A new geometric approach to blind source separation of bounded sources

作     者：Jinlong Zhang a, Guoxu Zhoua, Zuyuan Yang a, Xiaoxin Liao b a School of Electrics & Information Engineering, South China University of Technology, Guangzhou 510641, China b Department of Control Science and Engineering, Huazhong University of Science and Technology, Wuhan 430074, China 

作者机构：School of Electrics & Information Engineering South China University of Technology Guangzhou 510641 China Department of Control Science and Engineering Huazhong University of Science and Technology Wuhan 430074 China 

出 版 物：《Progress in Natural Science:Materials International》 (自然科学进展·国际材料(英文))

年 卷 期：2009年第19卷第7期

页      面：891-896页

核心收录：

学科分类：08[工学] 080203[工学-机械设计及理论] 0802[工学-机械工程] 

基　　金：supported by the National Natural Science Foundation of China (Grant No. U0635001 60674033 and 60774094) 

主　　题：Blind source separation Independent component analysis Minimum-range approach 

摘      要：Based on the minimum-range approach, a new geometric approach is proposed to deal with blind source separation in this paper. The new approach is the batch mode of the original minimum-range approach. Compared with the original approach, the optimization algorithm of the proposed approach needs no parameters and is more efficient and reliable. In addition, the extension of minimum-rangebased approaches is discussed. The simulations show the efficiency of the proposed approach.