计算机技术与发展2016，Vol.26Issue(7)：46-50,5.DOI:10.3969/j.issn.1673-629X.2016.07.010
基于改进蜂群算法的数字信号调制识别
A Modulation Identification Algorithm for Digital Signals Based on Modified Artificial Bee Colony Algorithm
摘要
Abstract
In view of the slow convergence speed and non-uniform distribution of the initial food source of traditional Artificial Bee Colo-ny ( ABC) algorithm,a modified ABC algorithm based on two-dimensional uniform design and Euclidean-distance has been proposed. Two-dimensional uniform design is used to make the food source uniformly distribute in the solution space when the modified ABC algo-rithm establishes the food source,which can improve the global search ability of the algorithm. Euclidean-distance is applied in construc-ting new food source to improve the efficiency optimization. In this paper,four feature parameters which are picked up from second-or-der,fourth-order and sixth-order cumulants are obtained as a feature vector because second and higher order cumulants can suppress ad-ditive white Gaussian noise. SVM classifier and modified ABC algorithm is used to optimize the penalty factor and kernel function param-eter,realizing the identification of 2FSK,BPSK,QPSK,16QAM and 64QAM. The simulation results show that the convergence speed of modified ABC algorithm is improved and the average recognition rate is 92. 9% when SNR is-3 dB,as well as over 99% when SNR is more than 4 dB.关键词
人工蜂群/欧氏距离/二维均匀设计/支持向量机/调制识别Key words
artificial bee colony/Euclidean-distance/two-dimensional uniform design/support vector machines/modulation identifica-tion分类
计算机与自动化引用本文复制引用
吴少华,单剑锋..基于改进蜂群算法的数字信号调制识别[J].计算机技术与发展,2016,26(7):46-50,5.基金项目
国家自然科学基金资助项目(61302155,GZ212015) （61302155,GZ212015）
