Improved Classification Performance of Support Vector Machine Technique Using the Genetic Algorithm | ||
AL-Rafidain Journal of Computer Sciences and Mathematics | ||
Article 8, Volume 12, Issue 2, December 2018, Pages 49-60 PDF (562.63 K) | ||
Document Type: Research Paper | ||
DOI: 10.33899/csmj.2018.163581 | ||
Authors | ||
Omar Saber Qasim; Mustafa Ayham Abed Alhafedh | ||
College of Computer Science and Mathematics University of Mosul, Mosul, Iraq | ||
Abstract | ||
In this research, the genetic algorithm was proposed as a method to find the parameters of support vector machine, specifically the σ and c parameters for kernel and the hyperplane respectively. Based on the Least squares method, the fitness function was built in the genetic algorithm to find the optimal values of the parameters in the proposed method. The proposed method showed better and more efficient results than the classical method of support vector machine which adopts the default or random values of parameters σ and c in the classification of leukemia data. | ||
Keywords | ||
genetic algorithm; Support vector machine; Parameter Selection | ||
Statistics Article View: 265 PDF Download: 531 |