Feature Selection using Simulated Annealing with Optimal Neighborhood Approach

Abstract

The one of the metaheuristic approaches that can be used was simulated annealing (SA) algorithm which inspired by annealing metallurgical process. This algorithm shows advantages in finding global optimum of given function which will be used in feature selection. In this study, we will trying to combine the neighborhood size and limited approach by using data simulation comparing between two function which is Akaike Index Criterion (AIC) function and Bayesian Index Criterion (BIC) function. The result of this experiment shows that the selected variables using optimal neighborhood size and limit the selected variable provide the result of goodness model around 98% of accuracy and specificity and 94% of sensitivity compared with simulated annealing algorithms without any modification using both AIC function and BIC function, and in the simulation also shows that BIC function give better result than AIC function.