Signal classification using wavelets

There has been an explosion of interest in the study and application of wavelets during the last decade. In this paper we consider the wavelet transform of a square integrable function f(x). This representation of f(x) can be depicted visually by a plot where the x-axis is the translate v, the y-axis the resolution level j, and the z-axis the amplitude of the corresponding wavelet coefficients. This plot is (in some respects) analogous to the spectrogram, where f(x) is represented by trigonometric basis functions. The wavelet transform instead moves f(x) to the scale domain where wavelets are the basis functions. In this paper we focus on the use of wavelets for classification. That is, the allocation of f(x), typically represented by a discretely sampled signal, to a fixed number of predetermined classes