盲源信号分离EASI算法研究与改进  

Research and Improvement of Blind Source Separation Based on EASI Algorithm

作　　者：余华[1] 吴文全[1] 

机构地区：[1]海军工程大学电子工程学院,湖北武汉430033

出　　处：《计算技术与自动化》2009年第4期76-79,共4页Computing Technology and Automation

基　　金：国家863项目(2007ADA299)

摘　　要：研究EASI算法,以串音误差为衡量盲源信号分离效果的指标,给出EASI算法的仿真结果及性能分析。验证EASI算法的有效性,总结EASI算法应用于盲信号分离的优点与不足,并提出利用模拟退火策略有效地结合两种步长的优点,在初期快速下降,在后期精确收敛。结果表明,在本实验中使用模拟退火策略来调整学习率是简单有效的。EASI algorithm is further studied using cross talking error as an evaluation parameter. Simulation result and performance comparison of EASI algorithm is given. Validity of EASI algorithm is proved and the advantages and shortcomings of it is discussed,then a new method which using genetic algorithm to adjust step-length is presented. The method integrates the advantages of large step-length and short step-length. Simulation result of the method shows it is simple and effective.

关 键 词：盲信号分离 EASI算法 串音误差(ETC) 模拟退火策略 

分 类 号：TN911.7[电子电信—通信与信息系统]