Ship radiation signal recognition method based on multi-kernel learning and discriminant analysis

Abstract

The invention discloses a ship radiation signal recognition method based on multi-kernel learning and discriminant analysis. According to the method, pretreatment, auditory sense model feature extraction, dimensionality reduction and classifier classification and judgment are sequentially conducted on a ship radiation signal sample, wherein in the stage of dimensionality reduction, a method based on multi-kernel learning and discriminant analysis is adopted, alternate optimization is utilized, and optimization operation is conducted on kernel mapping coefficients and linear multi-kernel combination coefficients respectively under the goal of kernel discriminant analysis optimization represented in a graph embedding mode. Compared with the prior art, on the aspect of ship radiation signal recognition, the recognition performance of a system can be improved effectively.

Description

technical field [0001] The invention belongs to the field of ship radiation signal recognition, in particular to a ship radiation signal recognition method based on multi-core learning discriminant analysis. Background technique [0002] The analysis of ship radiation signal is a necessary step for underwater ship target recognition through underwater acoustic signals. The ship’s radiation noise received by sonar can judge the type of ship target or even a series of targets at a relatively long distance. Specific ship parameters. Ship radiation signals come from various factors such as machinery, propellers, water flow, etc. Therefore, the analysis of ship radiation signals is a complicated task for both manual and machine. As a key step in the analysis and identification of ship radiation signals, the reduction of the characteristic dimension of ship radiation signals is of great significance for extracting features that are beneficial to identify different ships. At pres...

AI Technical Summary

Problems solved by technology

[0005] Technical problem to be solved: Aiming at the deficiencies in the prior art, the present invention proposes a ship radiation signal recognition method based on Multiple Kernel Learning (Fisher) Discriminant Analysis (MKL-FDA for short here). auditory model features, using MKL-FDA for dimensionality reduction training, to solve the existing technology, relying on expert systems and subjective experience to analyze and identify ship radiation signals, it takes a lot of manpower and can not be well analyzed. Identify obvious ship radiation signals; when using the nuclear method for identification, there is a technical problem of inaccurate selection of data nuclear mapping in the identification

Images