English

应用科学学报 ›› 2012, Vol. 30 ›› Issue (2): 141-145.doi: 10.3969/j.issn.0255-8297.2012.02.006

• 论文 • 上一篇    下一篇

基于IM-SAPSO和SVM的EBPSK检测器设计

靳一， 王继武， 吴乐南   

  1. 东南大学信息科学与工程学院，南京210096
  • 收稿日期:2010-12-28 修回日期:2011-05-17 出版日期:2012-03-26 发布日期:2012-03-30
  • 通信作者: 靳一，博士生，研究方向：通信中的信号处理，E-mail: john.0216@163.com；
  • 作者简介:靳一，博士生，研究方向：通信中的信号处理，E-mail: john.0216@163.com；吴乐南，教授，博导，研究方向：多媒体信息处理、通信中的信号处理、模式识别与认证，E-mail: wuln@seu.edu.cn
  • 基金资助:

    国家自然科学基金(No. 60872075)；国家“863”高技术研究发展计划基金(No. 2008AA01Z227)资助

EBPSK Signal Detector Based on IM-SAPSO and SVM

JIN Yi, WANG Ji-wu, WU Le-nan   

  1. School of Information Science and Engineering, Southeast University, Nanjing 210096, China
  • Received:2010-12-28 Revised:2011-05-17 Online:2012-03-26 Published:2012-03-30

PDF

1118

被引次数

3

摘要：

参数选择对于支持向量机(support vector machine, SVM)的分类性能很重要，其本质是搜索寻优.该文提出以最小化K-fold交叉验证误差为目标，以改进模拟退火粒子群优化算法(improved simulated annealing particle swarm optimization, IM-SAPSO)为寻优方法的SVM参数优化方法. 利用优化的SVM对扩展的二元相移键控(extended binary phase shift keying, EBPSK)通信系统中经冲击滤波器的“0”和“1”码元进行分类，并和基于SVM、PSO-SVM以及幅度积分判决的EBPSK检测器进行性能对比. 仿真结果表明：基于IMSAPSO和SVM的EBPSK检测器性能明显好于其他3 种检测器.

关键词: 支持向量机, 模拟退火粒子群优化算法, 扩展的二元相移键控, 冲击滤波器, 幅度积分判决

Abstract:

Parameter selection is important to the classification performance of support vector machine (SVM),which is essentially a search of optimum. This paper proposes a parameter selection method for SVM with the algorithm of improved simulated annealing particle swarm optimization (IM-SAPSO) to search the best parameters. The minimized K-fold cross-validation error is used as the object of IM-SAPSO. The optimized SVM is then used to classify the symbols 0 and 1 passing the impacting filter of an extended binary phase shift keying (EBPSK) communication system. Comparison is made for the detection performance of EBPSK detector between the proposed IM-SAPSO and other methods including those based on SVM, PSO-SVM and amplitude integral decision. Simulation results show that IM-SAPSO and SVM are significantly better than the other three methods.

Key words: support vector machine, simulated annealing particle swarm optimization algorithm, extended binary phase shift keying (EBPSK), impacting filter, amplitude integral decision

中图分类号: