Correlation Preserving Indexing Based Text Clustering
Journal Title: IOSR Journals (IOSR Journal of Computer Engineering) - Year 2013, Vol 13, Issue 1
Abstract
In Document clustering previously they presented new document clustering method based on correlation preserving indexing. It simultaneously maximizes the correlation between the documents in the local patches and minimizes the correlation between the documents outside these patches. Consequently, a low dimensional semantic subspace is derived where the documents corresponding to the same semantics are close to each other with learning level parsing procedure based CPI method. The proposed CPI method with learning level parsing procedure is to find correlation between relational documents to avoid maximum unknown clusters those are not effectual to find exact correlation between documents depend on accuracy of sentences. The proposed CPI method with learning level parsing procedure in document clustering doubles the accuracy of previous correlation coefficient. The proposed hierarchical clustering algorithm behavior is different with CPI in terms of NMI, Accuracy
Authors and Affiliations
Venkata Gopala Rao . S
Keywords
Related Articles
- EP ID EP87638
- DOI -
- Views 157
- Downloads 0
“Design and Detection of Mobile Botnet Attacks”
Abstract: A mobile botnet is a type of bot that runs automatically when installed on a mobile phone, which does not have any anti-malware. The botnet gains complete access over our mobile device. The common propagation m...
Bandwidth Management on Cloud Computing Network
Abstract: To be able to manage the available bandwidth and distribute it among the Cloud Applications userseffectively is a very critical issue to avoid network congestion and network resources abuse. In this paper...
Correlation Coefficient Based Average Textual Similarity Modelfor Information Retrieval System in Wide Area Networks
Abstract: In wide area networks, retrieving the relevant text is a challenging task for information retrievalbecause most of the information requests are text based. The focus of paper is on the similarity measurem...
Pattern Analytical Module for EDOS Attacker Recognition
Abstract: Cloud computing has provided a platform to its users where they are charged on the basis of usage of the cloud resources; this is known as “pay-as-you-use”. Today, Cloud computing is the most hyped techno...
Approximating Source Accuracy Using Dublicate Records in Data Integration
Currently, there are two main basic strategies to resolve conflicts in data integration: Instance-based strategy and metadata-based strategy. However, the two strategies have their limitations and their problems....