Airborne multifunctional radar working mode identification method based on improved K-nearest neighbor

Abstract

The invention discloses an airborne multifunctional radar working mode identification method based on improved K-nearest neighbor. The method comprises the steps of acquiring a data set of multifunctional radar signals in a composite scene; preprocessing the data set to obtain multi-dimensional feature representation of each sample in the data set; performing one-bit coding on each sample to obtain a sample label; further obtaining a label sample set, and then randomly selecting to form a training set and a test set; according to the inter-class boundary, effectively rejecting samples with fuzzy boundaries in the training set by using a 1-NN algorithm to obtain a target training set; then carrying out PCA principal component contribution rate analysis, reducing the influence of redundant features on classification recognition, and obtaining a target training set after dimension reduction; repeatedly training a preset k-nearest neighbor algorithm model, and determining an optimal value of k; and using the test set to test the k-nearest neighbor algorithm model determining k as of the optimal value for identification. The method can reduce the classification and identification time, and has good robustness and generalization.

Description

technical field [0001] The invention belongs to the technical field of electronic warfare signal processing, and in particular relates to an airborne multifunctional radar working mode recognition method based on improved K-nearest neighbors. Background technique [0002] With the continuous development and innovation of equipment technology, in today's electromagnetic environment, a single-system radar can no longer meet the operational needs in complex environments. Therefore, multi-functional radars have become more and more important and their applications are becoming more and more extensive. In electronic warfare, what kind of working mode the multi-function radar is currently in and what kind of combat intention it will have at the next moment play an important role in electronic intelligence reconnaissance, electronic support and threat warning systems. Traditional classification and identification methods rely on For the parameter extraction of radar signals, manual...

AI Technical Summary

Problems solved by technology

Chen You and others proposed a particle swarm optimization algorithm to adaptively optimize the DPNN network, and use the trained

Images