Open AccessCommunication signal classification and recognition method based on GA-LSSVM classifier
Author(s) -
Qingyu Meng,
Xiaoming Chen,
Yulin Zhu,
Dayong Hu,
Rui Li,
YongTiao Jiang
Publication year - 2019
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/1345/2/022066
Subject(s) - classifier (uml) , pattern recognition (psychology) , support vector machine , quadratic classifier , artificial intelligence , computer science , margin classifier , machine learning
In order to recognize signals more efficiently and accurately, this paper proposes a method of communication signal classification and recognition based on GA-LSSVM classifier. Firstly, GA algorithm is used to optimize the penalty factor and kernel function parameters of the two main parameters in the model of support vector machine classifier. By constructing a GA-LSSVM classifier for wireless communication signals, combining with the characteristic parameters of modulated signals, the signals are identified and simulated under different SNR conditions, and the analysis and verification are carried out. The performance of GA-LSSVM classifier is studied. The simulation results show that GA-LSSVM classifier has better recognition and classification performance than other classifiers in different SNR environments, and more than 90% accuracy can be achieved when SNR is greater than 0 dB.