Advanced Hybrid Information Processing. Second EAI International Conference, ADHIP 2018, Yiyang, China, October 5-6, 2018, Proceedings

Research Article

Modulation Recognition Technology of Communication Signals Based on Density Clustering and Sample Reconstruction

Download
82 downloads
  • @INPROCEEDINGS{10.1007/978-3-030-19086-6_53,
        author={Hui Han and Xianglong Zhou and Xiang Chen and Ruowu Wu and Yun Lin},
        title={Modulation Recognition Technology of Communication Signals Based on Density Clustering and Sample Reconstruction},
        proceedings={Advanced Hybrid Information Processing. Second EAI International Conference, ADHIP 2018, Yiyang, China, October 5-6, 2018, Proceedings},
        proceedings_a={ADHIP},
        year={2019},
        month={5},
        keywords={Modulation recognition Entropy features Density clustering Restructure SVM},
        doi={10.1007/978-3-030-19086-6_53}
    }
    
  • Hui Han
    Xianglong Zhou
    Xiang Chen
    Ruowu Wu
    Yun Lin
    Year: 2019
    Modulation Recognition Technology of Communication Signals Based on Density Clustering and Sample Reconstruction
    ADHIP
    Springer
    DOI: 10.1007/978-3-030-19086-6_53
Hui Han1, Xianglong Zhou2, Xiang Chen1, Ruowu Wu1, Yun Lin2,*
  • 1: State Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System (CEMEE)
  • 2: Harbin Engineering University
*Contact email: linyun_phd@hrbeu.edu.cn

Abstract

Modulation recognition is an important part in the field of communication signal processing. In recent years, with the development of modulation recognition technology, various problems have emerged. In this title, we propose an improved recognition framework based on SVM, which extracts the entropy feature of the signal and distinguishes it from the traditional modulation recognition framework. We combine the training set with the test set first, then carry on the density clustering to the whole data set. The data set after the cluster is extracted according to a certain proportion to build a new training set, and the new training set is used to train the SVM. Finally, the data of the test set is modulated by the modulation recognition. Experimental results show that the proposed method improves the recognition rate of traditional SVM framework and enhances the stability of traditional SVM framework.