Segmentation of exercise repetitions enabling real-time patient analysis and feedback using a single exemplar

Sarsfield, J ORCID logoORCID: https://orcid.org/0000-0003-0146-9102, Brown, D ORCID logoORCID: https://orcid.org/0000-0002-1677-7485, Sherkat, N ORCID logoORCID: https://orcid.org/0000-0003-1488-5682, Langensiepen, C ORCID logoORCID: https://orcid.org/0000-0002-0165-9048, Lewis, J ORCID logoORCID: https://orcid.org/0000-0002-2788-5043, Taheri, M ORCID logoORCID: https://orcid.org/0000-0001-7594-4530, Selwood, L, Standen, P and Logan, P, 2019. Segmentation of exercise repetitions enabling real-time patient analysis and feedback using a single exemplar. IEEE Transactions on Neural Systems and Rehabilitation Engineering, 27 (5), pp. 1004-1019. ISSN 1558-0210

[thumbnail of 13563_Sarsfield.PDF]
Preview
Text
13563_Sarsfield.PDF - Post-print

Download (3MB) | Preview

Abstract

We present a segmentation algorithm capable of segmenting exercise repetitions in real-time. This approach uses subsequence dynamic time warping and requires only a single exemplar repetition of an exercise to correctly segment repetitions from other subjects, including those with limited mobility. This approach is invariant to low range of motion, instability in movements and sensor noise while remaining selective to different exercises. This algorithm enables responsive feedback for technology-assisted physical rehabilitation systems. We evaluated the algorithm against a publicly available dataset (CMU) and against a healthy population and stroke patient population performing rehabilitation exercises captured on a consumer-level depth sensor. We show the algorithm can consistently achieve correct segmentation in real-time.

Item Type: Journal article
Publication Title: IEEE Transactions on Neural Systems and Rehabilitation Engineering
Creators: Sarsfield, J., Brown, D., Sherkat, N., Langensiepen, C., Lewis, J., Taheri, M., Selwood, L., Standen, P. and Logan, P.
Publisher: Institute of Electrical and Electronics Engineers
Date: May 2019
Volume: 27
Number: 5
ISSN: 1558-0210
Identifiers:
Number
Type
10.1109/TNSRE.2019.2907483
DOI
913704
Other
Divisions: Schools > School of Science and Technology
Record created by: Jonathan Gallacher
Date Added: 12 Apr 2019 12:30
Last Modified: 28 Sep 2021 10:55
URI: https://irep.ntu.ac.uk/id/eprint/36241

Actions (login required)

Edit View Edit View

Statistics

Views

Views per month over past year

Downloads

Downloads per month over past year