TY - JOUR
T1 - Shift-Adaptive Estimation of Joint Angle Using Instrumented Brace with Two Stretch Sensors Based on Gaussian Mixture Models
AU - Eguchi, Ryo
AU - Michael, Brendan
AU - Howard, Matthew
AU - Takahashi, Masaki
N1 - Funding Information:
Manuscript received February 24, 2020; accepted June 29, 2020. Date of publication July 20, 2020; date of current version July 30, 2020. This letter was recommended for publication by Associate Editor T. Watanabe and Editor Y. Choi upon evaluation of the reviewers. comments. This work was supported by in part by the JSPS KAKENHI under Grants JP16H04290 and JP19J12205 and in part by the JSPS Overseas Challenge Program for Young Researchers. (Corresponding author: Ryo Eguchi.) Ryo Eguchi is with the School of Science for Open and Environmental Systems, Graduate School of Science and Technology, Keio University, Yokohama 223-8522, Japan (e-mail: eguchi.ryo@keio.jp).
Publisher Copyright:
© 2016 IEEE.
PY - 2020/10
Y1 - 2020/10
N2 - Wearable motion sensing in daily life has attracted attention in various disciplines. Especially, stretchable strain sensors have been instrumented into garments (e.g. brace). To estimate joint motions from such sensors, previous studies have modelled relationships between the sensor strains and motion parameters via supervised/semi-supervised learning. However, typically these only model a single relationship assuming the sensor to be located at a specific point on the body. Consequently, they exhibit reduced performance when the strain-parameter relationship varies due to sensor shifts caused by long-term wearing or donning/doffing of braces. This letter presents a shift-adaptive estimation of knee joint angle. First, a brace is instrumented with two stretch sensors placed at different heights. Next, the different strain-angle relationships at varying brace shift positions are learned using Gaussian mixture models (GMMs). The system then estimates the joint angle from the sensor strains through Gaussian mixture regression using a maximum likelihood shift GMM, which is identified by referring to the two strains in a previous 1 s period. Experimental results indicated that the proposed method estimates the joint angle at multiple shift positions (0-20 mm) with higher accuracy than methods using a single model, single sensor, or referring to the present sensor strains.
AB - Wearable motion sensing in daily life has attracted attention in various disciplines. Especially, stretchable strain sensors have been instrumented into garments (e.g. brace). To estimate joint motions from such sensors, previous studies have modelled relationships between the sensor strains and motion parameters via supervised/semi-supervised learning. However, typically these only model a single relationship assuming the sensor to be located at a specific point on the body. Consequently, they exhibit reduced performance when the strain-parameter relationship varies due to sensor shifts caused by long-term wearing or donning/doffing of braces. This letter presents a shift-adaptive estimation of knee joint angle. First, a brace is instrumented with two stretch sensors placed at different heights. Next, the different strain-angle relationships at varying brace shift positions are learned using Gaussian mixture models (GMMs). The system then estimates the joint angle from the sensor strains through Gaussian mixture regression using a maximum likelihood shift GMM, which is identified by referring to the two strains in a previous 1 s period. Experimental results indicated that the proposed method estimates the joint angle at multiple shift positions (0-20 mm) with higher accuracy than methods using a single model, single sensor, or referring to the present sensor strains.
KW - Automation in life sciences: Biotechnology
KW - Gaussian mixture regression
KW - human motion sensing
KW - medical robots and systems
KW - pharmaceutical and health care
KW - wearable sensor
UR - http://www.scopus.com/inward/record.url?scp=85089304016&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85089304016&partnerID=8YFLogxK
U2 - 10.1109/LRA.2020.3010486
DO - 10.1109/LRA.2020.3010486
M3 - Article
AN - SCOPUS:85089304016
VL - 5
SP - 5881
EP - 5888
JO - IEEE Robotics and Automation Letters
JF - IEEE Robotics and Automation Letters
SN - 2377-3766
IS - 4
M1 - 9144406
ER -