ABSTRACT
This chapter first introduces some basic concepts and algorithms of ICA, and then focuses on the use of ICA for data cleansing, including data filtering and data preprocessing.
4.1.1 Blind Source Separation (BSS) Now take a look at a signal processing problem. Assume that two people are speaking simultaneously in a room. There are two microphones located in two different locations. The two microphones record time signals denoted by x1(t) and x2(t), with x1 and x2 being the amplitudes and t the time index. Each of these recorded signals is a weighted sum of the speech signals emitted by the two speakers, denoted by
4.2.6 An Example ....................................................................................94 4.2.6.1 Example 1 .........................................................................94
4.3 Data Cleansing with ICA ..........................................................................95 4.3.1 Data Filtering with ICA ..................................................................96
