摘要
设计了一种用于雷达一维像识别的粒子群分类算法.新算法首先对数据样本预处理,利用粒子群优化算法通过训练数据进行分类规则的提取,根据提取得到的规则对雷达一维像进行分类识别.基于Bayes定理和随机状态转移过程对新算法的收敛性进行分析.通过对三种飞机缩比模型的实测数据的识别实验,验证了新算法对实测数据和加噪数据均具有较高的识别率.
A novel particle swarm classifier is designed for one-dimensional image recognition of radar target. After pretreating the data, the classification rules are discovered by particle swarm optimization algorithm based on the training samples, and then the one-dimensional image of radar target is recognized by the discovered rules. The convergence of the new algorithm based on Bayesrs theorem and stochastic transform process are analyzed. Experimental results on the data of three airplanes obtained in a microwave anechoic chamber show that the proposed method has a stable performance in recognizing both the one- dimensional images without noise and the one-dimensional images with noise.
出处
《光子学报》
EI
CAS
CSCD
北大核心
2007年第11期2157-2162,共6页
Acta Photonica Sinica
基金
高等学校博士学科点专项科研基金(20060699026)
航空基础科学基金(05D53021)资助
关键词
雷达一维像识别
数据分类
粒子群优化
One-dimensional image recognition of radar target
Data classification
Particle swarm optimization