Zhou Guoxu, Yang Zuyuan, Xie Shengli, Yang Jun-Mei
School of Electronics and Information Engineering, South China University of Technology, Guangzhou 510641, China.
IEEE Trans Neural Netw. 2011 Apr;22(4):550-60. doi: 10.1109/TNN.2011.2109396. Epub 2011 Mar 3.
Online blind source separation (BSS) is proposed to overcome the high computational cost problem, which limits the practical applications of traditional batch BSS algorithms. However, the existing online BSS methods are mainly used to separate independent or uncorrelated sources. Recently, nonnegative matrix factorization (NMF) shows great potential to separate the correlative sources, where some constraints are often imposed to overcome the non-uniqueness of the factorization. In this paper, an incremental NMF with volume constraint is derived and utilized for solving online BSS. The volume constraint to the mixing matrix enhances the identifiability of the sources, while the incremental learning mode reduces the computational cost. The proposed method takes advantage of the natural gradient based multiplication updating rule, and it performs especially well in the recovery of dependent sources. Simulations in BSS for dual-energy X-ray images, online encrypted speech signals, and high correlative face images show the validity of the proposed method.
为克服高计算成本问题，提出了在线盲源分离（BSS），该问题限制了传统批量BSS算法的实际应用。然而，现有的在线BSS方法主要用于分离独立或不相关的源。最近，非负矩阵分解（NMF）在分离相关源方面显示出巨大潜力，其中常施加一些约束来克服分解的非唯一性。本文推导了一种具有体积约束的增量NMF，并将其用于解决在线BSS问题。对混合矩阵的体积约束增强了源的可识别性，而增量学习模式降低了计算成本。所提出的方法利用基于自然梯度的乘法更新规则，并且在相关源的恢复方面表现尤其出色。在双能X射线图像、在线加密语音信号和高度相关面部图像的BSS中的仿真表明了所提方法的有效性。
