Issue |
ITM Web Conf.
Volume 70, 2025
2024 2nd International Conference on Data Science, Advanced Algorithm and Intelligent Computing (DAI 2024)
|
|
---|---|---|
Article Number | 02024 | |
Number of page(s) | 7 | |
Section | Machine Learning in Healthcare and Finance | |
DOI | https://doi.org/10.1051/itmconf/20257002024 | |
Published online | 23 January 2025 |
Advancements of Deep Learning Model-Based Rehabilitation Training System
Electronic Information Science and Technology, Wenzhou University, 325035 Wenzhou, China
Corresponding author: 21211710234@stu.wzu.edu.cn
Traditional therapies for rehabilitation training in modern society are difficult to track patients dynamically, so this paper introduces a rehabilitation training evaluation system under deep learning modeling to help assess the effectiveness of rehabilitation training. In this paper, one of the studies proposed the concept of posture-guided matching based on paired Siamese Convolutional Neural Networks (SCNN), abbreviated as ST-AMCNN, on a dataset of the traditional Chinese rehabilitation training Baduanjin. Another study classified the output layers of shoulder pain rehabilitation using IMU sensors with multiple training programs for different patients wearing IMUs. IMU sensors for rehabilitation training that requires some time to analyze data and feedback data, there are more efficient studies that promote finger movement by giving patients robotic gloves to wear and propose a hand rehabilitation system thus helping stroke survivors with active rehabilitation. In addition, it was suggested to use a Smart Movement and Rehabilitation Monitoring System (SMRMS) to focus more on the participants’ training precision and recuperation. The experimental results show that there is still room for the development of rehabilitation training assessment systems in terms of privacy, interpretation ability, and application scenarios, and that researchers can address the above issues by using federated learning, developing an expert system, and using transfer learning domain adaptation, respectively.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.