基于深度神经网络的干扰知识库构建与识别方法

Construction and Identification Method of Interference Knowledge Base Based on Deep Neural Network

随着各类无线终端数量的增加与不同无线网络的跨域融合,使得网络中的同频与外在干扰变得异常严峻。为了改善通信传输质量、抑制复杂干扰对无线终端通信质量的影响,文章针对复杂电磁环境下存在多种类型干扰信号导致实时通信质量和效率较差问题,提出了一种基于深度神经网络的干扰知识库构建与识别方法。仿真结果表明,该方法的识别准确率优于传统决策树识别方法 8%左右。

With the increase in the number of various types of wireless terminals and the cross-domain integration of different wireless networks,the co-channel and external interference in networks have become exceptionally severe.In order to improve the communication transmission quality and suppress the influence of complex interference on the communication quality of wireless terminals,this paper proposes a construction and identification method of interference knowledge base based on Deep Neural Network for the problem of poor real-time communication quality and efficiency due to the existence of multiple types of interference signals in complex electromagnetic environments.The simulation results show that the correct recognition rate of the proposed method is better in terms of 8%than that of the traditional decision tree algorithm.