Parallel computing of kernel ensity estimates with MPI / Szymon Łukasik // W: Computational Science - ICCS 2007 : 7th International Conference, Beijing China, May 27-30, 2007 : Proceedings, Part III [Dokument ... więcej

Parallel computing of kernel ensity estimates with MPI / Szymon Łukasik // W: Computational Science - ICCS 2007 : 7th International Conference, Beijing China, May 27-30, 2007 : Proceedings, Part III [Dokument elektroniczny] / ed. by Yong Shi, Geert Dick van Albada, Jack Dongarra, Peter M.A. Sloot. – Germany : Springer-Verlag Berlin Heidelberg, 2007. – (Lecture Notes in Computer Science ; 4489). – S. 726-733 : wykr. – Tryb dostępu: https://link.springer.com/content/pdf/10.1007/978-3-540-72588-6.pdf. – Bibliogr. 16 poz., Abstr., ISSN 0302-9743. – doi: 10.1007/978-3-540-72588-6_120. – ISBN 978-3-540-72587-9 (print). – ISBN 978-3-540-72588-6 (online)

Kernel density estimation is nowadays very popular tool for nonparametric probabilistic density estimation. One of its most important disadvantages is computational complexity of calculations needed, especially ... więcej

Kernel density estimation is nowadays very popular tool for nonparametric probabilistic density estimation. One of its most important disadvantages is computational complexity of calculations needed, especially for data-based bandwidth selection and adaptation of bandwidth coefficient. The article presents parallel methods which can significantly improve calculation time. Results of using reference implementation based on Message Passing Interface standard in multicomputer environment are included as well as a discussion on effectiveness of parallelization.