An Artificial Bee Colony Based Algorithm for Feature Selection

Abstract

The aim of the feature selection is to reduce the number of features to be used during the classification process to improve run-time performance and efficiency of the classifier. In this study, Artificial Bee Colony (ABC) Optimization Technique, which is a recent successful swarm intelligence algorithm, based feature selection method is proposed for classification tasks. The algorithm was experimented on fifteen datasets from the UCI Repository which are commonly used in classification problems. The experimental results of this study showed that the proposed ABC based algorithm is able to select good features for classification tasks.

Artificial Bee Colony for Features Selection Optimization in Increasing T-Method Accuracy

“…E. Zorarpaci et al, (2015) Modified the ABC algorithm for feature selection purposes into a binary form that affects the way of producing the new neighborhood of food source operator while the fitness function was done separately using Weka J48 classifier. The team proved that ABC is performing better than other algorithm and can be applied efficiently in solving hard combination problems with high dimensionality [30].…”

“…Overall procedure of T-method is basically following the S.Teshima et al, (2012) [6] but for the method used by the bees (employed and onlooker) to search for the new food source which having more nectar amount within its neighborhood are basically following the approach introduced by D. Karaboga and B. Bastuk (2007) [31]. Equation 18 summarized the approaches used in fulfilling this intention but also an enhancement approaches made by E. Zorarpaci et al (2015) [30]. X r1 and X r2 in equation 18 are the random numbers in terms of (0,1) while r1 and r2 is just a random number between 0 to 1 and X i is the initial food source.…”

“…Mohammad Shokouhifar Shahid (2014) used a colony size of 50 for their case study due to convergence speed acceptance [32]. While E. Zorarpaci et al, (2015) used colony size 50 and the maximum cycle of 500 on their case [30]. M.S.…”