期刊名称：International Journal of Computer Science Issues
印刷版ISSN：1694-0784
电子版ISSN：1694-0814
出版年度：2013
卷号：10
期号：3
出版社：IJCSI Press
摘要：Support Vector Machines (SVM) and Probabilistic Neural Networks (PNN) that are within the scope of artificial intelligence applications has been widely accepted. Because of strong statistical foundations of these methods, they generate generalizable results. In this study we aimed to compare classification performance of SVM and PNN methods using real and empirical data sets. In the real data set, we investigated the success of diagnosis of some demographic characteristics and some gene polymorphisms on knee osteoarthritis. In addition, success of SVM and PNN methods were compared for classification of samples that have various data structure. We found that the classification performance of PNN method is better than SVM. The most important disadvantage of PNN method is that the analysis time increase with sample size and number of attributes. When the proportion of the observation number to attributes number is greater than 5, SVM and PNN can be used for classification.
关键词：Optimization; classification; radial basis function; support vector machine; neural networks
