Establishment of Identification Method of μ Rhythm in Events and Non-events by Wavelet Transform
| Autor: | Ming-yao Tsai, 蔡名堯 |
|---|---|
| Rok vydání: | 2018 |
| Druh dokumentu: | 學位論文 ; thesis |
| Popis: | 106 For patients with paraplegia or hemiplegia, this work tries to use the inhibition phenomenon of the patient''s μ rhythm activated by the motor imagery as a control switch to drive the video replay function of the mirror therapy system. By combining motor imagery with visual feedback, it is hoped that such a brain computer interface (BCI) system can more effectively recover the brain function than the traditional motor imagery system. However, to achieve this goal, we need to develop an algorithm that can accurately identify the μ rhythm activity generated during the motor imagery process. This study used the wavelet transform to compute the energy time varying patterns in different frequency bands. By processing the wavelet transform results with vector quantization method and principal component analysis method, this study develops a number of features to try to detect the motor imagery events. In specific, this study developed and tested three different classifiers. Unfortunately, we are not able to obtain satisfactory classification results. By increasing the number of electroencephalography (EEG) signal channels, improving the experimental environment and improving the degree of the involvement of the test subjects, it is hoped that future work can develop a more effective μ rhythm detection algorithm for this integrated motor imagery visual feedback system. |
| Databáze: | Networked Digital Library of Theses & Dissertations |
| Externí odkaz: |
|