دانلود رایگان مقاله انگلیسی مقایسه الگوریتم ژنتیک با تکامل دستوری برای طراحی خودکار الگوریتم های طبقه بندی برنامه نویسی ژنتیک - الزویر 2018

Abstract

Genetic Programming(GP) is gaining increased attention as an effective method for inducing classifiers for data classification. However, the manual design of a genetic programming classification algorithm is a non-trivial time consuming process. This research investigates the hypothesis that automating the design of a GP classification algorithm for data classification can still lead to the induction of effective classifiers and also reduce the design time. Two evolutionary algorithms, namely, a genetic algorithm (GA) and grammatical evolution (GE) are used to automate the design of GP classification algorithms. The classification performance of the automated designed GP classifiers i.e. GA designed GP classifiers and GE designed GP classifiers are compared to each other and to manually designed GP classifiers on real-world problems. Furthermore, a comparison of the design times of automated design and manual design is also carried out for the same set of problems. The automated designed classifiers were found to outperform manually designed classifiers across problem domains. Automated design time is also found to be less than manual design time. This study revealed that for the considered datasets GE performs better for binary classification while the GA does better for multiclass classification. Overall the results of the study are in support of the hypothesis.

Conclusion

This study investigated the feasibility of automating the design of GP classification algorithms for data classification using a genetic algorithm and grammatical evolution. A GA and GE were used to evolve configurations for GP. The effectiveness of automated design is tested on a varied set of real-world problems 1170 selected from the UCI dataset repository and on the NSL-KDD dataset. The automated designed configurations were used to evolve GP algorithms that produce classifiers that perform binary classification and multiclass classification. The results of predictive accuracy and design times of the GA and GE were compared to each other and to those of manual design. The results showed that 1175 for the selected UCI binary class problems, on average across all datasets the predictive accuracy of GP classifiers evolved using configurations designed by GE is higher than those designed by a GA and manual design. The predictive accuracy of GP classifiers evolved by both the GA and GE were shown to be statistically significantly higher than the predictive accuracy of manually designed 1180 GP classifiers. However the differences between the GA and GE were not statistically significant and either algorithm was found to be suitable for automated design. Both the GA and GE were found to have less design times than manual design although the GA on average had a higher design time than GE. For the selected UCI multiclass instances the GA was found to be better than both GE 1185 and manual design. The performance of the GA was statistically significantly better than the manual design but not statistically significantly better than GE. On average GE had higher predictive accuracies across all multiclass datasets than manual design however, the differences were not statistically significant.