Graph Convolutional Networks for Assessment of Physical Rehabilitation Exercises
Health professionals often prescribe patients to perform specific exercises for rehabilitation of several diseases (e.g., stroke, Parkinson, backpain). When patients perform those exercises in the absence of an expert (e.g., physicians/therapists), they cannot assess the correctness of the performan...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2022-01-01
|
| Series: | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9709340/ |
| _version_ | 1797805126529843200 |
|---|---|
| author | Swakshar Deb Md Fokhrul Islam Shafin Rahman Sejuti Rahman |
| author_facet | Swakshar Deb Md Fokhrul Islam Shafin Rahman Sejuti Rahman |
| author_sort | Swakshar Deb |
| collection | DOAJ |
| description | Health professionals often prescribe patients to perform specific exercises for rehabilitation of several diseases (e.g., stroke, Parkinson, backpain). When patients perform those exercises in the absence of an expert (e.g., physicians/therapists), they cannot assess the correctness of the performance. Automatic assessment of physical rehabilitation exercises aims to assign a quality score given an RGBD video of the body movement as input. Recent deep learning approaches address this problem by extracting CNN features from co-ordinate grids of skeleton data (body-joints) obtained from videos. However, they could not extract rich spatio-temporal features from variable-length inputs. To address this issue, we investigate Graph Convolutional Networks (GCNs) for this task. We adapt spatio-temporal GCN to predict continuous scores(assessment) instead of discrete class labels. Our model can process variable-length inputs so that users can perform any number of repetitions of the prescribed exercise. Moreover, our novel design also provides self-attention of body-joints, indicating their role in predicting assessment scores. It guides the user to achieve a better score in future trials by matching the same attention weights of expert users. Our model successfully outperforms existing exercise assessment methods on KIMORE and UI-PRMD datasets. |
| first_indexed | 2024-03-13T05:47:22Z |
| format | Article |
| id | doaj.art-f5ac461d723b44f5bfc6202ffc07652f |
| institution | Directory Open Access Journal |
| issn | 1558-0210 |
| language | English |
| last_indexed | 2024-03-13T05:47:22Z |
| publishDate | 2022-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Transactions on Neural Systems and Rehabilitation Engineering |
| spelling | doaj.art-f5ac461d723b44f5bfc6202ffc07652f2023-06-13T20:09:01ZengIEEEIEEE Transactions on Neural Systems and Rehabilitation Engineering1558-02102022-01-013041041910.1109/TNSRE.2022.31503929709340Graph Convolutional Networks for Assessment of Physical Rehabilitation ExercisesSwakshar Deb0Md Fokhrul Islam1https://orcid.org/0000-0002-0031-4937Shafin Rahman2https://orcid.org/0000-0001-7169-0318Sejuti Rahman3https://orcid.org/0000-0001-6226-2434Department of Robotics and Mechatronics Engineering, University of Dhaka, Dhaka, BangladeshDepartment of Robotics and Mechatronics Engineering, University of Dhaka, Dhaka, BangladeshDepartment of Electrical and Computer Engineering, North South University, Dhaka, BangladeshDepartment of Robotics and Mechatronics Engineering, University of Dhaka, Dhaka, BangladeshHealth professionals often prescribe patients to perform specific exercises for rehabilitation of several diseases (e.g., stroke, Parkinson, backpain). When patients perform those exercises in the absence of an expert (e.g., physicians/therapists), they cannot assess the correctness of the performance. Automatic assessment of physical rehabilitation exercises aims to assign a quality score given an RGBD video of the body movement as input. Recent deep learning approaches address this problem by extracting CNN features from co-ordinate grids of skeleton data (body-joints) obtained from videos. However, they could not extract rich spatio-temporal features from variable-length inputs. To address this issue, we investigate Graph Convolutional Networks (GCNs) for this task. We adapt spatio-temporal GCN to predict continuous scores(assessment) instead of discrete class labels. Our model can process variable-length inputs so that users can perform any number of repetitions of the prescribed exercise. Moreover, our novel design also provides self-attention of body-joints, indicating their role in predicting assessment scores. It guides the user to achieve a better score in future trials by matching the same attention weights of expert users. Our model successfully outperforms existing exercise assessment methods on KIMORE and UI-PRMD datasets.https://ieeexplore.ieee.org/document/9709340/Automated assessmentdynamically changing attentiongraph convolution networkperformance metricsphysical rehabilitation |
| spellingShingle | Swakshar Deb Md Fokhrul Islam Shafin Rahman Sejuti Rahman Graph Convolutional Networks for Assessment of Physical Rehabilitation Exercises IEEE Transactions on Neural Systems and Rehabilitation Engineering Automated assessment dynamically changing attention graph convolution network performance metrics physical rehabilitation |
| title | Graph Convolutional Networks for Assessment of Physical Rehabilitation Exercises |
| title_full | Graph Convolutional Networks for Assessment of Physical Rehabilitation Exercises |
| title_fullStr | Graph Convolutional Networks for Assessment of Physical Rehabilitation Exercises |
| title_full_unstemmed | Graph Convolutional Networks for Assessment of Physical Rehabilitation Exercises |
| title_short | Graph Convolutional Networks for Assessment of Physical Rehabilitation Exercises |
| title_sort | graph convolutional networks for assessment of physical rehabilitation exercises |
| topic | Automated assessment dynamically changing attention graph convolution network performance metrics physical rehabilitation |
| url | https://ieeexplore.ieee.org/document/9709340/ |
| work_keys_str_mv | AT swakshardeb graphconvolutionalnetworksforassessmentofphysicalrehabilitationexercises AT mdfokhrulislam graphconvolutionalnetworksforassessmentofphysicalrehabilitationexercises AT shafinrahman graphconvolutionalnetworksforassessmentofphysicalrehabilitationexercises AT sejutirahman graphconvolutionalnetworksforassessmentofphysicalrehabilitationexercises |