Date of Publication :20th February 2018

Abstract: This paper is based on the analysis of various soft computing techniques for the diagnosis of sleep disorders especially sleep apnea, insomnia, parasomnia and snoring on the basis of following three performance parameters: accuracy, sensitivity and specificity. Many techniques and methods are adopted by researchers to implement and diagnose these sleep disorders. The current traditional technique used to diagnose these sleep disorders is polysomnography which is costly and requires human specialists and done in unique labs. Subsequently, there is a need of a more comfortable and less expensive technique to detect such types of disorders. As of late analysts concentrated on signal processing and pattern recognition as substitute modes to reveal them. The following research is focused on the detection of sleep disorders using ECG signals by applying Tunable Q-Factor wavelet transform (TQWT) and accuracy achieved by this method is 94.2%.

Reference :