2022_A Framework of Finger Progress Prediction for Virtual Fine Motor Stroke Rehabilitation
| Format: | General Document |
|---|
| _version_ | 1860798144443318272 |
|---|---|
| building | INTELEK Repository |
| collection | Online Access |
| collectionurl | https://intelek.unisza.edu.my/intelek/pages/search.php?search=!collection3 |
| copyright | Copyright©PWB2025 |
| country | Malaysia |
| date | 2022-08-08 |
| format | General Document |
| id | 16163 |
| institution | UniSZA |
| originalfilename | A FRAMEWORK OF FINGER PROGRESS PREDICTION FOR VIRTUAL FINE MOTOR STROKE REHABILITATION (PHD_2022).pdf |
| person | Mohd Amir Idzham Bin Iberahim |
| recordtype | oai_dc |
| resourceurl | https://intelek.unisza.edu.my/intelek/pages/view.php?ref=16163 |
| sourcemedia | Server storage Scanned document |
| spelling | 16163 https://intelek.unisza.edu.my/intelek/pages/view.php?ref=16163 https://intelek.unisza.edu.my/intelek/pages/search.php?search=!collection3 General Document Malaysia Library Staff (Top Management) Library Staff (Management) Library Staff (Support) Terengganu Faculty of Informatics & Computing English application/pdf 1.5 Server storage Scanned document Universiti Sultan Zainal Abidin UniSZA Private Access UNIVERSITI SULTAN ZAINAL ABIDIN SAMBox 2.3.4; modified using iTextSharp™ 5.5.10 ©2000-2016 iText Group NV (AGPL-version) Copyright©PWB2025 2022-08-08 253 A FRAMEWORK OF FINGER PROGRESS PREDICTION FOR VIRTUAL FINE MOTOR STROKE REHABILITATION (PHD_2022).pdf Stroke rehabilitation Mohd Amir Idzham Bin Iberahim 2022_A Framework of Finger Progress Prediction for Virtual Fine Motor Stroke Rehabilitation Early upper limb and fine motor rehabilitation are critical for stroke patients to return to normal daily activities. A VR solution for stroke therapy might induce motion sickness, cognitive burden, and affect accessibility and acceptability for therapeutic groups like the elderly, and also most VR equipment is quite costly. On the other hand, medical and technology experts do not collaborate, machine learning prediction analysis for stroke progression might be ineffective. Therefore, this study aims to contribute on the prediction model for fine motor stroke rehabilitation by using markerless VR technology. The research methodology involved three phases. First, proposing a framework consists of three models; capturing finger movement by using a time-based simplified Denavit Heartenberg (TSDH) model, the finger state progress(FSP) model for measuring finger movement progress, and the enhancement of the FSP(E-FSP) model for producing a new dataset and evaluated with selected regression classifiers. Second, the development of a markerless VR prototype (VRFirst) with the ADDIE model. Then, experiments and data collection were performed. A total of 30 patients from the rehabilitation center who undergo a series of VR exercises were sampled and interviewed. The final process involved regression classifier analysis by comparing their Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) values. The results of the analysis involving the patient were validated by the therapist at the rehabilitation center. Results show that the RandomForest classifier without feature selection had the lowest MAE (8.26) and RMSE (12.38) for the new dataset. The result of the patient’s perspective was very positive and the post-study system usability questionnaire (PSSUQ) for the therapist achieved a high satisfaction-based mean of 1.737. Since to date, there are no published studies of regression with the lowest MAE and RMSE for the markerless VR with kinematic implementation for fine motor prediction model in stroke rehabilitation. Overall, this study has contributed a predictive framework containing TSDH, FSP, and E-FSP models and developed a VR rehabilitation application that serves as an effective technique for capturing finger movement and finger progress prediction during the markerless VR fine motor stroke rehabilitation sessions. Dissertations, Academic Finger Movement Prediction Virtual Stroke Therapy Fine Motor Rehabilitation Thesis |
| spellingShingle | 2022_A Framework of Finger Progress Prediction for Virtual Fine Motor Stroke Rehabilitation |
| state | Terengganu |
| subject | Stroke rehabilitation Dissertations, Academic |
| summary | Early upper limb and fine motor rehabilitation are critical for stroke patients to return to normal daily activities. A VR solution for stroke therapy might induce motion sickness, cognitive burden, and affect accessibility and acceptability for therapeutic groups like the elderly, and also most VR equipment is quite costly. On the other hand, medical and technology experts do not collaborate, machine learning prediction analysis for stroke progression might be ineffective. Therefore, this study aims to contribute on the prediction model for fine motor stroke rehabilitation by using markerless VR technology. The research methodology involved three phases. First, proposing a framework consists of three models; capturing finger movement by using a time-based simplified Denavit Heartenberg (TSDH) model, the finger state progress(FSP) model for measuring finger movement progress, and the enhancement of the FSP(E-FSP) model for producing a new dataset and evaluated with selected regression classifiers. Second, the development of a markerless VR prototype (VRFirst) with the ADDIE model. Then, experiments and data collection were performed. A total of 30 patients from the rehabilitation center who undergo a series of VR exercises were sampled and interviewed. The final process involved regression classifier analysis by comparing their Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) values. The results of the analysis involving the patient were validated by the therapist at the rehabilitation center. Results show that the RandomForest classifier without feature selection had the lowest MAE (8.26) and RMSE (12.38) for the new dataset. The result of the patient’s perspective was very positive and the post-study system usability questionnaire (PSSUQ) for the therapist achieved a high satisfaction-based mean of 1.737. Since to date, there are no published studies of regression with the lowest MAE and RMSE for the markerless VR with kinematic implementation for fine motor prediction model in stroke rehabilitation. Overall, this study has contributed a predictive framework containing TSDH, FSP, and E-FSP models and developed a VR rehabilitation application that serves as an effective technique for capturing finger movement and finger progress prediction during the markerless VR fine motor stroke rehabilitation sessions. |
| title | 2022_A Framework of Finger Progress Prediction for Virtual Fine Motor Stroke Rehabilitation |
| title_full | 2022_A Framework of Finger Progress Prediction for Virtual Fine Motor Stroke Rehabilitation |
| title_fullStr | 2022_A Framework of Finger Progress Prediction for Virtual Fine Motor Stroke Rehabilitation |
| title_full_unstemmed | 2022_A Framework of Finger Progress Prediction for Virtual Fine Motor Stroke Rehabilitation |
| title_short | 2022_A Framework of Finger Progress Prediction for Virtual Fine Motor Stroke Rehabilitation |
| title_sort | 2022_a framework of finger progress prediction for virtual fine motor stroke rehabilitation |