Automated detecting sleep apnea syndrome: A novel system based on genetic SVM

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 several bio-signals that used to detect this syndrome. The conventional approach of detecting the sleep apnea uses a manual analysis of most of bio-signals to achieve reasonable accuracy. The manual process 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 consists of three main parts which are signal segmentation, feature generation and classification based on genetic SVM. Results show efficiency of this system and its superiority versus previous methods with more bio-signals as input.