Extraction of Desirable Perceptual Domain Properties Improved by the Whale Optimization Algorithm to Detect Underwater Acoustic Targets

It is important to use underwater acoustic signals received by hydrophones to communicate between vessels and to model sonar systems. This modeling is to receive input data as a single feature with a minimum number. The purpose of this paper is to derive the optimal characteristics of Mel frequency frequency coefficient coefficients (MFCC) without reducing the detection accuracy for the application of sonar signal detection. Due to the fact that the number of features is very effective in the complexity of the classifier, in this paper, in order to reduce the number of features, the Coherent Wall Optimization (WOA) algorithm will be used. The probabilistic neural network (PNN) is used as a classifier to evaluate the extracted features. In this regard, the results of the proposed algorithm will be compared with conventional and dynamic MFCC methods. The simulation results show that the number of MFCC features is reduced from 13 per frame to 5, without reducing the classifier accuracy.