A novel particle swarm optimization trained support vector machine for automatic sense-through-foliage target recognition system

Detection and recognition of targets that are embedded in foliage is of interest to both military and civilian research. Due to multipath propagation effects of rough surfaces, scattering from trees and ground tend to overwhelm the weak backscattering of targets, which makes it more difficult for sense through foliage target detection and recognition. In this paper, a novel intelligent recognition model based on support vector machine (SVM) and novel particle swarm optimization for sense through foliage targets recognition is proposed. SVM is a powerful novel tool for solving the recognition problem with small sampling, nonlinearity and high dimension. A new adaptive chaos particle swarm optimization (ACPSO) is developed in this study to determine the optimal parameters for SVM with the highest accuracy and generalization ability. Moreover, the measured real target echo signals are processed using sparse representation. Principal component analysis (PCA) is performed to extract the features of targets. Then, a hybrid feature selection is used to remove the redundant and irrelevant information of the features. The computational results on different real measurement datasets validate the effectiveness of the proposed approach.