Design of a real time portable low-cost multi-channel surface electromyography system to aid neuromuscular disorder and post stroke rehabilitation patients
| Autor: | Vinay Chandrasekhar, Madhav Rao, Vikas Vazhayil |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Wrist Joint
0209 industrial biotechnology Computer science medicine.medical_treatment 0206 medical engineering 02 engineering and technology Electromyography Wrist Upper Extremity 020901 industrial engineering & automation medicine Humans Computer vision Muscle fibre Multi channel Rehabilitation medicine.diagnostic_test business.industry Stroke Rehabilitation Motor impairment Neuromuscular Diseases 020601 biomedical engineering medicine.anatomical_structure Post stroke rehabilitation Upper limb Artificial intelligence business |
| Zdroj: | EMBC |
| ISSN: | 2694-0604 |
| Popis: | Surface and needle-based electromyography signals are used as diagnostic markers for detecting neuromuscular disorders. Existing systems that are used to acquire these signals are usually expensive and invasive in practice. A novel 8 channel surface EMG (sEMG) acquisition system is designed and developed to acquire signals for various upper limb movements in order to evaluate the motor impairment. The real time sEMG signals are generated from the muscle fibre movements, originated solely from the upper limb physical actions. Intuitively, sEMG signals characterize different actions performed by the upper limb, which is considered apt for assessing the improvement for post stroke patients undergoing routine physical therapy activities. The system is designed and assembled in a view to make it affordable and modular for easier proliferation, and extendable to motor classifying applications. The system was validated by recording realtime sEMG data using six differential electrodes for various finger and wrist actions. The signals are filtered and processed to develop a machine learning (ML) model to classify upper limb actions, and other electronic systems are designed in the portable form around the patch electrodes. A classifier was trained to predict each action and the accuracy of the classifier was assessed across different usage of channels. The accuracy of the classifier was improved by optimizing the number of electrodes as well as the spatial position of these electrodes. The sEMG circuit designed has the capacity to characterize wrists, and finger movements. The improvement observed in the sEMG signals should benefit the physiotherapists to plan further protocols in the prescribed rehabilitation program. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|