Alternate feature optimization for 3-class underwater target recognition based on SVM classifiers

A novel signal processing method based on alternate feature optimization is introduced and analyzed in this paper. And a new underwater target recognition system using the optimized feature and SVM (support vector machine) is presented here. The system utilizes the alternate feature extraction method to optimize the feature selection process. The optimized feature set feeds a 3-class classification module, which is based on the traditional binary SVM classifier. The optimized feature set reduces the burden of the SVM classifier and improves its learning speed and classification accuracy. The paper includes, the algorithm of alternate feature optimization, the classification mechanism of SVM and the simulation studies. The result indicates that the proposed system has excellent performance.