This study uses flow rate and blood oxygen saturation signals to detect apnea and hypopnea events. The detection process consist two phases, by using the peaks of flow rate signals to determine respiratory cycles, the first phase uses seven flow rate feature to distinguish normal and abnormal respiratory events. To reduce the false detection rate, by appending two additional blood oxygen saturation variables into the feature set, the second phase tries to filter out some falsely detected events made in the first phase. Experimental results show that the proposed approach achieves detection accuracy is 81%. The corresponding false detection rate is 67%. One reason for the high false detection rate is that many normal respiratory events has lower amplitude airflow pattern. To resolve such a difficulty, additional physiological signals may be required.
Identifer | oai:union.ndltd.org:NSYSU/oai:NSYSU:etd-0718108-143429 |
Date | 18 July 2008 |
Creators | Huang, Ren-tsung |
Contributors | Yu, Ming-Huei, Yen,Chen-Wen, Pei-Chung Chen |
Publisher | NSYSU |
Source Sets | NSYSU Electronic Thesis and Dissertation Archive |
Language | Cholon |
Detected Language | English |
Type | text |
Format | application/pdf |
Source | http://etd.lib.nsysu.edu.tw/ETD-db/ETD-search/view_etd?URN=etd-0718108-143429 |
Rights | unrestricted, Copyright information available at source archive |
Page generated in 0.0018 seconds