Abstract
This paper presents a feasibility study of a brain-machine interface system to assist repetitive facilitation exercise. Repetitive facilitation exercise is an effective rehabilitation method for patients with hemiplegia. In repetitive facilitation exercise, a therapist stimulates the paralyzed part of the patient while motor commands run along the nerve pathway. However, successful repetitive facilitation exercise is difficult to achieve and even a skilled practitioner cannot detect when a motor command occurs in patient's brain. We proposed a brain-machine interface system for automatically detecting motor commands and stimulating the paralyzed part of a patient. To determine motor commands from patient electroencephalogram (EEG) data, we constructed a support vector machine (SVM) system. In this paper, we validated that the discrimination ratio of the motor command by EEG using SVM was higher than the success rate of the repetitive facilitation exercise administered by a therapist. In the experiments, we measured the EEG when the participant bent their elbow when prompted to do so. We analyzed the EEG data using a cross-validation method. We found that the discrimination ratio for each participant was at least 69%, which is above the success rate for repetitive facilitation exercise administered by a therapist. We conclude that the EEG using SVM is useful for detecting motor commands.
| Original language | English |
|---|---|
| Title of host publication | 2017 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2017 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| Pages | 267-272 |
| Number of pages | 6 |
| Volume | 2017-July |
| ISBN (Electronic) | 9781538620342 |
| DOIs | |
| Publication status | Published - 2018 Mar 9 |
| Event | 2017 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2017 - Okinawa, Japan Duration: 2017 Jul 14 → 2017 Jul 18 |
Other
| Other | 2017 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2017 |
|---|---|
| Country | Japan |
| City | Okinawa |
| Period | 17/7/14 → 17/7/18 |
Fingerprint
ASJC Scopus subject areas
- Control and Optimization
- Artificial Intelligence
Cite this
Motor command detection for a repetitive facilitation exercise assistance system. / Miura, Satoshi; Takazawa, Junichi; Kobayashi, Yo; Fujie, Masakatsu G.
2017 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2017. Vol. 2017-July Institute of Electrical and Electronics Engineers Inc., 2018. p. 267-272.Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Motor command detection for a repetitive facilitation exercise assistance system
AU - Miura, Satoshi
AU - Takazawa, Junichi
AU - Kobayashi, Yo
AU - Fujie, Masakatsu G.
PY - 2018/3/9
Y1 - 2018/3/9
N2 - This paper presents a feasibility study of a brain-machine interface system to assist repetitive facilitation exercise. Repetitive facilitation exercise is an effective rehabilitation method for patients with hemiplegia. In repetitive facilitation exercise, a therapist stimulates the paralyzed part of the patient while motor commands run along the nerve pathway. However, successful repetitive facilitation exercise is difficult to achieve and even a skilled practitioner cannot detect when a motor command occurs in patient's brain. We proposed a brain-machine interface system for automatically detecting motor commands and stimulating the paralyzed part of a patient. To determine motor commands from patient electroencephalogram (EEG) data, we constructed a support vector machine (SVM) system. In this paper, we validated that the discrimination ratio of the motor command by EEG using SVM was higher than the success rate of the repetitive facilitation exercise administered by a therapist. In the experiments, we measured the EEG when the participant bent their elbow when prompted to do so. We analyzed the EEG data using a cross-validation method. We found that the discrimination ratio for each participant was at least 69%, which is above the success rate for repetitive facilitation exercise administered by a therapist. We conclude that the EEG using SVM is useful for detecting motor commands.
AB - This paper presents a feasibility study of a brain-machine interface system to assist repetitive facilitation exercise. Repetitive facilitation exercise is an effective rehabilitation method for patients with hemiplegia. In repetitive facilitation exercise, a therapist stimulates the paralyzed part of the patient while motor commands run along the nerve pathway. However, successful repetitive facilitation exercise is difficult to achieve and even a skilled practitioner cannot detect when a motor command occurs in patient's brain. We proposed a brain-machine interface system for automatically detecting motor commands and stimulating the paralyzed part of a patient. To determine motor commands from patient electroencephalogram (EEG) data, we constructed a support vector machine (SVM) system. In this paper, we validated that the discrimination ratio of the motor command by EEG using SVM was higher than the success rate of the repetitive facilitation exercise administered by a therapist. In the experiments, we measured the EEG when the participant bent their elbow when prompted to do so. We analyzed the EEG data using a cross-validation method. We found that the discrimination ratio for each participant was at least 69%, which is above the success rate for repetitive facilitation exercise administered by a therapist. We conclude that the EEG using SVM is useful for detecting motor commands.
UR - http://www.scopus.com/inward/record.url?scp=85050594179&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85050594179&partnerID=8YFLogxK
U2 - 10.1109/RCAR.2017.8311872
DO - 10.1109/RCAR.2017.8311872
M3 - Conference contribution
AN - SCOPUS:85050594179
VL - 2017-July
SP - 267
EP - 272
BT - 2017 IEEE International Conference on Real-Time Computing and Robotics, RCAR 2017
PB - Institute of Electrical and Electronics Engineers Inc.
ER -