1Assistant Professor, Department of Biomedical Engineering, Vels Institute of Science Technology and Advanced Studies, Chennai, India
2Student, Department of Biomedical Engineering, Vels Institute of Science Technology and Advanced Studies, Chennai, India
*Corresponding Author: A. Josephin Arockia Dhivya, Assistant Professor, Department of Biomedical Engineering, Vels Institute of Science Technology and Advanced Studies, Chennai, India, Email: a.dhivya.se@velsuniv.ac.in
Online published on 4 June, 2019.
Polysomnography test is the most commonly used test in the diagnosis of OSAS-Obstructive Sleep Apnea Syndrome and other sleep abnormalities like insomnia. PSG (polysomnography) signals consist of multiple physiological signals related to sleep and wakefulness such as subject's EEG taken from FPZ-CZ and PZ-OZ, EMG of chin, respiratory signal, EOG signal, Temp rectal signal. Insomnia is a sleep disorder in which the affected person suffers from the problems of lack of sleep, falling asleep or staying asleep for a long time. The main reasons for the insomnia in the individuals are mainly due to stress, anxiety, depression, pain or discomfort. In this project the classification of healthy and normal insomnia subjects taken from the online database (physionet) done based on spectral analysis of PSG(polysomnography) signals of subjects by applying FFT. The frequency domain features are obtained for the subjects and the obtained features are classified with the help of linear SVM and ANN classifiers.
PSG (Polysomnography), FFT (Fast Fourier Transform), SVM (Support Vector Machine), ANN (Artificial Neural Network)
