Improved Performance and Accuracy using Different Clustering Techniques in WUM
In an era of internet, websites on the internet are useful resource of data for almost each action. Thus there's a quick growth of World Wide Web (WWW) in its traffic amount, the range and complexional of websites. There are multiple issues associated with the existing techniques of web usage mining. Existing web usage mining algorithms suffer from problem of practical applicability. So, a completely unique analysis is extremely abundant necessary for the accurate prediction of future performance of web users with fast execution time. This paper consists of preprocessing and clustering of web users. Log data is routinely noisy and unclear, so preprocessing is an essential process for effective mining process. Initially, the pre-processing is applied on whole documents to remove the unnecessary words and phrases of every document. Then the clustering process is applied on country and OS to make the partition of the documents through the proposed semantic similarity measure used.
Keywords - WWW, Clustering, Web Data, FCM, FPCM Algorithm.