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：2012
卷号：9
期号：3
出版社：IJCSI Press
摘要：Recent research studies on liver diagnosis indicated difference in classification accuracy of various classifiers with different data sets. K-Nearest Neighbor classifier is observed to be giving best results with India liver patients data set with all feature set combinations. Performance is better for the India Liver dataset compared to UCLA liver dataset with all the selected algorithms [1]. In order to envisage the reason for this difference, we propose to analyze the liver patients populations of both USA and India. We have carried out extensive ANOVA, MANOVA analysis on these data sets to observe any significant difference among the groups. It has observed that liver patients of both the countries are having significant difference which is the reason for difference in classifiers performance. Results of this study are very important for the development of automatic medical diagnosis system and the need for its localization settings based on the geographical region.
