Sleep Apnea Syndrome Recognition Using GreyART Network

Autor: Che-Yuan Hu, 胡哲源
Rok vydání: 2008
Druh dokumentu: 學位論文 ; thesis
Popis: 96
This thesis uses GreyART network to recognize the EEG signal of sleep apnea syndrome. Seventeen out of eighteen records from MIT/BIH Polysomnographic Database are used to examine the recognition ability of GreyART network. The data applied to GreyART network are preprocessed by order 4 wavelet transform. Among those seventeen records, record slp01b could attain the recognition accuracy of 93.33%, which is the best one. Moreover, the corresponding training phase and test phase accuracy is 95.80% and 92.12%, respectively. Besides, the average recognition accuracy of seventeen records is 78.10%, which was better than previous researches.
Databáze: Networked Digital Library of Theses & Dissertations