimated based on the EEG signals. The measured EEG signals are pre-processed and input to a time-embedded linear model, which is assumed to decode the elbow joint angular velocities. The genetic algorithm (GA) is used to train the model. A six fold cross validation process was performed for each motion segment of each subject. The experimental results suggest that EEG signals with the tested decoding model can be used to continuously decode the elbow joint velocity.",
author = "Lalitharatne, {Thilina Dulantha} and Akihiro Yoshino and Yoshikai Hayashi and Kenbu Teramoto and Kazuo Kiguchi",
year = "2012",
month = "12",
day = "1",
doi = "10.1109/MHS.2012.6492482",
language = "English",
isbn = "9781467348126",
series = "2012 International Symposium on Micro-NanoMechatronics and Human Science, MHS 2012",
pages = "421--424",
booktitle = "2012 International Symposium on Micro-NanoMechatronics and Human Science, MHS 2012",

}

TY - GEN

T1 - Toward EEG control of upper limb power-assist exoskeletons

T2 - A preliminary study of decoding elbow joint velocities using EEG signals

AU - Lalitharatne, Thilina Dulantha

AU - Yoshino, Akihiro

AU - Hayashi, Yoshikai

AU - Teramoto, Kenbu

AU - Kiguchi, Kazuo

PY - 2012/12/1

Y1 - 2012/12/1

N2 - It may not an easy task for physically weak elderly, disabled and injured individuals to perform the day to day activities in their life. Therefore, many assistive devices have been developed in order to improve the quality of life of those people in which they may not depend on others. Especially upper-limb power-assist exoskeletons have been developed since the upper limb motions are very important for the daily activities. Electromyography (EMG) signals and/or force sensor based control methods have been identified as the promising methods to control such exoskeleton devices. However, if the user cannot generate sufficient muscle signals or movements, the EMG or force sensor based methods could not be useful to the user. On the other hand, electroencephalography (EEG) signals are also important biological signals to extract the user's motion intention. In this study, the user's elbow joint motion is estimated based on the EEG signals. The measured EEG signals are pre-processed and input to a time-embedded linear model, which is assumed to decode the elbow joint angular velocities. The genetic algorithm (GA) is used to train the model. A six fold cross validation process was performed for each motion segment of each subject. The experimental results suggest that EEG signals with the tested decoding model can be used to continuously decode the elbow joint velocity.

AB - It may not an easy task for physically weak elderly, disabled and injured individuals to perform the day to day activities in their life. Therefore, many assistive devices have been developed in order to improve the quality of life of those people in which they may not depend on others. Especially upper-limb power-assist exoskeletons have been developed since the upper limb motions are very important for the daily activities. Electromyography (EMG) signals and/or force sensor based control methods have been identified as the promising methods to control such exoskeleton devices. However, if the user cannot generate sufficient muscle signals or movements, the EMG or force sensor based methods could not be useful to the user. On the other hand, electroencephalography (EEG) signals are also important biological signals to extract the user's motion intention. In this study, the user's elbow joint motion is estimated based on the EEG signals. The measured EEG signals are pre-processed and input to a time-embedded linear model, which is assumed to decode the elbow joint angular velocities. The genetic algorithm (GA) is used to train the model. A six fold cross validation process was performed for each motion segment of each subject. The experimental results suggest that EEG signals with the tested decoding model can be used to continuously decode the elbow joint velocity.

UR - http://www.scopus.com/inward/record.url?scp=84876513122&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84876513122&partnerID=8YFLogxK

U2 - 10.1109/MHS.2012.6492482

DO - 10.1109/MHS.2012.6492482

M3 - Conference contribution

AN - SCOPUS:84876513122

SN - 9781467348126

T3 - 2012 International Symposium on Micro-NanoMechatronics and Human Science, MHS 2012

SP - 421

EP - 424

BT - 2012 International Symposium on Micro-NanoMechatronics and Human Science, MHS 2012

ER -