Applying Hybrid Deep Learning Models to Assess Upper Limb Rehabilitation
Upper limb rehabilitation training is an effective method to restore and improve the upper limb motor function of stroke patients, which enables them to engage in daily life activities independently. However, traditional rehabilitation training methods have limitations such as high cost of rehabilit...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10720137/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536155428847616 |
|---|---|
| author | Sheng Miao Zitong Liu Dezhen Wang Xiang Shen Nana Shen |
| author_facet | Sheng Miao Zitong Liu Dezhen Wang Xiang Shen Nana Shen |
| author_sort | Sheng Miao |
| collection | DOAJ |
| description | Upper limb rehabilitation training is an effective method to restore and improve the upper limb motor function of stroke patients, which enables them to engage in daily life activities independently. However, traditional rehabilitation training methods have limitations such as high cost of rehabilitation equipment and imprecise assessment. Currently, Kinect is widely used to track key points of human skeleton, but Kinect is costly and requires high indoor environment, which makes it unsuitable for use in complex scenarios. In order to solve these problems, this study presents a new method that utilizes deep learning algorithms to recognize rehabilitation movements and thus evaluate rehabilitation effects. The proposed method is designed to help healthcare professionals monitor the patient’s rehabilitation progress and develop an optimal rehabilitation program for the patient. The method uses a monocular camera to capture video data from the patient’s upper limb rehabilitation training, utilizes Faster R-CNN and HRNet to recognize the human body position and upper limb bone key point information, and then builds a long short-term memory (LSTM) neural network model incorporating the ProbSparse Self-Attention mechanism to evaluate the rehabilitation training movements. The experimental results show that the accuracy of the proposed method in this study reaches 94.1%, and its overall performance is better than that of the baseline method in low-cost, high-precision and complex scenarios. |
| format | Article |
| id | doaj-art-12ad0f9180e64654917b81beb73afe0a |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-12ad0f9180e64654917b81beb73afe0a2025-01-15T00:03:40ZengIEEEIEEE Access2169-35362024-01-011215433715434810.1109/ACCESS.2024.348211510720137Applying Hybrid Deep Learning Models to Assess Upper Limb RehabilitationSheng Miao0https://orcid.org/0000-0001-6176-3624Zitong Liu1https://orcid.org/0009-0006-0288-1042Dezhen Wang2https://orcid.org/0009-0005-3449-7726Xiang Shen3https://orcid.org/0000-0002-6457-0411Nana Shen4https://orcid.org/0009-0003-1529-6430School of Information and Control Engineering, Qingdao University of Technology, Qingdao, ChinaSchool of Information and Control Engineering, Qingdao University of Technology, Qingdao, ChinaSchool of Information and Control Engineering, Qingdao University of Technology, Qingdao, ChinaDepartment of Statistic, The George Washington University, Washington, DC, USADepartment of Rehabilitation, The Affiliated Hospital of Qingdao University, Qingdao, ChinaUpper limb rehabilitation training is an effective method to restore and improve the upper limb motor function of stroke patients, which enables them to engage in daily life activities independently. However, traditional rehabilitation training methods have limitations such as high cost of rehabilitation equipment and imprecise assessment. Currently, Kinect is widely used to track key points of human skeleton, but Kinect is costly and requires high indoor environment, which makes it unsuitable for use in complex scenarios. In order to solve these problems, this study presents a new method that utilizes deep learning algorithms to recognize rehabilitation movements and thus evaluate rehabilitation effects. The proposed method is designed to help healthcare professionals monitor the patient’s rehabilitation progress and develop an optimal rehabilitation program for the patient. The method uses a monocular camera to capture video data from the patient’s upper limb rehabilitation training, utilizes Faster R-CNN and HRNet to recognize the human body position and upper limb bone key point information, and then builds a long short-term memory (LSTM) neural network model incorporating the ProbSparse Self-Attention mechanism to evaluate the rehabilitation training movements. The experimental results show that the accuracy of the proposed method in this study reaches 94.1%, and its overall performance is better than that of the baseline method in low-cost, high-precision and complex scenarios.https://ieeexplore.ieee.org/document/10720137/Upper limb functionalitydeep learninghuman action recognitionhealthcarestroke |
| spellingShingle | Sheng Miao Zitong Liu Dezhen Wang Xiang Shen Nana Shen Applying Hybrid Deep Learning Models to Assess Upper Limb Rehabilitation IEEE Access Upper limb functionality deep learning human action recognition healthcare stroke |
| title | Applying Hybrid Deep Learning Models to Assess Upper Limb Rehabilitation |
| title_full | Applying Hybrid Deep Learning Models to Assess Upper Limb Rehabilitation |
| title_fullStr | Applying Hybrid Deep Learning Models to Assess Upper Limb Rehabilitation |
| title_full_unstemmed | Applying Hybrid Deep Learning Models to Assess Upper Limb Rehabilitation |
| title_short | Applying Hybrid Deep Learning Models to Assess Upper Limb Rehabilitation |
| title_sort | applying hybrid deep learning models to assess upper limb rehabilitation |
| topic | Upper limb functionality deep learning human action recognition healthcare stroke |
| url | https://ieeexplore.ieee.org/document/10720137/ |
| work_keys_str_mv | AT shengmiao applyinghybriddeeplearningmodelstoassessupperlimbrehabilitation AT zitongliu applyinghybriddeeplearningmodelstoassessupperlimbrehabilitation AT dezhenwang applyinghybriddeeplearningmodelstoassessupperlimbrehabilitation AT xiangshen applyinghybriddeeplearningmodelstoassessupperlimbrehabilitation AT nanashen applyinghybriddeeplearningmodelstoassessupperlimbrehabilitation |