The Theoretical Basis of Blind Source Separation
摘要
This chapter mainly introduces the theoretical basis of blind source separation (BSS) technology. Firstly, Independent Component Analysis (ICA) and Principal Component Analysis (PCA), which are widely used in overdetermined/determined BSS, and Sparse Component Analysis (SCA), which are widely used in underdetermined BSS, are introduced. On this basis, the current common methods of BSS are given. Finally, several common performance indexes of BSS algorithms are defined to lay the groundwork for evaluating the performance of BSS algorithms given in the following chapters.