期刊名称：International Journal of Computer Trends and Technology
电子版ISSN：2231-2803
出版年度：2011
卷号：2
期号：2-1
出版社：Seventh Sense Research Group
摘要：Building an efficient classification model for classification problems with different sample size is important. The main tasks are the selection of the best training set and its parameters to predict the test set. In contrast to random sampling, the particle swarm optimization is applied to identify the optimal sample instance subsets. This may improve a quality of the base classifiers and result in a more accurate ensemble. In this paper, we use Particle Swarm Optimization (PSO) to find the best training set selection and then evaluated fitness values with a Support Vector Machine (SVM) classifier, which is combined with the oneversusrest method; the method proposed has applied to identify the spam Email using a data set collected at HewlettPackard Labs with remarkable results. The results obtained show that approaches PSOSVM gives a better classification in terms of accuracy even though the execution time increased.
