【摘要】：針對基于支持向量機(SVM)的雷達(dá)輻射源信號識別方法中SVM模型參數(shù)對識別性能影響較大的問題,提出基于優(yōu)化算法的雷達(dá)輻射源信號識別方法,并選擇遺傳算法、蟻群算法和粒子群算法三種典型的優(yōu)化算法應(yīng)用于新的識別方法進(jìn)行優(yōu)化識別。通過不同條件下計算機仿真實驗,驗證了新方法的有效性,并分析了三種典型優(yōu)化算法在新方法中的綜合性能,為對雷達(dá)輻射源信號進(jìn)行更好的識別提供一定的依據(jù)。
[Abstract]:In order to solve the problem that the parameters of SVM model have great influence on the recognition performance of radar emitter signal recognition method based on support vector machine (SVM), a radar emitter signal recognition method based on optimization algorithm is proposed, and three typical optimization algorithms, genetic algorithm, ant colony algorithm and particle swarm optimization algorithm, are selected and applied to the new recognition method. The effectiveness of the new method is verified by computer simulation experiments under different conditions, and the comprehensive performance of three typical optimization algorithms in the new method is analyzed, which provides a certain basis for better recognition of radar emitter signals.
【作者單位】： 空軍預(yù)警學(xué)院研究生管理大隊;
【分類號】：TN957.51

【參考文獻(xiàn)】

相關(guān)期刊論文 前8條

1 關(guān)欣;郭強;張政超;趙靜;翟鴻君;;基于核函數(shù)支持向量機的雷達(dá)輻射源識別[J];彈箭與制導(dǎo)學(xué)報;2011年04期

2 宋小杉;蔣曉瑜;汪熙;姚軍;;基于改進(jìn)Joachims上界的SVM泛化性能評價方法[J];電子學(xué)報;2011年06期

3 韓俊;何明浩;朱振波;王杰;;基于復(fù)雜度特征的未知雷達(dá)輻射源信號分選[J];電子與信息學(xué)報;2009年11期

4 徐t，

本文編號：2521990