期刊名称：International Journal of Innovative Research in Science, Engineering and Technology
印刷版ISSN：2347-6710
电子版ISSN：2319-8753
出版年度：2015
卷号：4
期号：8
页码：6994
DOI：10.15680/IJIRSET.2015.0408219
出版社：S&S Publications
摘要：In this paper we tend to use machine learning algorithms like SVM, KNN and GIS to perform a behavior comparison on the net pages classifications drawback, fro m the experiment we tend to see within the SVM with tiny range of negative documents to make the centroids has the littlest storage demand and also the least on line take a look at co mputation value. however mo st GIS with completel y different range of nearest neighbors have a fair higher storage demand and on line take a look at computation value than KNN. this means that some future work ought to be done to do to cut back the storage demand and on list take a look at value of GIS
