Classification of electroencephalogram (EEG) for lower limb movement of post stroke patients using artificial neural network (ANN)
Nowadays, many neurological conditions happen suddenly, such as stroke or spinal cord injury. This can cause chronic gait function impairment due to functional deficits in motor control. Current physiotherapy techniques such as functional electrical stimulation (FES) can be used to reconstruct some...
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English English English |
| Published: |
2020
|
| Subjects: | |
| Online Access: | http://eprints.uthm.edu.my/904/1/24p%20KHAIRUL%20AZLAN%20A.%20RAHMAN.pdf http://eprints.uthm.edu.my/904/2/KHAIRUL%20AZLAN%20A.%20RAHMAN%20COPYRIGHT%20DECLRATION.pdf http://eprints.uthm.edu.my/904/3/KHAIRUL%20AZLAN%20A.%20RAHMAN%20WATERMARK.pdf |
| _version_ | 1796868361249882112 |
|---|---|
| author | A. Rahman, Khairul Azlan |
| author_facet | A. Rahman, Khairul Azlan |
| author_sort | A. Rahman, Khairul Azlan |
| collection | UTHM |
| description | Nowadays, many neurological conditions happen suddenly, such as stroke or spinal cord injury. This can cause chronic gait function impairment due to functional deficits in motor control. Current physiotherapy techniques such as functional electrical stimulation (FES) can be used to reconstruct some skills needed for movements of daily life. However, FES system provides only a limited degree of motor function recovery and has no mechanism for reflecting a patient’s motor intentions, hence requires novel therapies. Brain-Computer Interfaces (BCI) provides the means to decode mental states and activate devices according to user intentions. However, conventional BCI cannot be used fully, due to the lack of accuracy, and need some improvement. In addition to that, the integration of BCI with lower extremity FES systems has received less attention compared to the BCI-FES systems with upper extremity. The discussion of this thesis was divided into two parts, which were the BCI part as input and the functional electrical stimulator (FES) controller part as the output for this system. For BCI part, the main processes involved are brainwave signals classification and mapping process. Here the signal has been classed will be applied to match the appropriate rehabilitation exercise. Whereas for the FES part, the signal from the mapping system will be controlled by the controller to ensure that the target knee angle is achieved to make the rehabilitation process more effective. As a conclusion, patients can be classified into two classes based on their alpha and beta signals status and these must undergone rehabilitation sessions according to their post-stroke level. So the results proved that the ANN model developed was able to classify the post-stroke severity. Also, the result had proven that the BCI fuzzy-based mapping system in this study was able to work perfectly into mapping the post-stroke patient with a suitable exercise according to their post-stroke level. |
| first_indexed | 2024-03-05T21:38:42Z |
| format | Thesis |
| id | uthm.eprints-904 |
| institution | Universiti Tun Hussein Onn Malaysia |
| language | English English English |
| last_indexed | 2024-03-05T21:38:42Z |
| publishDate | 2020 |
| record_format | dspace |
| spelling | uthm.eprints-9042021-09-09T02:13:48Z http://eprints.uthm.edu.my/904/ Classification of electroencephalogram (EEG) for lower limb movement of post stroke patients using artificial neural network (ANN) A. Rahman, Khairul Azlan RC Internal medicine QA75-76.95 Calculating machines Nowadays, many neurological conditions happen suddenly, such as stroke or spinal cord injury. This can cause chronic gait function impairment due to functional deficits in motor control. Current physiotherapy techniques such as functional electrical stimulation (FES) can be used to reconstruct some skills needed for movements of daily life. However, FES system provides only a limited degree of motor function recovery and has no mechanism for reflecting a patient’s motor intentions, hence requires novel therapies. Brain-Computer Interfaces (BCI) provides the means to decode mental states and activate devices according to user intentions. However, conventional BCI cannot be used fully, due to the lack of accuracy, and need some improvement. In addition to that, the integration of BCI with lower extremity FES systems has received less attention compared to the BCI-FES systems with upper extremity. The discussion of this thesis was divided into two parts, which were the BCI part as input and the functional electrical stimulator (FES) controller part as the output for this system. For BCI part, the main processes involved are brainwave signals classification and mapping process. Here the signal has been classed will be applied to match the appropriate rehabilitation exercise. Whereas for the FES part, the signal from the mapping system will be controlled by the controller to ensure that the target knee angle is achieved to make the rehabilitation process more effective. As a conclusion, patients can be classified into two classes based on their alpha and beta signals status and these must undergone rehabilitation sessions according to their post-stroke level. So the results proved that the ANN model developed was able to classify the post-stroke severity. Also, the result had proven that the BCI fuzzy-based mapping system in this study was able to work perfectly into mapping the post-stroke patient with a suitable exercise according to their post-stroke level. 2020-07 Thesis NonPeerReviewed text en http://eprints.uthm.edu.my/904/1/24p%20KHAIRUL%20AZLAN%20A.%20RAHMAN.pdf text en http://eprints.uthm.edu.my/904/2/KHAIRUL%20AZLAN%20A.%20RAHMAN%20COPYRIGHT%20DECLRATION.pdf text en http://eprints.uthm.edu.my/904/3/KHAIRUL%20AZLAN%20A.%20RAHMAN%20WATERMARK.pdf A. Rahman, Khairul Azlan (2020) Classification of electroencephalogram (EEG) for lower limb movement of post stroke patients using artificial neural network (ANN). Doctoral thesis, Universiti Tun Hussein Onn Malaysia. |
| spellingShingle | RC Internal medicine QA75-76.95 Calculating machines A. Rahman, Khairul Azlan Classification of electroencephalogram (EEG) for lower limb movement of post stroke patients using artificial neural network (ANN) |
| title | Classification of electroencephalogram (EEG) for lower limb movement of post stroke patients using artificial neural network (ANN) |
| title_full | Classification of electroencephalogram (EEG) for lower limb movement of post stroke patients using artificial neural network (ANN) |
| title_fullStr | Classification of electroencephalogram (EEG) for lower limb movement of post stroke patients using artificial neural network (ANN) |
| title_full_unstemmed | Classification of electroencephalogram (EEG) for lower limb movement of post stroke patients using artificial neural network (ANN) |
| title_short | Classification of electroencephalogram (EEG) for lower limb movement of post stroke patients using artificial neural network (ANN) |
| title_sort | classification of electroencephalogram eeg for lower limb movement of post stroke patients using artificial neural network ann |
| topic | RC Internal medicine QA75-76.95 Calculating machines |
| url | http://eprints.uthm.edu.my/904/1/24p%20KHAIRUL%20AZLAN%20A.%20RAHMAN.pdf http://eprints.uthm.edu.my/904/2/KHAIRUL%20AZLAN%20A.%20RAHMAN%20COPYRIGHT%20DECLRATION.pdf http://eprints.uthm.edu.my/904/3/KHAIRUL%20AZLAN%20A.%20RAHMAN%20WATERMARK.pdf |
| work_keys_str_mv | AT arahmankhairulazlan classificationofelectroencephalogrameegforlowerlimbmovementofpoststrokepatientsusingartificialneuralnetworkann |