A Genetic Programming Approach to Binary Classification Problem

EAI Endorsed Transactions on Energy Web

R. Regin¹  Karrar Kadhim²  Bhopendra Singh³  Leo Santoso⁴  S. Rajest⁵ 

[1] Advanced Studies (VISTAS), Tamil Nadu, India;Assistant Professor, Department of Information Technology, Adhiyamaan College of Engineering, India;Associate Professor, Amity University, Dubai;Petra Christian University, 121-131 Siwalankerto Rd, Surabaya, East Java, Indonesia;;Vels Institute of Science, Technology &

关键词: binary classification;    evolutionary algorithms;    genetic programming;    machine learning;   

DOI  :  10.4108/eai.13-7-2018.165523

来源: DOAJ

【 摘 要 】

The Binary classification is the most challenging problem in machine learning. One of the most promising technique to solvethis problem is by implementing genetic programming (GP). GP is one of Evolutionary Algorithm (EA) that used to solveproblems that humans do not know how to solve it directly. The objectives of this research is to demonstrate the use ofgenetic programming in this type of problems; that is, other types of techniques are typically used, e.g., regression, artificialneural networks. Genetic programming presents an advantage compared to those techniques, which is that it does not needan a priori definition of its structure. The algorithm evolves automatically until finding a model that best fits a set of trainingdata. Feature engineering was considered to improve the accuracy. In this research, feature transformation and featurecreation were implemented. Thus, genetic programming can be considered as an alternative option for the development ofintelligent systems mainly in the pattern recognition field.

【 授权许可】

Unknown