Relative Reference Measure for Hierarchical Document Clustering

Abstract

Clustering is a foremost concept in data mining. Clustering usually require a measure that needs to be computed among the clustering objects this measure could be either a similarity or a dissimilarity measure, here a multiple relative reference based similarity measure is used which could give more informative assessment of the similarity moreover this measure is derived from the traditional cosine similarity measure. In order to evaluate the performance of proposed measure an incremental clustering algorithm- Master only algorithm is used initially with cosine similarity and then with Relative Reference similarity measures for document clustering. As an extended application of Relative Reference measure to generate hierarchical clusters we used Master-Slave algorithm. The results of clustering are evaluated by using a cluster validity index-Davies Bouldin index.

Authors and Affiliations

D. Satya Prasad, T. Nirosh Kumar

Keywords

Related Articles

A New Wavelet Packet Based Method for Denoising of Biological Signals

Wavelet packets have been found to be effective in denoising of biological signals. Wavelet based denoising methods widely employ hard and soft thresholding filters for denoising the signals. This paper introduces a N...

An Efficient Parallel Processing Technique For Large Text Files

Now a days the data was increasing rapidly because of heterogeneous resources. The data that is useful for large organisations will required large number of computing resources for processing large data sets. there a...

Minimum Bandwidth Reservations for Periodic Streams in Wireless Real-Time Systems

Reservation-based (as opposed to contention-based) channel access in WLANs provides predictable and deterministic transmission and is therefore able to provide timeliness guarantees for wireless and embedded real-ti...

To Measure The Average Delay Experienced By A Subscriber To Connect In An Attribute Tree

Validation of publishers and subscribers is not simple to get due to the loose coupling ofpublishers and subscribers.We also present extensions of the cryptographic methods to proffer capable routing of encrypted eve...

Performance Analysis of Improved ODMRP with Motion Detection (IOMD) in Mobile Ad Hoc Network

Multicast transmission is a more effective mechanism when more effective mechanism to unicasts for group communication based applications and of due importance to future network development. Multicasting in ad hoc ne...

Download PDF file
  • EP ID EP27791
  • DOI -
  • Views 243
  • Downloads 1

How To Cite

D. Satya Prasad, T. Nirosh Kumar (2013). Relative Reference Measure for Hierarchical Document Clustering. International Journal of Research in Computer and Communication Technology, 2(12), -. https://europub.co.uk/articles/-A-27791