Real-time monitoring of lower limb movement resistance based on deep learning
Real-time lower limb movement resistance monitoring is critical for various applications in clinical and sports settings, such as rehabilitation and athletic training. Current methods often face limitations in accuracy, computational efficiency, and generalizability, which hinder their practical imp...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-01-01
|
| Series: | Alexandria Engineering Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S1110016824010457 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841524937366437888 |
|---|---|
| author | Burenbatu Yuanmeng Liu Tianyi Lyu |
| author_facet | Burenbatu Yuanmeng Liu Tianyi Lyu |
| author_sort | Burenbatu |
| collection | DOAJ |
| description | Real-time lower limb movement resistance monitoring is critical for various applications in clinical and sports settings, such as rehabilitation and athletic training. Current methods often face limitations in accuracy, computational efficiency, and generalizability, which hinder their practical implementation. To address these challenges, we propose a novel Mobile Multi-Task Learning Network (MMTL-Net) that integrates MobileNetV3 for efficient feature extraction and employs multi-task learning to simultaneously predict resistance levels and recognize activities. The advantages of MMTL-Net include enhanced accuracy, reduced latency, and improved computational efficiency, making it highly suitable for real-time applications. Experimental results demonstrate that MMTL-Net significantly outperforms existing models on the UCI Human Activity Recognition and Wireless Sensor Data Mining Activity Prediction datasets, achieving a lower Force Error Rate (FER) of 6.8% and a higher Resistance Prediction Accuracy (RPA) of 91.2%. Additionally, the model shows a Real-time Responsiveness (RTR) of 12 ms and a Throughput (TP) of 33 frames per second. These findings underscore the model’s robustness and effectiveness in diverse real-world scenarios. The proposed framework not only advances the state-of-the-art in resistance monitoring but also paves the way for more efficient and accurate systems in clinical and sports applications. In real-world settings, the practical implications of MMTL-Net include its potential to enhance patient outcomes in rehabilitation and improve athletic performance through precise, real-time monitoring and feedback. |
| format | Article |
| id | doaj-art-e6b3ec6bcd3045ac9772691da430534d |
| institution | Kabale University |
| issn | 1110-0168 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Alexandria Engineering Journal |
| spelling | doaj-art-e6b3ec6bcd3045ac9772691da430534d2025-01-18T05:03:31ZengElsevierAlexandria Engineering Journal1110-01682025-01-01111136147Real-time monitoring of lower limb movement resistance based on deep learning Burenbatu0Yuanmeng Liu1Tianyi Lyu2School of Physical Education, Inner Mongolia Normal University, 010022, Hohhot, ChinaSchool of Physical Education, Qujing Normal University, 655011, Qujing, China; Corresponding author.Granite Telecommunications LLC, 02171, Quincy, United StatesReal-time lower limb movement resistance monitoring is critical for various applications in clinical and sports settings, such as rehabilitation and athletic training. Current methods often face limitations in accuracy, computational efficiency, and generalizability, which hinder their practical implementation. To address these challenges, we propose a novel Mobile Multi-Task Learning Network (MMTL-Net) that integrates MobileNetV3 for efficient feature extraction and employs multi-task learning to simultaneously predict resistance levels and recognize activities. The advantages of MMTL-Net include enhanced accuracy, reduced latency, and improved computational efficiency, making it highly suitable for real-time applications. Experimental results demonstrate that MMTL-Net significantly outperforms existing models on the UCI Human Activity Recognition and Wireless Sensor Data Mining Activity Prediction datasets, achieving a lower Force Error Rate (FER) of 6.8% and a higher Resistance Prediction Accuracy (RPA) of 91.2%. Additionally, the model shows a Real-time Responsiveness (RTR) of 12 ms and a Throughput (TP) of 33 frames per second. These findings underscore the model’s robustness and effectiveness in diverse real-world scenarios. The proposed framework not only advances the state-of-the-art in resistance monitoring but also paves the way for more efficient and accurate systems in clinical and sports applications. In real-world settings, the practical implications of MMTL-Net include its potential to enhance patient outcomes in rehabilitation and improve athletic performance through precise, real-time monitoring and feedback.http://www.sciencedirect.com/science/article/pii/S1110016824010457Real-time monitoringLower limb movement resistanceMobileNetV3Multi-task learning (MTL)Resistance predictionActivity recognition |
| spellingShingle | Burenbatu Yuanmeng Liu Tianyi Lyu Real-time monitoring of lower limb movement resistance based on deep learning Alexandria Engineering Journal Real-time monitoring Lower limb movement resistance MobileNetV3 Multi-task learning (MTL) Resistance prediction Activity recognition |
| title | Real-time monitoring of lower limb movement resistance based on deep learning |
| title_full | Real-time monitoring of lower limb movement resistance based on deep learning |
| title_fullStr | Real-time monitoring of lower limb movement resistance based on deep learning |
| title_full_unstemmed | Real-time monitoring of lower limb movement resistance based on deep learning |
| title_short | Real-time monitoring of lower limb movement resistance based on deep learning |
| title_sort | real time monitoring of lower limb movement resistance based on deep learning |
| topic | Real-time monitoring Lower limb movement resistance MobileNetV3 Multi-task learning (MTL) Resistance prediction Activity recognition |
| url | http://www.sciencedirect.com/science/article/pii/S1110016824010457 |
| work_keys_str_mv | AT burenbatu realtimemonitoringoflowerlimbmovementresistancebasedondeeplearning AT yuanmengliu realtimemonitoringoflowerlimbmovementresistancebasedondeeplearning AT tianyilyu realtimemonitoringoflowerlimbmovementresistancebasedondeeplearning |