一种改进的FCM聚类算法的混合矩阵估计  

Mixing matrix estimation based on an improved FCM clustering algorithm

作　　者：郭凌飞 张林波[1] GUO Lingfei;ZHANG Linbo(College of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, China)

机构地区：[1]哈尔滨工程大学信息与通信工程学院,黑龙江哈尔滨150001

出　　处：《应用科技》2019年第2期47-52,共6页Applied Science and Technology

摘　　要：在增强信号稀疏性的基础上,对模糊C均值(fuzzy C-means, FCM)聚类算法进行改进,达到提高混合矩阵估计精度的目的,更好地解决欠定盲源分离问题。主要针对稀疏成分分析理论"两步法"中的混合矩阵估计算法改进,提出一种基于隶属度划分优化的FCM聚类算法。通过改变目标函数中的隶属度划分方式,来影响数据的归类,从而决定了混合矩阵中元素的估计精度。最后,将改进的算法用于语音信号仿真实验,完成混合矩阵估计。实验结果表明,用改进的算法所获得的矩阵估计误差小且精度高,可使归一化均方误差减小1.3 dB,角度偏差最多可减小1°。The research is to improve the fuzzy C-means(FCM)clustering algorithm based on the enhancement of signal sparsity.Its goal is to achieve the purpose of improving the accuracy of mixing matrix estimation and solve the problem of underdetermined blind source separation better.In this paper,the mixing matrix estimation algorithm in the"two-step method"of sparse component analysis theory is improved mainly.After a brief description of the blind source separation problem,an FCM clustering algorithm based on membership classification optimization is proposed.The classification of the data is affected by changing the membership classification method in the objective function,determining the estimation accuracy of the elements in the mixing matrix.Finally,an improved algorithm was used in the speech signal simulation experiment to complete the mixing matrix estimation.The experimental results show that the matrix estimation error obtained by the improved algorithm is small,which can improve the estimation accuracy of the mixing matrix by reducing the normalized mean square error by 1.3 dB,and angular deviation by 1°at most.

关 键 词：欠定盲源分离 稀疏成分分析 两步法 混合矩阵估计 隶属度划分 FCM聚类算法 语音信号 估计精度 

分 类 号：TN911.7[电子电信—通信与信息系统]