02231940

a

02231940 Li, Jie Peng, Jing Chu, Heng Zhu, Weile Automatic digital modulation recognition using support vector machines and genetic algorithm. Wang, Jun (ed.) et al., Advances in neural networks -- ISNN 2005. Second international symposium on neural networks, Chongqing, China, May 30 -- June 1, 2005. Proceedings, Part II. Berlin: Springer (ISBN 3-540-25913-9/pbk). Lecture Notes in Computer Science 3497, 568-573 (2005). 2005 Berlin: Springer EN

doi:10.1007/b136478

Summary: A new method, based on support vector machines (SVMs) and genetic algorithm (GA), is proposed for automatic digital modulation recognition (ADMR). In particular, the best feature subset from the combined statistical feature set and spectral feature set is optimized using genetic algorithm. Compared to the conventional artificial neural network (ANN) method, the method proposed avoids overfitting and local optimal problems. Simulation results show that this method is more robust and effective than other existing approaches, particularly at a low signal noise ratio (SNR).