Feature selection and classification using age layered population structure genetic programming

摘要

This paper presents a new algorithm called Feature Selection Age Layered Population Structure (FSALPS) for feature subset selection and classification of varied supervised learning tasks. FSALPS is a modification of Hornby's ALPS algorithm - an evolutionary algorithm renown for avoiding pre-mature convergence on difficult problems. FSALPS uses a novel frequency count system to rank features in the GP population based on evolved feature frequencies. The ranked features are translated into probabilities, which are used to control evolutionary processes such as terminal-symbol selection for the construction of GP trees/sub-trees. The FSALPS meta-heuristic continuously refines the feature subset selection process whiles simultaneously evolving efficient classifiers through a non-converging evolutionary process that favors selection of features with high discrimination of class labels. We compared the performance of canonical GP, ALPS and FSALPS on some high-dimensional benchmark classification datasets, including a hyperspectral vision problem. Although all algorithms had similar classification accuracy, ALPS and FSALPS usually dominated canonical GP in terms of smaller and efficient trees. Furthermore, FSALPS significantly outperformed canonical GP, ALPS, and other feature selection strategies in the literature in its ability to perform dimensionality reduction.