Similarity Measurement Of Web Navigation Pattern Using K-Harmonic Mean Algorithm
Journal Title: Elysium Journal of Engineering Research and Management - Year 2017, Vol 4, Issue 5
Abstract
we present a new method to improve the web Navigation Usage Pattern to discover the web data based on similarity between two cluster points. The web usage patterns can be extracted from Web server logs regularly verified for working websites by first handling the log data to find users, user sessions, and user task-oriented transactions, and then applying a Web usage mining algorithm to determine patterns among web usage paths. In conventional Web usage mining, semantic information of the Web page content does not take part in the pattern generation process. The web navigation usage pattern including information about both the path and time essential for user-oriented tasks. It is taken by our ideal user communicating path models. It can be measure to distance between similar web usage patterns. In this approach, the user visited pages are subdivided into clusters using a non-Euclidean distance measure called the Sequence Order Method (SOM) and Euclidean method measure called Association Distance Measure (ADM). In this paper mainly focus to identify page path similarity, and implementing KHM clustering algorithm. The minimum number of pages in a session and similarity of usage path were calculated
Authors and Affiliations
Abirami K, Mayilvaganan P
Keywords
Related Articles
- EP ID EP365547
- DOI -
- Views 115
- Downloads 0
A LITERATURE STUDY ON ASSOCIATION RULE MINING
Association Rule mining has become an essential topic in data mining during recent years. It gains more popularity because of its wide range of applicability. Many researches introduced new algorithms ba...
HIGHLY ACCURATE RECOGNITION OF BODY MASS INDEX AND HUMAN DIABETICS THROUGH SENSORS
Monitoring of diabetics and BMI (Body Mass Index) is used in many medical field and research applications. This paper suggests a method for performing highly accurate recognition of pressure, sugar, he...
A Statistical Pattern Recognition Approach for Tracking Left Ventricle Endocardium
The Left Ventricle endocardium has a difficult problem can be determined by a new statistical pattern recognition approach. In this pattern, resampling algorithm along with the current time step is estimated and appearan...
COMPARATIVE ANALYSIS OF HANDOFF TECHNIQUES USING RESPONSE SURFACE ALGORITHM
Handoff is one of the most challenging topic for the next-generation wireless network. In this paper, the handoff techniques are compared by using the five parameters such as Bandwidth, Network latency,...
A Patch Based Approach for the Segmentation of Pathologies: Application to Glioma Labelling
This paper proposes a novel and generic approach with multi-atlas patch-based voting techniques for addressing the fullyautomatic segmentation of brain tumors. To avoid the local search window assumption, conventional pa...