Open AccessICA based on Split Generalized Gaussian
Author(s) -
Przemysław Spurek,
Przemysław Rola,
Jacek Tabor,
Aleksander Czechowski,
Andrzej Bedychaj
Publication year - 2019
Publication title -
schedae informaticae
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.122
H-Index - 4
eISSN - 2083-8476
pISSN - 1732-3916
DOI - 10.4467/20838476si.19.002.14379
Subject(s) - kurtosis , independent component analysis , fastica , gaussian , skewness , metric (unit) , moment (physics) , computer science , mathematics , independence (probability theory) , transformation (genetics) , pattern recognition (psychology) , artificial intelligence , algorithm , blind signal separation , statistics , computer network , biochemistry , channel (broadcasting) , physics , operations management , chemistry , classical mechanics , quantum mechanics , economics , gene
Independent Component Analysis (ICA) is a method for searching the linear transformation that minimizes the statistical dependence between its components. Most popular ICA methods use kurtosis as a metric of independence (non-Gaussianity) to maximize, such as FastICA and JADE. However, their assumption of fourth-order moment (kurtosis) may not always be satisfied in practice. One of the possible solution is to use third-order moment (skewness) instead of kurtosis, which was applied in ICA_SG and EcoICA. In this paper we present a competitive approach to ICA based on the Split Generalized Gaussian distribution (SGGD), which is well adapted to heavy-tailed as well as asymmetric data. Consequently, we obtain a method which works better than the classical approaches, in both cases: heavy tails and non-symmetric data