Data classification provides effective solutions to various real-world problems in areas such as disease diagnosis, network intrusion detection, and financial forecasting, among others. Classification algorithms such as induction algorithms, e.g., ID3, and genetic programming are used to produce classifiers. The design of these classification algorithms is time-consuming, requiring many person hours, and is an optimization problem. This chapter examines the automated design of genetic programming as a classification algorithm. The study compares the performance of genetic algorithms and grammatical evolution in automating the design of genetic programming for classifier induction. The performance of the classifiers produced by automated design is compared to that produced by manually designed genetic programming algorithms for binary and multi-class classification in various areas including network intrusion detection and financial forecasting. The automated design required less design time and produced classifiers that performed better than the manually designed classifiers. Grammatical evolution was found to produce better-performing classifiers for binary classification and genetic algorithms for multi-class classification.
[1]
Conor Ryan,et al.
Survey Of Evolutionary Automatic Programming
,
2003
.
[2]
Goldberg,et al.
Genetic algorithms
,
1993,
Robust Control Systems with Genetic Algorithms.
[3]
Nasser R. Sabar,et al.
A Bi-objective Hyper-Heuristic Support Vector Machines for Big Data Cyber-Security
,
2018,
IEEE Access.
[4]
Michael O'Neill,et al.
Grammatical evolution - evolutionary automatic programming in an arbitrary language
,
2003,
Genetic programming.
[5]
Nelishia Pillay,et al.
Comparison of a genetic algorithm to grammatical evolution for automated design of genetic programming classification algorithms
,
2018,
Expert Syst. Appl..
[6]
Alex Alves Freitas,et al.
Evolutionary Design of Decision-Tree Algorithms Tailored to Microarray Gene Expression Data Sets
,
2014,
IEEE Transactions on Evolutionary Computation.
[7]
Randal S. Olson,et al.
TPOT: A Tree-based Pipeline Optimization Tool for Automating Machine Learning
,
2016,
AutoML@ICML.
[8]
David W. Corne,et al.
Hyper-heuristic decision tree induction
,
2009,
2009 World Congress on Nature & Biologically Inspired Computing (NaBIC).