A New Crossover Operator in Genetic Programming for Object Classification

@article{Zhang2007b, abstract = {The crossover operator has been considered ldquothe centre of the stormrdquo in genetic programming (GP). However, many existing GP approaches to object recognition suggest that the standard GP crossover is not sufficiently powerful in producing good child programs due to the totally random choice of the crossover points. To deal with this problem, this paper introduces an approach with a new crossover operator in GP for object recognition, particularly object classification. In this approach, a local hill-climbing search is used in constructing good building blocks, a weight called looseness is introduced to identify the good building blocks in individual programs, and the looseness values are used as heuristics in choosing appropriate crossover points to preserve good building blocks. This approach is examined and compared with the standard crossover operator and the headless chicken crossover (HCC) method on a sequence of object classification problems. The results suggest that this approach outperforms the HCC, the standard crossover, and the standard crossover operator with hill climbing on all of these problems in terms of the classification accuracy. Although this approach spends a bit longer time than the standard crossover operator, it significantly improves the system efficiency over the HCC method.}, author = {Zhang, Mengjie and Gao, Xiaoying and Lou, Weijun }, booktitle = {Systems, Man, and Cybernetics, Part B, IEEE Transactions on}, citeulike-article-id = {2764414}, doi = {http://dx.doi.org/10.1109/TSMCB.2007.902043}, journal = {Systems, Man, and Cybernetics, Part B, IEEE Transactions on}, number = {5}, pages = {1332--1343}, posted-at = {2008-05-07 10:24:37}, priority = {2}, title = {A New Crossover Operator in Genetic Programming for Object Classification}, url = {http://dx.doi.org/10.1109/TSMCB.2007.902043}, volume = {37}, year = {2007} }

TY - JOUR ID - Zhang2007b L3 - citeulike-article-id:2764414 N2 - The crossover operator has been considered ldquothe centre of the stormrdquo in genetic programming (GP). However, many existing GP approaches to object recognition suggest that the standard GP crossover is not sufficiently powerful in producing good child programs due to the totally random choice of the crossover points. To deal with this problem, this paper introduces an approach with a new crossover operator in GP for object recognition, particularly object classification. In this approach, a local hill-climbing search is used in constructing good building blocks, a weight called looseness is introduced to identify the good building blocks in individual programs, and the looseness values are used as heuristics in choosing appropriate crossover points to preserve good building blocks. This approach is examined and compared with the standard crossover operator and the headless chicken crossover (HCC) method on a sequence of object classification problems. The results suggest that this approach outperforms the HCC, the standard crossover, and the standard crossover operator with hill climbing on all of these problems in terms of the classification accuracy. Although this approach spends a bit longer time than the standard crossover operator, it significantly improves the system efficiency over the HCC method. IS - 5 JF - Systems, Man, and Cybernetics, Part B, IEEE Transactions on EP - 1343 TI - A New Crossover Operator in Genetic Programming for Object Classification VL - 37 T2 - Systems, Man, and Cybernetics, Part B, IEEE Transactions on SP - 1332 AU - Zhang, Mengjie AU - Gao, Xiaoying AU - Lou, Weijun PY - 2007/// UR - http://dx.doi.org/10.1109/TSMCB.2007.902043 ER -