A Non Parametric Estimation Based Underwater Target Classifier

Underwater noise sources constitute a prominent class of input signal in most underwater signalprocessing systems. The problem of identification of noise sources in the ocean is of greatimportance because of its numerous practical applications. In this paper, a methodology ispresented for the detection and identification of underwater targets and noise sources based onnon parametric indicators. The proposed system utilizes Cepstral coefficient analysis and theKruskal-Wallis H statistic along with other statistical indicators like F-test statistic for the effectivedetection and classification of noise sources in the ocean. Simulation results for typicalunderwater noise data and the set of identified underwater targets are also presented in thispaper.