期刊名称:International Journal of Computer Applications and Information Technology
印刷版ISSN:2278-7720
出版年度:2014
卷号:6
期号:2
页码:129-135
出版社:Mahadev Educational Society
摘要:Data and information are basis for today's industrial and day to day app lications of almost every domain. The volume of data for most of human friendly applications is generally enormous in nature and thus it is mandatory to scale them in pre-defined cl usters based on their properties. Data mining has always interested the researchers to characterize the data and is integrated in applications like: Statistics, Machine Learning, Artificial Intelligence, pattern recognition etc. Data mining applications can derive much demographic information concerning customers that was previously not known or hidden in the data. We have recently seen an increase in data mining techniques targeted to such applications as fraud detection, identifying criminal suspects, and prediction of potential terrorists. By and large, data mining systems that have been developed to data for clusters, distributed clusters and grids have assumed that the processors are the sca rce resource, and hence shared. When processors become available, the data is moved to the processors. This paper surveys some data mining methods in their actual nature and modifications made in their algorithms for better output in their performance.