Data mining with evolutionary algorithms

• Main Author: Qin, Jinjing
• Other Authors: Chan Chee Keong
• Format: Final Year Project
• Language: English
• Published: 2010
• Subjects: DRNTU::Engineering::Electrical and electronic engineering::Computer hardware, software and systems
• Online Access: http://hdl.handle.net/10356/20772
• Institution: Nanyang Technological University

Data mining has been applied in many areas in real life such as medicine, business, and government and so on. Several algorithms have been developed for different data mining tasks. Among them, evolutionary algorithms are used to solve problems with unknown search space, and are very effective for difficult problems that cannot be solved by other algorithms. This project explores the feasibility of performing data mining tasks with evolutionary algorithms. The objective is to design a data mining system using evolutionary algorithm, to implement the system with Java language, and to test the effectiveness of the system through experiments. Firstly, the relevant theories of data mining and evolutionary algorithms have been reviewed in the report. As one main step in the process of knowledge discovery in databases (KDD), data mining deals with inputting prepared data, searching data with algorithms, and outputting patterns. There are many data mining tasks such as classification, clustering and so on. For evolutionary algorithm, the overall mechanism and the concept of the data structure, the operations and the fitness function have been interpreted. Secondly, the design of the system has been explained in details. Based on the selected breast cancer dataset input, the system was designed to perform classification tasks using genetic algorithm.