An Approach to Text Documents Clustering with {n, n-1, ….., 1}-Word(s) Appearance Using Graph Mining Techniques

Abstract

This paper is about text document clustering with an input of n words. Initially a cluster of all text documents with extension name ".Txt" from m-documents of various types is formed. Then on an input of n-words, the proposed algorithm starts n, n-1, n-2,.....,1 sets of cluster. Each cluster of text documents with the presence of n, n-1, n- 2,......,1 word(s) respectively. These n-forms of clustering are treated as documents-words relation and in memory it is represented as un-oriented documents-words incidence matrix. Finally these un-oriented documents-words incidence matrices are represented as bi-partite graphs, since the bipartite graph has two sets of nodes namely document and word. The proposed algorithm using graph mining techniques was implemented using C++ programming language and the result was satisfactory.

Authors and Affiliations

Bapuji Rao| Research Scholar, CSE, BPUT, Rourkela, India CSE&A, IGIT, Sarang, Dhenkanal, India bapuji.research@gmail.com, Saroja Nanda Mishra| Research Scholar, CSE, BPUT, Rourkela, India CSE&A, IGIT, Sarang, Dhenkanal, India sarose.mishra@gmail.com

Keywords

Related Articles

Green Internet Routing Between Traffic Volume and Power Consumption

We plan a green Internet routing plan, where the routing can lead movement in a way that is green. We contrast from past reviews where they switch organize parts, for example, line cards and routers, into rest mode....

Dynamics Of Multi layered Composite Shell With Shape Memory Alloys

The use of different composite materials has been continuously growing in recent years. Although many applications for composite materials have been identified. Extensive research is still being carried out in order...

Effective Resource Allocation in flexible Overlay Routing

Overlay routing is the very attractive scheme that allows the improving certain properties of the routing without the need to change the standards of the current underlying routing. However, deploying overlay routing...

Haze monitoring in wireless systems using ARM7 controller

The overwhelming haze, depicted as a pall of smoke brought about boundless health problems particularly among the elderly, the youthful and children. Haze is a climatic wonder where clean, smoke and different particl...

Self-Assured Formal Deduplication In FusionCloud Methodology

Data deduplication is a critical system in support dispose of excess information as an option of enthralling records; it provisions simply distinct copy of file. Together with the whole associations stockpiling patte...

Download PDF file
  • EP ID EP16844
  • DOI -
  • Views 339
  • Downloads 8

How To Cite

Bapuji Rao, Saroja Nanda Mishra (2016). An Approach to Text Documents Clustering with {n, n-1, ….., 1}-Word(s) Appearance Using Graph Mining Techniques. International Journal of Science Engineering and Advance Technology, 4(12), 756-762. https://europub.co.uk/articles/-A-16844