دورية أكاديمية

Uniqueness of non-Gaussianity-based dimension reduction.

التفاصيل البيبلوغرافية
العنوان: Uniqueness of non-Gaussianity-based dimension reduction.
المؤلفون: Theis, F.J., Kawanabe, M., Müller, K.-R.
المصدر: IEEE Trans. Signal Process. 59, 4478 - 4482 (2011)
بيانات النشر: IEEE
سنة النشر: 2011
المجموعة: PuSH - Publikationsserver des Helmholtz Zentrums München
مصطلحات موضوعية: Identifiability, Independent subspace analysis, non-Gaussian component analysis, projection pursuit
الوصف: Dimension reduction is a key step in preprocessing large-scale data sets. A recently proposed method named non-Gaussian component analysis searches for a projection onto the non-Gaussian part of a given multivariate recording, which is a generalization of the deflationary projection pursuit model. In this contribution, we discuss the uniqueness of the subspaces of such a projection. We prove that a necessary and sufficient condition for uniqueness is that the non-Gaussian signal subspace is of minimal dimension. Furthermore, we propose a measure for estimating this minimal dimension and illustrate it by numerical simulations. Our result guarantees that projection algorithms uniquely recover the underlying lower dimensional data signals.
نوع الوثيقة: article in journal/newspaper
اللغة: English
تدمد: 1053-587X
1941-0476
العلاقة: info:eu-repo/semantics/altIdentifier/wos/undefined; info:eu-repo/semantics/altIdentifier/isbn/1053-587X; info:eu-repo/semantics/altIdentifier/pissn/1053-587X; info:eu-repo/semantics/altIdenti; https://push-zb.helmholtz-muenchen.de/frontdoor.php?source_opus=6790Test; urn:isbn:1053-587X; urn:issn:1053-587X; urn:issn:1941-0476
DOI: 10.1109/TSP.2011.2159600
الإتاحة: https://doi.org/10.1109/TSP.2011.2159600Test
https://push-zb.helmholtz-muenchen.de/frontdoor.php?source_opus=6790Test
حقوق: info:eu-repo/semantics/closedAccess
رقم الانضمام: edsbas.87F6D459
قاعدة البيانات: BASE
الوصف
تدمد:1053587X
19410476
DOI:10.1109/TSP.2011.2159600