Automated detecting and classifying of sleep apnea syndrome based on genetic-SVM

Authors:
Yashar Maali;Adel Al-Jumaily
Affiliations:
Faculty of Engineering and IT, University of Technology Sydney UTS, Sydney, Australia;Faculty of Engineering and IT, University of Technology Sydney UTS, Sydney, Australia
Venue:
International Journal of Hybrid Intelligent Systems
Year:
2012

Citing 6
Cited 0

An expert system based on Wavelet Neural Network-Adaptive Norm Entropy for scale invariant texture classification

Expert Systems with Applications: An International Journal
Spoken language classification using hybrid classifier combination

International Journal of Hybrid Intelligent Systems
Incorporating prior knowledge in support vector machines for classification: A review

Neurocomputing
Fuzzy reasoning used to detect apneic events in the sleep apnea-hypopnea syndrome

Expert Systems with Applications: An International Journal
A new intelligent diagnosis system for the heart valve diseases by using genetic-SVM classifier

Expert Systems with Applications: An International Journal
An amplitude signal based technique for hypopneas detection

ASC '07 Proceedings of The Eleventh IASTED International Conference on Artificial Intelligence and Soft Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

Sleep apnea SA is one of the common sleep disorders. It has several consequences that can affect daily life activities. The common diagnose procedure is carried out through an overnight sleep test. The test usually includes of several bio-signals recordings that are used to detect this syndrome. The conventional approach of detecting the sleep apnea uses a manual analysis of most bio-signals to achieve reasonable accuracy. The manual process of this test, is highly cost and time consuming. This paper presents a novel automatic system for detecting and classifying apnea events by using just a few of bio-signals that are related to breathe defect. This method uses only the air flow, thoracic and abdominal respiratory movement as inputs for the system. The proposed technique consists of four main parts which are; signal segmentation, feature generation, feature selection and data reduction based on genetic SVM, and classification. Statistical analyzes on the attained results show efficiency of this system and its superiority versus previous methods even with more bio-signals as input.