抄録
Recently, brain-computer interfaces, combined with feedback systems and goal-oriented training, have been investigated for their capacity to promote functional recovery after stroke. Accordingly, we developed a brain-computer interface-triggered robotic hand orthosis that assists hand-closing and hand-opening for post-stroke patients without sufficient motor output. In this system, near-infrared spectroscopy is used to monitor the affected motor cortex, and a linear discriminant analysis-based binary classifier estimates hand posture. The estimated posture then wirelessly triggers the robotic hand orthosis. For better performance of the brain-computer interface, we tested feature windows of different lengths and varying feature vector compositions with motor execution data from seven neurologically intact participants. The interaction between a feature window and a delay in the hemodynamic response significantly affected both classification accuracy (Matthew Correlation Coefficient) and detection latency. The 'preserving channels' feature vector was able to increase accuracy by 13.14% and decrease latency by 29.48%, relative to averaging. Oxyhemoglobin combined with deoxyhemoglobin improved accuracy by 3.71% and decreased latency by 6.01% relative to oxyhemoglobin alone. Thus, the best classification performance resulted in an accuracy of 0.7154 and a latency of 2.8515 s. The hand rehabilitation system was successfully implemented using this feature vector composition, which yielded better classification performance.
元の言語 | 英語 |
---|---|
記事番号 | 3845 |
ジャーナル | Applied Sciences (Switzerland) |
巻 | 9 |
発行部数 | 18 |
DOI | |
出版物ステータス | 出版済み - 9 1 2019 |
Fingerprint
All Science Journal Classification (ASJC) codes
- Materials Science(all)
- Instrumentation
- Engineering(all)
- Process Chemistry and Technology
- Computer Science Applications
- Fluid Flow and Transfer Processes
これを引用
Comparison of feature vector compositions to enhance the performance of NIRS-BCI-triggered robotic hand orthosis for post-stroke motor recovery. / Lee, Jongseung; Mukae, Nobutaka; Arata, Jumpei; Iihara, Koji; Hashizume, Makoto.
:: Applied Sciences (Switzerland), 巻 9, 番号 18, 3845, 01.09.2019.研究成果: ジャーナルへの寄稿 › 記事
}
TY - JOUR
T1 - Comparison of feature vector compositions to enhance the performance of NIRS-BCI-triggered robotic hand orthosis for post-stroke motor recovery
AU - Lee, Jongseung
AU - Mukae, Nobutaka
AU - Arata, Jumpei
AU - Iihara, Koji
AU - Hashizume, Makoto
PY - 2019/9/1
Y1 - 2019/9/1
N2 - Recently, brain-computer interfaces, combined with feedback systems and goal-oriented training, have been investigated for their capacity to promote functional recovery after stroke. Accordingly, we developed a brain-computer interface-triggered robotic hand orthosis that assists hand-closing and hand-opening for post-stroke patients without sufficient motor output. In this system, near-infrared spectroscopy is used to monitor the affected motor cortex, and a linear discriminant analysis-based binary classifier estimates hand posture. The estimated posture then wirelessly triggers the robotic hand orthosis. For better performance of the brain-computer interface, we tested feature windows of different lengths and varying feature vector compositions with motor execution data from seven neurologically intact participants. The interaction between a feature window and a delay in the hemodynamic response significantly affected both classification accuracy (Matthew Correlation Coefficient) and detection latency. The 'preserving channels' feature vector was able to increase accuracy by 13.14% and decrease latency by 29.48%, relative to averaging. Oxyhemoglobin combined with deoxyhemoglobin improved accuracy by 3.71% and decreased latency by 6.01% relative to oxyhemoglobin alone. Thus, the best classification performance resulted in an accuracy of 0.7154 and a latency of 2.8515 s. The hand rehabilitation system was successfully implemented using this feature vector composition, which yielded better classification performance.
AB - Recently, brain-computer interfaces, combined with feedback systems and goal-oriented training, have been investigated for their capacity to promote functional recovery after stroke. Accordingly, we developed a brain-computer interface-triggered robotic hand orthosis that assists hand-closing and hand-opening for post-stroke patients without sufficient motor output. In this system, near-infrared spectroscopy is used to monitor the affected motor cortex, and a linear discriminant analysis-based binary classifier estimates hand posture. The estimated posture then wirelessly triggers the robotic hand orthosis. For better performance of the brain-computer interface, we tested feature windows of different lengths and varying feature vector compositions with motor execution data from seven neurologically intact participants. The interaction between a feature window and a delay in the hemodynamic response significantly affected both classification accuracy (Matthew Correlation Coefficient) and detection latency. The 'preserving channels' feature vector was able to increase accuracy by 13.14% and decrease latency by 29.48%, relative to averaging. Oxyhemoglobin combined with deoxyhemoglobin improved accuracy by 3.71% and decreased latency by 6.01% relative to oxyhemoglobin alone. Thus, the best classification performance resulted in an accuracy of 0.7154 and a latency of 2.8515 s. The hand rehabilitation system was successfully implemented using this feature vector composition, which yielded better classification performance.
UR - http://www.scopus.com/inward/record.url?scp=85072405239&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85072405239&partnerID=8YFLogxK
U2 - 10.3390/app9183845
DO - 10.3390/app9183845
M3 - Article
AN - SCOPUS:85072405239
VL - 9
JO - Applied Sciences (Switzerland)
JF - Applied Sciences (Switzerland)
SN - 2076-3417
IS - 18
M1 - 3845
ER -