Estimation of Neuromuscular Activities Using Gait Analysis and Deep Learning for Rehabilitation Purposes
Gait analysis using modern motion tracking techniques including measurement of kinematic variables is an important modality in rehabilitation research and applications. Functional electrical stimulation (FES) for patients with paralysis and cerebral diseases is one of the most important application...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | Arabic |
| Published: |
damascus university
2022-05-01
|
| Series: | مجلة جامعة دمشق للعلوم الهندسية |
| Subjects: | |
| Online Access: | http://journal.damasuniv.edu.sy/index.php/engj/article/view/4680 |
| _version_ | 1818005891200319488 |
|---|---|
| author | ابراهيم اسماعيل صالح مسعود حسام حنا |
| author_facet | ابراهيم اسماعيل صالح مسعود حسام حنا |
| author_sort | ابراهيم اسماعيل صالح مسعود حسام حنا |
| collection | DOAJ |
| description |
Gait analysis using modern motion tracking techniques including measurement of kinematic variables is an important modality in rehabilitation research and applications. Functional electrical stimulation (FES) for patients with paralysis and cerebral diseases is one of the most important applications of rehabilitation science. Efficient muscle stimulation requires a pre-knowledge about limb motility and muscles synergy. In this paper, we are working to track the angle changes of the thigh and shin during walking phases based on accelerometer and gyroscope sensors, and estimating the thigh-shin angle and its derivative using HuGaDB dataset. Those three features are used with a feedforward neural network (FNN) to determine the activity of the rectus femoris muscle by pre-training of neural network with gait analysis as input and electromyography (EMG) signal as the output of the same patient. The results illustrate the ability of FNN to reproduce EMG for each gait cycle of the same patient with average precision equal to 96% as training and 92.5% as testing. The proposed method presents a good tool for FES systems, especially for EMG encoding stages.
|
| first_indexed | 2024-04-14T04:51:38Z |
| format | Article |
| id | doaj.art-e926f250212e41bfb16ebbb9a177559a |
| institution | Directory Open Access Journal |
| issn | 1999-7302 2789-6854 |
| language | Arabic |
| last_indexed | 2024-04-14T04:51:38Z |
| publishDate | 2022-05-01 |
| publisher | damascus university |
| record_format | Article |
| series | مجلة جامعة دمشق للعلوم الهندسية |
| spelling | doaj.art-e926f250212e41bfb16ebbb9a177559a2022-12-22T02:11:16Zaradamascus universityمجلة جامعة دمشق للعلوم الهندسية1999-73022789-68542022-05-01382Estimation of Neuromuscular Activities Using Gait Analysis and Deep Learning for Rehabilitation Purposesابراهيم اسماعيل صالح مسعود حسام حنا Gait analysis using modern motion tracking techniques including measurement of kinematic variables is an important modality in rehabilitation research and applications. Functional electrical stimulation (FES) for patients with paralysis and cerebral diseases is one of the most important applications of rehabilitation science. Efficient muscle stimulation requires a pre-knowledge about limb motility and muscles synergy. In this paper, we are working to track the angle changes of the thigh and shin during walking phases based on accelerometer and gyroscope sensors, and estimating the thigh-shin angle and its derivative using HuGaDB dataset. Those three features are used with a feedforward neural network (FNN) to determine the activity of the rectus femoris muscle by pre-training of neural network with gait analysis as input and electromyography (EMG) signal as the output of the same patient. The results illustrate the ability of FNN to reproduce EMG for each gait cycle of the same patient with average precision equal to 96% as training and 92.5% as testing. The proposed method presents a good tool for FES systems, especially for EMG encoding stages. http://journal.damasuniv.edu.sy/index.php/engj/article/view/4680Gait AnalysisFeedforward neural networkElectromyography (EMG). |
| spellingShingle | ابراهيم اسماعيل صالح مسعود حسام حنا Estimation of Neuromuscular Activities Using Gait Analysis and Deep Learning for Rehabilitation Purposes مجلة جامعة دمشق للعلوم الهندسية Gait Analysis Feedforward neural network Electromyography (EMG). |
| title | Estimation of Neuromuscular Activities Using Gait Analysis and Deep Learning for Rehabilitation Purposes |
| title_full | Estimation of Neuromuscular Activities Using Gait Analysis and Deep Learning for Rehabilitation Purposes |
| title_fullStr | Estimation of Neuromuscular Activities Using Gait Analysis and Deep Learning for Rehabilitation Purposes |
| title_full_unstemmed | Estimation of Neuromuscular Activities Using Gait Analysis and Deep Learning for Rehabilitation Purposes |
| title_short | Estimation of Neuromuscular Activities Using Gait Analysis and Deep Learning for Rehabilitation Purposes |
| title_sort | estimation of neuromuscular activities using gait analysis and deep learning for rehabilitation purposes |
| topic | Gait Analysis Feedforward neural network Electromyography (EMG). |
| url | http://journal.damasuniv.edu.sy/index.php/engj/article/view/4680 |
| work_keys_str_mv | AT ạbrạhymạsmạʿylṣạlḥmsʿwdḥsạmḥnạ estimationofneuromuscularactivitiesusinggaitanalysisanddeeplearningforrehabilitationpurposes |