Fast Independent Component Analysis and Its Application
Xianchuan Yu, Dan Hu, Jindong Xu · 2014
In this chapter, we discussed the concepts, solutions for independent component, and application of FastICA. We systematically reviewed two FastICA methods (FastICA and M-FastICA). Some practical examples of speech signals, images, and geochemical exploration data were presented toward the end of the chapter. When applied to geochemical exploration data analysis, mineral resources prediction, remote sensing image classification, image noise reduction, and image information extraction, FastICA shows high accuracy. Compared with ICA and FastICA, M-FastICA shows the best performance in face recognition.