A separability and robustness based algorithm for classification of transient sonar signal using wavelet

An improved method for transient sonar signal classification is presented. In the ocean, noise exists nearly everywhere and the accuracy of classifying sonar signals is decreased to some extent. To remove the noise's negative effect, this algorithm is specially designed to extract the robust signal feature in the environment with low SNR. Additionally, the amplitude of the wavelet coefficient is always regarded as the unique standard for feature extraction. This algorithm combines the class separability criterion with the amplitude of the wavelet coefficients in order to choose both the most principal and most discriminative features of the transient sonar signals. Then the features are tested by the original DARPA data set and modified data set contaminated by a relatively strong noise with the back-propagation neural network.