Deep radio signal clustering with interpretability analysis based on saliency map

作     者：Huaji Zhou Jing Bai Yiran Wang Junjie Ren Xiaoniu Yang Licheng Jiao 

作者机构：School of Artificial Intelligence Xidian University Science and Technology on Communication Information Security Control Laboratory 

出 版 物：《Digital Communications and Networks》 (数字通信与网络(英文))

年 卷 期：2024年第10卷第5期

页      面：1448-1458页

核心收录：

学科分类：080904[工学-电磁场与微波技术] 12[管理学] 0809[工学-电子科学与技术（可授工学、理学学位）] 08[工学] 0810[工学-信息与通信工程] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 081104[工学-模式识别与智能系统] 080402[工学-测试计量技术及仪器] 0804[工学-仪器科学与技术] 081001[工学-通信与信息系统] 0835[工学-软件工程] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：supported in part by the National Natural Science Foundation of China (No.62276206) the Key Research and Development Program of Shaanxi under Grant S2022-YF-YBGY-0921 the State Key Program of National Natural Science of China (No.62231027) supported by the Science and Technology on Communication Information Security Control Laboratory 

主　　题：Unsupervised radio signal clustering Autoencoder Clustering features visualization Deep learning interpretability 

摘      要：With the development of information technology,radio communication technology has made rapid *** radio signals that have appeared in space are difficult to classify without manually *** radio signal clustering methods have recently become an urgent need for this ***,the high complexity of deep learning makes it difficult to understand the decision results of the clustering models,making it essential to conduct interpretable *** paper proposed a combined loss function for unsupervised clustering based on *** combined loss function includes reconstruction loss and deep clustering *** clustering loss is added based on reconstruction loss,which makes similar deep features converge more in feature *** addition,a features visualization method for signal clustering was proposed to analyze the interpretability of autoencoder utilizing Saliency *** experiments have been conducted on a modulated signal dataset,and the results indicate the superior performance of our proposed method over other clustering *** particular,for the simulated dataset containing six modulation modes,when the SNR is 20dB,the clustering accuracy of the proposed method is greater than 78%.The interpretability analysis of the clustering model was performed to visualize the significant features of different modulated signals and verified the high separability of the features extracted by clustering model.