摘要
提出了基于最优决策理论的最佳分类器用神经网络实现的方法 ,并对通信信号的调制类型进行自动识别。这种方法以使类域最大分离为目标 ,利用神经网络良好的非线性和自适应性 ,把最优准则下的自学习功能引入训练过程 ,结合快速训练和修剪算法 ,克服了一般神经网络分类器的不足 ,实验证明其性能良好。
This paper mainly proposes an algorithm that the optimal classifier of neural networks is implemented with the optimal decision theory, and automatically classes modulation types of communication signal. The method is according to the purpose of classification, using the advantages of non - linearity and adaptiveness of neural networks, and combining with the algorithms of fast training and pruning. It overcomes the drawbacks of the general classifier of neural networks. Test shows that it has good performance.
出处
《系统工程与电子技术》
EI
CSCD
北大核心
2001年第5期44-46,共3页
Systems Engineering and Electronics
