Bioelectrics
Sobhan Sheykhivand; Tohid Yousefi Rezaii; Zohreh Mousavi; Saeed Meshgini
Volume 11, Issue 4 , February 2018, , Pages 313-325
Abstract
Using an intelligent method to automatically detect sleep patterns in medical applications is one of the most important challenges in recent years to reduce the workload of physicians in analyzing sleep data through visual inspection. In this paper, a single-channel EEG-based algorithm is used to automatically ...
Read More
Using an intelligent method to automatically detect sleep patterns in medical applications is one of the most important challenges in recent years to reduce the workload of physicians in analyzing sleep data through visual inspection. In this paper, a single-channel EEG-based algorithm is used to automatically identify sleep stages using discrete wavelet transform and a hybrid model of simulated annealing and neural network. The signal is decomposed using a discrete wavelet transform into seven levels and statistical properties of each level is calculated. To optimize and reduce the dimensions of feature vectors, hybrid model of simulated annealing algorithm and multi-layered neural network are used. Then ANOVA test is applied to validate the selected features. Finally the classification is performed on the validated features by a perceptron neural network with a hidden layer, which provides an average of 90% classification ccuracy for 2 to 6-class classification of different steps of sleep EEG. Suggesting that the proposed method has higher degree of success in classifying sleep stages compared to the existing methods.