SOS based selection and parameter optimization for underwater target classification

Abstract

The identification and classification of underwater noise sources is of utmost importance in modern underwater acoustic signal processing systems. Dynamic and complicated oceanic environment makes underwater target classification a challenging task. An underwater acoustic target classification system identifies the acoustics targets from a mixture of acoustic events through their characteristic acoustic signature. The characteristic acoustic signatures are patterned by feature recognition algorithms operating on data captured by hydrophone. In this paper, an SVM classifier distinguishes acoustic signatures of four different target types. The performance of the classifier depends on a variety of factors, of which SVM parameter tuning is very important. Several attempts have been made for automatic kernel selection and parameter optimization, including meta-heuristic algorithms such as genetic algorithms (GA) and particle swarm optimization (PSO). This paper attempts towards selection of SVM parameters, kernel and kernel parameter optimization using the Symbiotic Organisms Search (SOS) algorithm. The results indicate higher classification accuracy when compared to the commonly used PSO based selection and optimization.