EFFECTIVE EXPECTATION MAXIMIZATION ALGORITHM IMPLEMENTATION USING MULTICORE COMPUTER SYSTEMS
Alexei Kasitskij
pbidyuke_00@ukr.netNational Technical University "Kyiv Polytechnic Institute", Institute for Applied System Analysis (Ukraine)
Peter Bidyuk
National Technical University "Kyiv Polytechnic Institute", Institute for Applied System Analysis (Ukraine)
Alexander Gozhyi
Petro Mohyla Black Sea State University, Department of Information Technologies and Program Systems (Ukraine)
Abstract
A popular expectation maximization algorithm that is widely used in modern data processing systems to solve various problems including optimization and parameter estimation is considered in the paper. The task of the study was to enhance effectiveness of the algorithm execution in time. An enhancement of execution rate for the EM algorithm using multicore architecture of modern computer systems was carried out. Necessary modifications aimed at better parallelism were proposed for implementation of the EM algorithm. An efficiency of the software implementation was tested on the classic problem of Gaussian random variables mixture separation. It is shown that in the mixture separation problem EM algorithm performance degrades when the distance between mean values of distributions is less than three standard deviations, which is totally in the spirit of three sigma law. In such cases, it is very important to have an efficient EM algorithm implementation to be able to process such test cases in a reasonable time.
Keywords:
expectation maximization algorithm, multicore architecture, parallelism, problem of Gaussian random variables mixture separation, three sigma lawReferences
Ben-Ari M.: Principles of Concurrent and Distributed Programming (2nd ed.). Addison-Wesley, 2006.
Google Scholar
Bidyuk P. I., Gozhij O. P., Korshevnyuk L.O.: Computer based decision support systems. Chornomorsky State University named after Petro Mogyla, Mykolaiv, 2012.
Google Scholar
Borman S.: The expectation maximization algorithm a short tutorial. http://www.seanborman.com/publications/EM_algorithm.pdf
Google Scholar
Chapman B., Jost G. R., Kuck D. J.: Using Open MP: Portable Shared Memory Parallel Programming. The MIT Press, Boston 2007.
Google Scholar
Dellaert F.: The expectation maximization algorithm. Techn. paper, Georgia Institute of Technology, 2002.
Google Scholar
Dinov I. D.: Expectation maximization and mixture modeling tutorial. http://www.stat.ucla.edu/~dinov/courses_students.dir/04/Spring/Stat233.dir/STAT233_notes.dir/EM_Tutorial.pdf
Google Scholar
Hollsapple C. W., Winston A. B.: Decision support systems. West Publishing Company, New York 1996.
Google Scholar
Korbicz J.(Ed.): Measurements, models, systems and design. Wydawnictwa Komunikacji i łączności, 2007.
Google Scholar
Quinn M. J.: Parallel Programming in C with MPI and Open MP. McGraw-Hill Inc. 2004.
Google Scholar
Shuicheng Y., Chang S. F., Johnson M. H., Xi Z., Xiaodan Z., Huang T. S.: Sift-bag kernel for video event analysis. Proceeding of the 16th ACM international conference on Multimedia, 2008, 229-238.
Google Scholar
Authors
Alexei Kasitskijpbidyuke_00@ukr.net
National Technical University "Kyiv Polytechnic Institute", Institute for Applied System Analysis Ukraine
Authors
Peter BidyukNational Technical University "Kyiv Polytechnic Institute", Institute for Applied System Analysis Ukraine
Authors
Alexander GozhyiPetro Mohyla Black Sea State University, Department of Information Technologies and Program Systems Ukraine
Statistics
Abstract views: 194PDF downloads: 63
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Most read articles by the same author(s)
- Alexander Gozhyi, Irina Kalinina, INFORMATION SYSTEM FOR A FUZZY COGNITIVE ANALYSIS AND MODELING , Informatyka, Automatyka, Pomiary w Gospodarce i Ochronie Środowiska: Vol. 4 No. 2 (2014)
