Fuzzy Kohonen Network for the Classification of Transients Using the Wavelet Transform for Feature Extraction

A system for identifying and classifying short duration signals (transients) is proposed. The transients are perturbed by multiplicative noise, and are embedded in various noise backgrounds to simulate an undersea environment. The transients are generated using FM chirp sum and sinusoidal sum models. The system uses wavelets as linear filters for preprocessing, and a fuzzy Kohonen neural network for classification. The design of the classifier system is presented, as well as results from initial experiments. The system is shown to be able to classify signals down to -1 dB.