一种基于证据理论和神经网络的调制分类器

文章提出了一种基于证据理论和神经网络的调制信号分类方法。利用4种不同的神经网络分类器对常用的10种调制信号的同一组特征分别进行训练、分类;利用证据理论对它们的分类结果(决策)进行融合;最后,把融合结果作为调制信号的最终分类结果。实验结果与性能比较表明,该方法是有效的,获得了较高的识别率。

Classifier of Modulation Types Based on Evidence Theory and Neural Networks

A classification method of modulation signals based on the combination of neural networks with evidence theory is proposed.Firstly,four different artificial neural networks(ANNs) classifiers are used to train and classify the same set of characteristic parameters of ten modulation signals,respectively.Secondly,the four classification outputs of ANNs are fused with evidence theory.Finally,the fused result is considered as the classification result of modulation signals.Experimental results show that this method is very effective,and the classification accuracy is greatly improved compared with the single ANNs classifier.