View Article

Article Details

File Missing!
JournalInternational Journal of Computer Applications
TitleA Feature Selection Model based on High-Performance Computing (HPC) Techniques
Index TermInformation Sciences
AbstractHigh-Performance Computing (HPC) proved notable performance enhancements especially on fields where data processing is exceedingly time consuming. Such data raise the curse of dimensionality problem in which several methods followed to maintain the number of features describing that data. Feature Selection is one of the known procedures applied to overcome the drawback caused by the data size. In this work, a feature selection model designed and tested. Genetic Algorithm (GA) is the search algorithm involved, Linear Discriminant Analysis (LDA) used as a classifier, and both form the feature selection model. GA estimates an optimal solution that saves the enormous amount of time might be consumed by a brute force search, and LDA performs as its fitness object. HPC techniques implemented since the computational power was one of the leading obstacle causing an extensive processing time. The developed feature selection model saves 89% of the original time consumed while using common computing facilities. It also maintains an accuracy rate of almost 86% selecting 37% of the original number of features.
KeywordsGenetic Algorithm, Linear Discernment Analysis, Islands Model, Message Passing Interface, Boost.
No. of Pages6
Author NamesSahar Alwadei, Mohamed Dahab, Mahmoud Kamel
Author Emailssalwadei0010@stu.kau.edu.sa, mdahab@kau.edu.sa, miali@kau.edu.sa
References
  1. Fodor, Isola K. "A survey of dimension reduction techniques." (2002).
  2. Cunningham, Pádraig. "Dimension reduction. "Machine learning techniques for multimedia. Springer Berlin Heidelberg, (2008). 91-112.
  3. Kamel, Mahmoud I., and Anas A. Hadi. Improving P300 Based Speller by Feature Selection. Journal of Medical Imaging and Health Informatics 4.4: 469-487, 2014.
  4. Cunningham, Pádraig. Dimension reduction. Machine learning techniques for multimedia. Springer Berlin Heidelberg, (2008).91-112.
  5. Yu, Xinjie, and Mitsuo Gen. Introduction to evolutionary algorithms. Springer Science & Business Media, (2010). ‏
  6. Xin-She Yang, Engineering Optimization – An Introduction to Metaheuristic Applications. John Wiley & Sons, Hoboken, New Jersy, (2010).
  7. K Y Lee, M.A. El-Sharkawi, “Modern Heuristic Optimization Techniques” IEEE press and Wiley – InterScience, New Jersy, (2008).
  8. Rody P S Oldenhuis, “Trajectory Optimization of a mission to the Solar Bow shock and minor planets”, MSc thesis report, Delft University of Technology, Netherlands, (Jan 2010).
  9. Kachitvichyanukul, Voratas. Comparison of Three Evolutionary Algorithms. Industrial Engineering & Management Systems 11.3 (2012). 215-223. ‏
  10. Umbarkar, A. J., M. S. Joshi, and P. D. Sheth. OpenMP Dual Population Genetic Algorithm for Solving Constrained Optimization Problems. International Journal of Information Engineering and Electronic Business (IJIEEB) 7.1: 59, (2015).
  11. Slate's article Stephen: Wolfram's New Programming Language: He Can Make The World Computable, March 6, 2014. Retrieved on 14-05-2015.
  12. Fujitsu Supports King Abdul-Aziz University Research Capabilities with New Supercomputing System. Press release. King Abdul-Aziz University, Fujitsu Limited. Jeddah and Tokyo, June 01, 2015
  13. Top 500, The List. http://www.top500.org/site/50585 , (2015).
  14. John, Kohavi, and Pfleger, Irrelevant features and the subset selection problem. Machine Learning: Proceedings of the Eleventh International Conference, available at http://robotics.stanford.edu/~ronnyk. Last access: 10/22/2017.
  15. Datasets from UCI. SGI, Silicon Graphics International Corp. https://www.sgi.com/tech/mlc/db/ . Last access: 10/22/2017.
Files

Publishing Information

StatePublished
Volume180
Issue7
Start Page No.11
Editor's Choice