Feasibility of spectral domain techniques for the classification of non-stationary signals

Extensive research is carried out in the analysis of non stationary signals. Most of the real time signals are non-stationary in nature. In most cases, these non stationary signals are of types viz defect / non defect, normal / abnormal etc. Hence analysis refers to categorising the signals. Developing a signal processing algorithm for performing the above task is a major challenge. In Machine learning, features are extracted and classifiers are used for categorizing the signals. Feature extraction can be done in time domain, frequency domain and spectral domain. In this paper, feasibility of Singular Value Decomposition (SVD), Framelet Transforms, Discrete Wavelet Transform (DWT) and Discrete Cosine Transform (DCT) for feature extraction is studied. These features are aggregated using statistical parameters, namely mean, skewness and kurtosis. These aggregated features are then fed to Back Propagation Network (BPN). Performance of Back Propagation Network is measured in terms of sensitivity, specificity and accuracy.