Feasibility of Recurrent Neural Network for the Binary classification of Non stationary signals

Abstract

Spectral domain techniques are best suited for the examination of signals which are non-stationary in nature. Features extracted from spectral decomposition can be represented with statistical parameters. These features are then fed to classifiers for classifying the non-stationary signals. In this work, Recurrent Neural Network is used as the classifier for labeling signals as normal or abnormal and also embedded. Bursts and saw tooth non-stationary signals are considered and the performance is studied. Also the significant parameters are identified based on sensitivity, specificity and accuracy. From the analysis, it is found that Discreet Framelet Transform (DFT) co-efficients are best suited for binary classification of burst signals while Discrete Wavelet Transform (DWT) is the best suited technique for saw tooth non-stationary signals. This methods can be used for the non-stationary signals like ECG, speech signals etc.