On Statistical Pattern Recognition in Independent Component Analysis Mixture Modelling

• Main Author: Salazar, Addisson. (Author)
• Corporate Author: SpringerLink (Online service)
• Format: Electronic
• Language: English
• Published: Berlin, Heidelberg : Springer Berlin Heidelberg : Imprint: Springer, 2013.
• Series: Springer Theses, Recognizing Outstanding Ph.D. Research, 4
• Subjects: Engineering.; Optical pattern recognition.; Physics.; Signal, Image and Speech Processing.; Pattern Recognition.; Complexity.
• Online Access: https://ezaccess.library.uitm.edu.my/login?url=http://dx.doi.org/10.1007/978-3-642-30752-2

A natural evolution of statistical signal processing, in connection with the progressive increase in computational power, has been exploiting higher-order information. Thus, high-order spectral analysis and nonlinear adaptive filtering have received the attention of many researchers. One of the most...

Table of Contents:

• Introduction
• ICA and ICAMM Methods
• Learning Mixtures of Independent Component Analysers
• Hierarchical Clustering from ICA Mixtures
• Application of ICAMM to Impact-Echo Testing
• Cultural Heritage Applications: Archaeological Ceramics and Building Restoration
• Other Applications: Sequential Dependence Modelling and Data Mining
• Conclusions.