Hui Han, Jingchao Li*, Xiang Chen and Yulong Ying Pages 442 - 447 ( 6 )
Background: With the technical development of counter-reconnaissance and antijamming, communication system becomes more and more complex, and therefore, the recognition of communication signal becomes a challenging task according to recent patents. In order to achieve successful recognition and classification of radiation source signal under variant SNR environment, the design and selection of classifier are one of the key points.
Methods: Gray relation theory can solve the learning problem with a small number of samples and its algorithm is simple and can solve the issue of generality versus accuracy, which is very suitable for dealing with fuzzy mathematical problems. However, the selection of distinguishing coefficient has a direct effect on the recognition results by gray relation classifier. For conventional gray relation classifier, the distinguishing coefficient is usually set as a fixed value of 0.5, and for different types of signals, its recognition rate varies. Aiming at this issue, an improved adaptive gray relation classifier algorithm is proposed in the paper.
Results: The simulation results show that the recognition rate can still reach more than 87% even at the SNR of 10dB.
Conclusion: The proposed methods can improve the anti-jamming capability of the classifier, which can be widely used in the fields of electronic reconnaissance, fault diagnosis and image processing.
Signal's recognition, classifier design, gray relation theory, different SNR environment, counter-reconnaissance, anti-jamming.
State Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System (CEMEE), Luoyang, Henan 471003, Electronic Information College, Shanghai Dianji University, Shanghai 201306, State Key Laboratory of Complex Electromagnetic Environment Effects on Electronics and Information System (CEMEE), Luoyang, Henan 471003, School of Energy and Mechanical Engineering, Shanghai University of Electric Power Shanghai 200090