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

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.

[1]  Tim Johansson,et al.  Telerehabilitation in stroke care – a systematic review , 2011, Journal of telemedicine and telecare.

[2]  S. Chiba,et al.  Dynamic programming algorithm optimization for spoken word recognition , 1978 .

[3]  Min-Chun Hu,et al.  Real-Time Human Movement Retrieval and Assessment With Kinect Sensor , 2015, IEEE Transactions on Cybernetics.

[4]  Zhe Zhang,et al.  A Fuzzy Kernel Motion Classifier for Autonomous Stroke Rehabilitation , 2016, IEEE Journal of Biomedical and Health Informatics.

[5]  S. McEwen,et al.  Exercise-enhanced neuroplasticity targeting motor and cognitive circuitry in Parkinson's disease , 2013, The Lancet Neurology.

[6]  Shunzheng Yu,et al.  Hidden semi-Markov models , 2010, Artif. Intell..

[7]  Alex Mihailidis,et al.  A Survey on Ambient-Assisted Living Tools for Older Adults , 2013, IEEE Journal of Biomedical and Health Informatics.

[8]  Majid Sarrafzadeh,et al.  Using Pressure Map Sequences for Recognition of On Bed Rehabilitation Exercises , 2014, IEEE Journal of Biomedical and Health Informatics.

[9]  Jonathan Feng-Shun Lin,et al.  Online Segmentation of Human Motion for Automated Rehabilitation Exercise Analysis , 2014, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[10]  Marjorie Skubic,et al.  Fall Detection in Homes of Older Adults Using the Microsoft Kinect , 2015, IEEE Journal of Biomedical and Health Informatics.

[11]  Biing-Hwang Juang,et al.  Fundamentals of speech recognition , 1993, Prentice Hall signal processing series.

[12]  Shunzheng Yu,et al.  Practical implementation of an efficient forward-backward algorithm for an explicit-duration hidden Markov model , 2006, IEEE Transactions on Signal Processing.

[13]  Darwin G. Caldwell,et al.  Encoding the time and space constraints of a task in explicit-duration Hidden Markov Model , 2011, 2011 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[14]  Svetha Venkatesh,et al.  Activity recognition and abnormality detection with the switching hidden semi-Markov model , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[15]  Meinard Müller,et al.  Information retrieval for music and motion , 2007 .

[16]  Ning Li,et al.  Action recognition using weighted three-state Hidden Markov Model , 2008, 2008 9th International Conference on Signal Processing.

[17]  Chuan-Jun Su,et al.  Kinect-enabled home-based rehabilitation system using Dynamic Time Warping and fuzzy logic , 2014, Appl. Soft Comput..

[18]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.