Physical rehabilitation exercises assessment based on Hidden Semi-Markov Model by Kinect v2

M. Capecci; M. G. Ceravolo; F. Ferracuti; S. Iarlori; V. Kyrki; S. Longhi; L. Romeo; F. Verdini

doi:10.1109/BHI.2016.7455883

Physical rehabilitation exercises assessment based on Hidden Semi-Markov Model by Kinect v2

M. Capecci, M. G. Ceravolo, F. Ferracuti, S. Iarlori, V. Kyrki, S. Longhi, L. Romeo, F. Verdini

Marche Polytechnic University

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

23 Citations (Scopus)

Abstract

This work investigates how Hidden Semi-Markov Model (HSMM) can be used to monitor and evaluate physical rehabilitation exercises by Kinect v2 to support medical personnel and patients during rehabilitation at home. Authors developed an exercises assessment method based on the extraction of motion features determined by clinicians. Five different rehabilitation exercises are modeled using a HSMM to provide an assessment score. The scores are compared with those obtained using the Dynamic Time Warping to discriminate which, between these two methods, best correlates doctors and physiotherapists' evaluation. Results show that HSMM can be used to evaluate exercise performances and give a feedback to physiotherapists and patients about exercise execution.

Original language	English
Title of host publication	3rd IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2016
Publisher	IEEE
Pages	256-259
Number of pages	4
ISBN (Electronic)	978-1-5090-2455-1
DOIs	https://doi.org/10.1109/BHI.2016.7455883
Publication status	Published - 18 Apr 2016
MoE publication type	A4 Conference publication
Event	IEEE International Conference on Biomedical and Health Informatics - Las Vegas, United States Duration: 24 Feb 2016 → 27 Feb 2016 Conference number: 3

Conference

Conference	IEEE International Conference on Biomedical and Health Informatics
Abbreviated title	BHI
Country/Territory	United States
City	Las Vegas
Period	24/02/2016 → 27/02/2016

Access to Document

10.1109/BHI.2016.7455883

Cite this

Capecci, M., Ceravolo, M. G., Ferracuti, F., Iarlori, S., Kyrki, V., Longhi, S., Romeo, L., & Verdini, F. (2016). Physical rehabilitation exercises assessment based on Hidden Semi-Markov Model by Kinect v2. In 3rd IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2016 (pp. 256-259). Article 7455883 IEEE. https://doi.org/10.1109/BHI.2016.7455883

@inproceedings{6b76c2922d744b4a8b3aa65e40c431de,

title = "Physical rehabilitation exercises assessment based on Hidden Semi-Markov Model by Kinect v2",

abstract = "This work investigates how Hidden Semi-Markov Model (HSMM) can be used to monitor and evaluate physical rehabilitation exercises by Kinect v2 to support medical personnel and patients during rehabilitation at home. Authors developed an exercises assessment method based on the extraction of motion features determined by clinicians. Five different rehabilitation exercises are modeled using a HSMM to provide an assessment score. The scores are compared with those obtained using the Dynamic Time Warping to discriminate which, between these two methods, best correlates doctors and physiotherapists' evaluation. Results show that HSMM can be used to evaluate exercise performances and give a feedback to physiotherapists and patients about exercise execution.",

author = "M. Capecci and Ceravolo, {M. G.} and F. Ferracuti and S. Iarlori and V. Kyrki and S. Longhi and L. Romeo and F. Verdini",

year = "2016",

month = apr,

day = "18",

doi = "10.1109/BHI.2016.7455883",

language = "English",

pages = "256--259",

booktitle = "3rd IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2016",

publisher = "IEEE",

address = "United States",

note = "IEEE International Conference on Biomedical and Health Informatics, BHI ; Conference date: 24-02-2016 Through 27-02-2016",

}

Capecci, M, Ceravolo, MG, Ferracuti, F, Iarlori, S, Kyrki, V, Longhi, S, Romeo, L & Verdini, F 2016, Physical rehabilitation exercises assessment based on Hidden Semi-Markov Model by Kinect v2. in 3rd IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2016., 7455883, IEEE, pp. 256-259, IEEE International Conference on Biomedical and Health Informatics, Las Vegas, United States, 24/02/2016. https://doi.org/10.1109/BHI.2016.7455883

Physical rehabilitation exercises assessment based on Hidden Semi-Markov Model by Kinect v2. / Capecci, M.; Ceravolo, M. G.; Ferracuti, F. et al.
3rd IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2016. IEEE, 2016. p. 256-259 7455883.

Research output: Chapter in Book/Report/Conference proceeding › Conference article in proceedings › Scientific › peer-review

TY - GEN

T1 - Physical rehabilitation exercises assessment based on Hidden Semi-Markov Model by Kinect v2

AU - Capecci, M.

AU - Ceravolo, M. G.

AU - Ferracuti, F.

AU - Iarlori, S.

AU - Kyrki, V.

AU - Longhi, S.

AU - Romeo, L.

AU - Verdini, F.

N1 - Conference code: 3

PY - 2016/4/18

Y1 - 2016/4/18

N2 - This work investigates how Hidden Semi-Markov Model (HSMM) can be used to monitor and evaluate physical rehabilitation exercises by Kinect v2 to support medical personnel and patients during rehabilitation at home. Authors developed an exercises assessment method based on the extraction of motion features determined by clinicians. Five different rehabilitation exercises are modeled using a HSMM to provide an assessment score. The scores are compared with those obtained using the Dynamic Time Warping to discriminate which, between these two methods, best correlates doctors and physiotherapists' evaluation. Results show that HSMM can be used to evaluate exercise performances and give a feedback to physiotherapists and patients about exercise execution.

AB - This work investigates how Hidden Semi-Markov Model (HSMM) can be used to monitor and evaluate physical rehabilitation exercises by Kinect v2 to support medical personnel and patients during rehabilitation at home. Authors developed an exercises assessment method based on the extraction of motion features determined by clinicians. Five different rehabilitation exercises are modeled using a HSMM to provide an assessment score. The scores are compared with those obtained using the Dynamic Time Warping to discriminate which, between these two methods, best correlates doctors and physiotherapists' evaluation. Results show that HSMM can be used to evaluate exercise performances and give a feedback to physiotherapists and patients about exercise execution.

UR - http://www.scopus.com/inward/record.url?scp=84968698083&partnerID=8YFLogxK

U2 - 10.1109/BHI.2016.7455883

DO - 10.1109/BHI.2016.7455883

M3 - Conference article in proceedings

AN - SCOPUS:84968698083

SP - 256

EP - 259

BT - 3rd IEEE EMBS International Conference on Biomedical and Health Informatics, BHI 2016

PB - IEEE

T2 - IEEE International Conference on Biomedical and Health Informatics

Y2 - 24 February 2016 through 27 February 2016

ER -

Physical rehabilitation exercises assessment based on Hidden Semi-Markov Model by Kinect v2

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this