Nonstationary Signal Classification Using Pseudo Power Signatures

This paper deals with the problem of classiication of non-stationary signals using signatures which are essentially independent of the signal length. We develop the notion of a separable approximation to the Continuous Wavelet Transform (CW T) and use it to deene a power signature. We present a simple technique which uses the Singular Value Decomposition (SV D) to compute such an approximation, and demonstrate through an example how it is used to perform the classiication process. This example serves to show both the eeectiveness and the limitations of the approach. Our main result is an alternate approach which develops the idea of using orthogonal projections to reene the approximation process, thus allowing for the deenition of better signatures.