Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
3 results
Search Results
Item Alignment based similarity distance measure for better web sessions clustering(Elsevier B.V., 2011) Poornalatha, G.; Raghavendra, P.S.The evolution of the internet along with the popularity of the web has attracted a great attention among the researchers to web usage mining. Given that, there is an exponential growth in terms of amount of data available in the web that may not give the required information immediately; web usage mining extracts the useful information from the huge amount of data available in the web logs that contain information regarding web pages accessed. Due to this huge amount of data, it is better to handle small group of data at a time, instead of dealing with entire data together. In order to cluster the data, similarity measure is essential to obtain the distance between any two user sessions. The objective of this paper is to propose a technique, to measure the similarity between any two user sessions based on sequence alignment technique that uses the dynamic programming method. © 2011 Published by Elsevier Ltd.Item An improved web page recommendation system using partitioning and web usage mining(Association for Computing Machinery acmhelp@acm.org, 2015) Chanda, J.; Annappa, B.There are different types of hypertext documents available on the Internet. Accessing relevant information and serving useful information to the user from the Internet has become a complex and expensive task. To make this process simpler, one of the widely used recommendation systems is item based collaborative filtering recommendation system which predicts web pages based on the browsing activity of the user on the Internet and recommends web pages as per their interests. There are certain challenges in these systems like sparsity and scalability, the proposed approach overcomes these problems. The proposed approach uses weighted kmean clustering instead of simple k-mean clustering and the obtained clusters are partitioned on the basis of similarity which helps in reducing the processing time of recommendation generation. Clustering and partitioning enhances the existing item based collaborative filtering recommendation system. The MovieLens data set is used for demonstrating the proposed approach. The performance of the proposed approach is evaluated using various metrics. The result shows that the proposed approach is 30% efficient in terms of root mean square error and 21% effective in respect of mean absolute error analysis and the accuracy measures factors like precision, recall and F-measure are found to have higher values than the existing item based collaborative filtering recommendation systems. © 2015 ACM.Item Web sessions clustering using hybrid sequence alignment measure (HSAM)(Springer-Verlag Wien michaela.bolli@springer.at, 2013) Poornalatha, G.; Raghavendra, S.R.Web usage mining inspects the navigation patterns in web access logs and extracts previously unknown and useful information. This may lead to strategies for various web-oriented applications like web site restructure, recommender system, web page prediction and so on. The current work demonstrates clustering of user sessions of uneven lengths to discover the access patterns by proposing a distance method to group user sessions. The proposed hybrid distance measure uses the access path information to find the distance between any two sessions without altering the order in which web pages are visited. R2 is used to make a decision regarding the number of clusters to be constructed. Jaccard Index and Davies–Bouldin validity index are employed to assess the clustering done. The results obtained by these two standard statistic measures are encouraging and illustrate the goodness of the clusters created. © 2012, Springer-Verlag.