基于复杂度的通信辐射源目标识别方法  

Method for target recognition of communication radiation source based on complexity

作　　者：陈小惠[1] 彭杰[1] 薛毓楠 Chen Xiaohui;Peng Jie;Xue Yi'nan(School of Automation and Artificial Intelligence,Nanjing University of Posts and Telecommunications,Nanjing 210000,China)

机构地区：[1]南京邮电大学自动化院人工智能学院,南京210000

出　　处：《国外电子测量技术》2021年第5期22-26,共5页Foreign Electronic Measurement Technology

摘　　要：针对现在通信辐射源个体识别方法的特征难以提取、计算复杂及识别率低等问题。提出了一种基于复杂度的通信辐射源目标识别方法。首先信号进行奇异值分解(SVD)降噪处理,从熵值和分形维数两个复杂度方向分析细微信号所带来的变化,通过对比分析选择了样本熵、排列熵和盒维数作为特征参数;然后使用云自适应粒子群(CAPSO)的算法,优化极限学习机的阈值和连接权值,提高神经网络的分类预测精度,完成了辐射源个体的识别。仿真结果表明该方法在较低的信噪比环境下的识别率高达95%以上。It is difficult to extract the features,complicated to calculate and low recognition rate of individual identification methods of communication radiation sources.A method for target recognition of communication emitter based on complexity is proposed.Firstly,the signals were de-noised by singular value decomposition(SVD),and the changes caused by the subtle signals were analyzed from the two complexity directions of entropy and fractal dimension.The sample entropy,permutation entropy and box dimension were selected as characteristic parameters through comparative analysis.Then,the cloud adaptive particle swarm optimization(CAPSO)algorithm was used to optimize the threshold and connection weights of the extreme learning machine,improve the classification and prediction accuracy of the neural network,and complete the identification of individual radiation sources.The simulation results show that the recognition rate of this method is more than 95%in low SNR environment.

关 键 词：通信辐射源 复杂度 云粒子群优化极限学习机 识别率 

分 类 号：TN27[电子电信—物理电子学]