Identifying the best attributes for Decision Tree Learning Algorithms, inspired by DNA concepts, in computer science

Decision trees are some kinds of learning structures which are used to provide approximations on the accurate solutions for new instances using learning data classifications. The core part in a Decision Tree Learning Algorithm is the approach taken in each phase for choosing better attributes. In this paper we tried to develop a new approach for selecting better attributes in training phase of a decision tree using DNA-base algorithms with lower complexity in arithmetic operators.