Motion Error Classification for Assisted Physical Therapy - A Novel Approach using Incremental Dynamic Time Warping and Normalised Hierarchical Skeleton Joint Data

Richter, Júlia; Wiede, Christian; Shinde, Bharat; Hirtz, Gangolf

doi:10.5220/0006108002810288

Cited by 8 publications

(20 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Studies in the literature concerned with automated evaluation of therapy motions are scarce [23][24][25][26], and not much attention has been paid to the development of metrics for performance evaluation [27]. As a common scheme, a reference model is first captured as the ground truth.…”

Section: Performance Evaluationmentioning

confidence: 99%

“…A similar approach using HMMs to assess the correctness of telerehabilitation exercises was employed in [24], whereas a cloud-based physical therapy monitoring and guidance system that applies DTW to produce subjective assessments in terms of being too slow/fast or overdone/incomplete was proposed in [25]. An error classification algorithm for therapy exercises based on incremental DTW is presented in [26] to classify the incorrect motions in a hip abduction exercise into four discrete categories: bent knee, foot outside, upper body, and wrong plane. A variance of DTW called multi-template, multimatch DTW was used in [29] to detect and evaluate physical therapy exercises using wearable motion sensors, providing a quantitative measure of similarity between an exercise execution and previously recorded templates.…”

Section: Performance Evaluationmentioning

confidence: 99%

See 1 more Smart Citation

Rehabilitation Exergames: Use of Motion Sensing and Machine Learning to Quantify Exercise Performance in Healthy Volunteers (Preprint)

Osgouei¹,

Soulsby²,

Bello³

2019

Preprint

View full text Add to dashboard Cite

BACKGROUND Performing physiotherapy exercises in front of a physiotherapist yields qualitative assessment notes and immediate feedback. However, practicing the exercises at home lacks feedback on how well or not patients are performing the prescribed tasks. The absence of proper feedback might result in patients doing the exercises incorrectly, which could worsen their condition. OBJECTIVE We propose the use of two machine learning algorithms, namely Dynamic Time Warping (DTW) and Hidden Markov Model (HMM), to quantitively assess the patient’s performance with respects to a reference. METHODS Movement data were recorded using a Kinect depth sensor, capable of detecting 25 joints in the human skeleton model, and were compared to those of a reference. 16 participants were recruited to perform four different exercises: shoulder abduction, hip abduction, lunge, and sit-to-stand. Their performance was compared to that of a physiotherapist as a reference. RESULTS Both algorithms show a similar trend in assessing participants' performance. However, their sensitivity level was different. While DTW was more sensitive to small changes, HMM captured a general view of the performance, being less sensitive to the details. CONCLUSIONS The chosen algorithms demonstrated their capacity to objectively assess physical therapy performances. HMM may be more suitable in the early stages of a physiotherapy program to capture and report general performance, whilst DTW could be used later on to focus on the detail.

show abstract

Section: Performance Evaluationmentioning

confidence: 99%

Section: Performance Evaluationmentioning

confidence: 99%

Rehabilitation Exergames: Use of Motion Sensing and Machine Learning to Quantify Exercise Performance in Healthy Volunteers (Preprint)

Osgouei¹,

Soulsby²,

Bello³

2019

Preprint

View full text Add to dashboard Cite

show abstract

“…Regarding automated assessment of therapy motions, the studies in the literature are scarce [17]- [20], and not much attention has been paid to the development of metrics for perfromance evaluation [21]. As a common scheme, a reference model is captured as the ground truth first.…”

Section: B Performance Evaluationmentioning

confidence: 99%

“…A similar approach using HMMs to assess the correctness of tele-rehabilitation exercises is employed in [18], whereas a cloud-based physical therapy monitoring and guidance system is proposed in [19], which applies DTW to produce subjective assessments in terms of being too slow/fast or overdone/incomplete. Lastly, [20] presents a method based on incremental DTW to classify the incorrectness of the user's performance for a hip abduction exercise into four discrete categories: bent knee, foot outside, upper body, and wrong plane. What is common between all these efforts is that they focused on evaluating the incorrectness of the user's performance on the basis of some subjective terms.…”

Section: B Performance Evaluationmentioning

confidence: 99%

An Objective Evaluation Method for Rehabilitation Exergames

Osgouei

Soulsbv

Bello

2018

2018 IEEE Games, Entertainment, Media Conference (GEM)

View full text Add to dashboard Cite

The aim of this work is to objectively evaluate the performance of patients using a virtual rehabilitation system called MIRA. MIRA is a software platform which converts conventional therapeutic exercises into games, enabling the user to practice the given exercise by playing a game. The system includes a motion sensor to track and capture user's movements. Our assessment of the performance quality is based on the recorded trajectories of the human skeleton joints. We employ two different machine learning approaches, dynamic time warping (DTW) and hidden Markov modeling (HMM), both widely used for gesture recognition, to compare the user's performance with that of a reference as ground truth.

show abstract

“…Studies in the literature concerned with automated evaluation of therapy motions are scarce [ 23 - 26 ], and not much attention has been paid to the development of metrics for performance evaluation [ 27 ]. As a common scheme, a reference model is first captured as the ground truth.…”

Section: Introductionmentioning

confidence: 99%

Rehabilitation Exergames: Use of Motion Sensing and Machine Learning to Quantify Exercise Performance in Healthy Volunteers

Osgouei¹,

Soulsby²,

Bello³

2020

JMIR Rehabil Assist Technol

View full text Add to dashboard Cite

Background Performing physiotherapy exercises in front of a physiotherapist yields qualitative assessment notes and immediate feedback. However, practicing the exercises at home lacks feedback on how well patients are performing the prescribed tasks. The absence of proper feedback might result in patients performing the exercises incorrectly, which could worsen their condition. We present an approach to generate performance scores to enable tracking the progress by both the patient at home and the physiotherapist in the clinic. Objective This study aims to propose the use of 2 machine learning algorithms, dynamic time warping (DTW) and hidden Markov model (HMM), to quantitatively assess the patient’s performance with respect to a reference. Methods Movement data were recorded using a motion sensor (Kinect V2), capable of detecting 25 joints in the human skeleton model, and were compared with those of a reference. A total of 16 participants were recruited to perform 4 different exercises: shoulder abduction, hip abduction, lunge, and sit-to-stand exercises. Their performance was compared with that of a physiotherapist as a reference. Results Both algorithms showed a similar trend in assessing participant performance. However, their sensitivity levels were different. Although DTW was more sensitive to small changes, HMM captured a general view of the performance, being less sensitive to the details. Conclusions The chosen algorithms demonstrated their capacity to objectively assess the performance of physical therapy. HMM may be more suitable in the early stages of a physiotherapy program to capture and report general performance, whereas DTW could be used later to focus on the details. The scores enable the patient to monitor their daily performance. They can also be reported back to the physiotherapist to track and assess patient progress, provide feedback, and adjust the exercise program if needed.

show abstract

Motion Error Classification for Assisted Physical Therapy - A Novel Approach using Incremental Dynamic Time Warping and Normalised Hierarchical Skeleton Joint Data

Cited by 8 publications

References 0 publications

Rehabilitation Exergames: Use of Motion Sensing and Machine Learning to Quantify Exercise Performance in Healthy Volunteers (Preprint)

Rehabilitation Exergames: Use of Motion Sensing and Machine Learning to Quantify Exercise Performance in Healthy Volunteers (Preprint)

An Objective Evaluation Method for Rehabilitation Exergames

Rehabilitation Exergames: Use of Motion Sensing and Machine Learning to Quantify Exercise Performance in Healthy Volunteers

Contact Info

Product

Resources

About