Genetic programming with a genetic algorithm for feature construction and selection

被引：93

作者：

Smith M.G. ^{[1
]}

Bull L. ^{[1
]}

机构：

[1] Faculty of Computing, Engineering and Mathematical Sciences, University of the West of England, Bristol

来源：

Genetic Programming and Evolvable Machines | 2005年 / 6卷 / 3期

关键词：

Classification; Feature construction; Feature selection; Genetic algorithm; Genetic programming; Machine learning;

D O I：

10.1007/s10710-005-2988-7

中图分类号：

学科分类号：

摘要：

The use of machine learning techniques to automatically analyse data for information is becoming increasingly widespread. In this paper we primarily examine the use of Genetic Programming and a Genetic Algorithm to pre-process data before it is classified using the C4.5 decision tree learning algorithm. Genetic Programming is used to construct new features from those available in the data, a potentially significant process for data mining since it gives consideration to hidden relationships between features. A Genetic Algorithm is used to determine which such features are the most predictive. Using ten well-known datasets we show that our approach, in comparison to C4.5 alone, provides marked improvement in a number of cases. We then examine its use with other well-known machine learning techniques. © 2005 Springer Science + Business Media, Inc.

引用

页码：265 / 281

页数：16

共 24 条

[21] Siedlecki W., Sklansky J., On automatic feature selection, International Journal of Pattern Recognition and Artificial Intelligence, 2, pp. 197-220, (1988)
[22] Song D., Heywood M.I., Zincir-Heywood A.N., A linear genetic programming approach to intrusion detection, Genetic and Evolutionary Computation - GECCO-2003, pp. 2325-2336, (2003)
[23] Vafaie H., De Jong K., Genetic algorithms as a tool for restructuring feature space representations, Proceedings of the International Conference on Tools with A.I., (1995)
[24] Witten I., Frank E., Data Mining: Practical Machine Learning Tools and Techniques with Java Implementations, (2000)

← 1 2 3 →