Epigenetic modification of genetic algorithm for outlier detection

Abstract

The article presents a new operator in the genetic algorithm. The proposed operator mimics the epigenetic process of prion inheritance. For living organisms, epigenetic processes have a large impact on the differentiation of the population, hence the idea to imitate these processes in genetic algorithms. For the purposes of the experiments, a genetic algorithm to detect outliers was used. The proposed operator mimics the epigenetic process was added to the basic genetic algorithm and the impact of the operator on the effectiveness of the algorithm was assessed. The impact of the proposed modification on the efficiency of the genetic algorithm was tested on six data sets. The article also presents an experimental analysis of the proposed operator.