A Hard K-Means Clustering Techniques for Information Retrieval from Search Engine

International Journal of Computer Science and Engineering

© 2017 by SSRG - IJCSE Journal

Volume 4 Issue 2

Year of Publication : 2017

Authors : B.Srinivasa Rao, S.Vellusamy Raddy

10.14445/23488387/IJCSE-V4I2P102

How to Cite?

B.Srinivasa Rao, S.Vellusamy Raddy, "A Hard K-Means Clustering Techniques for Information Retrieval from Search Engine," SSRG International Journal of Computer Science and Engineering , vol. 4,  no. 2, pp. 4-7 , 2017. Crossref, https://doi.org/10.14445/23488387/IJCSE-V4I2P102

Abstract:

K-means clustering is a method of vector quantization, at firstcome from signal processing, that is famous for cluster analysis in data mining problem. K-means clustering objectives to dividen observations into k clusters in which everystatementgoes to the cluster with the nearest mean, allocation as a example of the cluster. These consequences in a partitioning of the data space into Voronoi cells. Data transmission meetsnumerouschallenges nowadays and one such is data recovery from a multidimensional and heterogeneous information set. Han & et al found some challenges in data mining. Aninnovative feature co-selection for web document clustering is suggested by them, which is entitled as Multitype Features Co-selection for Clustering (MFCC). MFCC practicesmidway clustering outcomes in one type of feature space to support the collection in other types of feature spaces. It reduces the noise affected from “pseudoclass” and additionally expands clustering performance. The data retrieval efficiency is used in, employing the MFCC algorithm in position algorithm of Search Engine technique. The future work is to put on the MFCC algorithm in search engine planning. Such that the data retrieves from the dataset is retrieved successfully and express the relevant retrieval.

Keywords:

MFCC algorithm, Search Engine, Ranking algorithm, Information Retrieval.

References:

[1] Ed. Green grass, "Information Retrieval: A survey"; 2000.
[2] Report from SWIR 2012; “Frontiers, Challenges, and Opportunities for IR”; ACM SIGIR forum vol. 46, No.1, June 2012.
[3] Sew Staff, "How search engines work", 2007.
[4] Han & et al., "Multi type feature co-selection for clustering for web documentation", IEEE transaction on knowledge engineering, June 2006.
[5] K.Parimala, Dr.V.Palanisamy, “Enhanced Performance of Search Engine withmultitype Feature Co-Selection for Clustering Algorithm”, International Journal of Computer Applications (0975 - 8887) Volume-53- No. 7, September2012.
[6] Sergey Brie & Lawrence Page, “The Anatomy of a large-scale hyper textual web search engine” 2009.
[7] Joseph Williams and Ravi Starzi, “Tuning up the search engine”, IT-PRO Jan/106-2011, 15 20-9202/01/2001 IEEE.
[8]Kristen L.Metzger, “Advanced web searching for the information professional”.
[9]David Hawking, “Web search engines: part 1 & part 2”, CSIRO/CT centre 2006; pg.86-89, June 2006; “Computer: How things work” pg.88489, Aug. 2006.
[10] Srinivas M & et al., “MFCC and ARM algorithms for text categorization”, Aug 2010.
[11] Srinivas M & et al., “Improving performance of Text categorization: Using MFCC and LSquare Machine Learning”, 2010.