Reducing the number of DNA primers for classifying Pejibaye Palm races using SVM

Abstract

This paper presents a feature reduction method, applying to Deoxyribonucleic Acid (DNA) primer, obtaining 100% classes identification based on Support Vector Machines (SVM). In particular, the biochemical parameterization has 89 Random Amplified polymorphic DNA (RADP) primers of Pejibaye Palm races, and it has been reduced to 10 RADP primers. The interest of this application is economic and computational, because it is so much cheaper to calculate less primers (only 11.24% from the previous dataset); and therefore, this supervised classification system is faster in order to do a method of origin denomination plant certification.