基于量子神经网络的辐射源识别方法  

A radar emitter recognition method based on quantum neural networks

作　　者：张中山[1] 贾可新 

机构地区：[1]中国电子科技集团公司第三十八研究所,安徽合肥230088

出　　处：《航天电子对抗》2013年第3期26-28,31,共4页Aerospace Electronic Warfare

摘　　要：针对传统的BP神经网络对雷达辐射源识别率不高问题,提出了基于量子神经网络的辐射源识别方法。由于量子神经网络借鉴了量子理论的量子态叠加思想,不仅保留了人工神经网络的固有优势,而且可形成特征空间的多级划分,使得分类具有更大的自由度,从而较好地对辐射源进行分类识别。实验结果表明,相比于传统BP神经网络,该方法能获得更高的雷达辐射源识别率。The conditional BP neural network has poor radar recognition rate. To solve this problem, a radar recognition algorithm based on quantum neural network is proposed. The quantum neural network adopts the superposition of the quantum theory,it not only has the advantages of BP network, but also to has more degree of freedom due to obtain the multi-lever partitions of the feature space, thus to recognize radar easily. Experimental results show that the proposed method could achieve better recognition rate than the conventional BP neural networks.

关 键 词：量子神经网络 雷达辐射源识别 多层激励函数 

分 类 号：TP183[自动化与计算机技术—控制理论与控制工程] TN974[自动化与计算机技术—控制科学与工程]