TY - GEN
T1 - Automatic segmentation for one leg stance test with inertial measurement unit
AU - Kong, W.
AU - Kodama, T.
AU - Sessa, S.
AU - Cosentino, S.
AU - Magistro, D.
AU - Kawashima, R.
AU - Takanishi, A.
N1 - Funding Information:
This research has been supported by the JSPS Grant-in-Aid for Young Scientists (Wakate B) [15K21437]. The present work was also supported in part by the Program for Leading Graduate Schools, Graduate Program for Embodiment Informatics of the Ministry of Education, Culture, Sports, Science and Technology.
Publisher Copyright:
© 2016 IEEE.
PY - 2017/2/6
Y1 - 2017/2/6
N2 - One Leg Stance (OLS), a test assessing postural stability, is popularly conducted both in clinic and community settings because it is inexpensive and time-efficient. However, the evaluation based on visual observation and manual time measurement with a stop-watch cannot provide quantitative and detailed parameters for longitudinal or cross-sectional studies. In recent years, to overcome these limitations, the use of Inertial Measurement Unit (IMU) as objective measurement analysis tools is becoming more and more popular. However, the greatest issue is that IMU data segmentation is still time-consuming and prone to errors, as the OLS segmentation is being done manually, off-line, on recorded data. In this paper we proposed a novel algorithm for the automatic segmentation of IMU data of the OLS test. The result showed that the correct rate of detection was over 90% which was close to the correct rate in manual segmentation. Compared to manual segmentation with video, besides being less time-consuming, the proposed algorithm closes the loop making the data acquisition and analysis completely automatic, thus can be integrated in self-assessment smart phone applications, allowing the continuous tracking of postural stability also outside clinics and health-care facilities.
AB - One Leg Stance (OLS), a test assessing postural stability, is popularly conducted both in clinic and community settings because it is inexpensive and time-efficient. However, the evaluation based on visual observation and manual time measurement with a stop-watch cannot provide quantitative and detailed parameters for longitudinal or cross-sectional studies. In recent years, to overcome these limitations, the use of Inertial Measurement Unit (IMU) as objective measurement analysis tools is becoming more and more popular. However, the greatest issue is that IMU data segmentation is still time-consuming and prone to errors, as the OLS segmentation is being done manually, off-line, on recorded data. In this paper we proposed a novel algorithm for the automatic segmentation of IMU data of the OLS test. The result showed that the correct rate of detection was over 90% which was close to the correct rate in manual segmentation. Compared to manual segmentation with video, besides being less time-consuming, the proposed algorithm closes the loop making the data acquisition and analysis completely automatic, thus can be integrated in self-assessment smart phone applications, allowing the continuous tracking of postural stability also outside clinics and health-care facilities.
UR - http://www.scopus.com/inward/record.url?scp=85015361664&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85015361664&partnerID=8YFLogxK
U2 - 10.1109/SII.2016.7844016
DO - 10.1109/SII.2016.7844016
M3 - Conference contribution
AN - SCOPUS:85015361664
T3 - SII 2016 - 2016 IEEE/SICE International Symposium on System Integration
SP - 307
EP - 312
BT - SII 2016 - 2016 IEEE/SICE International Symposium on System Integration
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2016 IEEE/SICE International Symposium on System Integration, SII 2016
Y2 - 13 December 2016 through 15 December 2016
ER -