Automated Detecting Sleep Apnea Syndrome: A Novel System Based on Genetic SVM

Publisher:
IEEE
Publication Type:
Conference Proceeding
Citation:
11th International Conference on Hybrid Intelligent Systems, 2011, pp. 590 - 594
Issue Date:
2011-01
Full metadata record
Files in This Item:
Filename Description Size
Thumbnail2011001319OK.pdf Published version762.29 kB
Adobe PDF
Sleep Apnea (SA) is one of the common symptoms and important part of sleep disorders. It has consequences that affect all daily life activities and present danger to the patient and/or others. The common diagnose procedure is based on an overnight sleep test. The test is usually including recording of serveral bio-signals that used to detect this syndrome. The conventional apprach of detecting the sleep apnea uses a manual analysis of most of bio-signals to achieve reasonable accuracy. The manual prcess is highly cost and time consuming. This paper presents a novel automatic system for detecting Apnea events by using just few of bio-signals that are related to breathe defect. This work use only, Air flow, thoracic and abdominal respiratory movement as inputs for the system. The proposed technique consist of three main parts which are signal segmnetation, feature generation and classification based on genetic SVM. Results show efficiency of this system as its superiority versus previous methods with more bio-signals as input.
Please use this identifier to cite or link to this item: