Paper Details

Web mining process can largely express as discovery and analysis of suitable data information from theWorld Wide Web. It can be express as the exploration and analysis of different pattern, during the web mining of web logfiles and linked data from a particular weblog file, in a manner that will be more efficiently for the user while using web.Web usage mining is a part of web mining, which defines data mining techniques to find the important relevantinformation as per the usage of user of web. The initial phase of the web usage mining is the processing of the data.Session reconstruction is the most important work of web usage mining since it directly emphasizes on the quality ofthe patterns which are extracted frequently. Similarly another factor affecting the web data extraction is the depend uponhow the clusters are form of the web data in the web usage mining. Forming the cluster of the web data efficientlyenhance the searching speed, decrease the searching time and give the most relevant data set to the user. There areseveral algorithms are apply for the clustering the data to partition it according to the web usage factors lik e mostviewed pages , ranking of the page, dataset, etc. Clustering is one of the main web data analysis methods and k -meansalgorithm is one of the popular algorithms. [1]There exist already many new technique were already proposed toimprove the efficiency and performance of the k -means algorithm, but it need extra efforts and parameters to improve theefficiency. But with the initial centroid]the efficiency of k mean will be improved without any other inputs. In this paperwe proposed by taking a web log of a user searching into consideration that if we divided the whole web log data intocluster using k mean with initial centroid algorithm instead of only K mean algorithm and on those clusters we willapplied different web extracting techniques to retrieve that search item then the combinations result will be moreefficient.

Jasmine M Chaniara, Prof. Firoz Sherasiya, “SURVEY ON AMELIORATE DATA EXTRACTION IN WEB MINING BY CLUSTERING THE WEB LOG DATA”, International Journal of Advance Engineering and Research Development (IJAERD), Vol. 1, Issue 12, pp. 9-14, December 2014.