Papers

Title: Novel Dimensionality Reduction Method for Symbolic Data using Coefficient of Variation
Year of Publication: 2015
Publisher: International Journal of Computer Systems (IJCS)
ISSN: 2394-1065
Series: Volume 2, Number 12
Authors: Veerabhadrappa, Lalitha Rangarajan

Citation:

Veerabhadrappa, Lalitha Rangarajan, "Novel Dimensionality Reduction Method for Symbolic Data using Coefficient of Variation", International Journal of Computer Systems (IJCS), 2(12), pp: 530-536, December 2015. BibTeX

@article{key:article,
	author = {Veerabhadrappa, Lalitha Rangarajan},
	title = {Novel Dimensionality Reduction Method for Symbolic Data using Coefficient of Variation},
	journal = {International Journal of Computer Systems (IJCS)},
	year = {2015},
	volume = {2},
	number = {12},
	pages = {530-536},
	month = {December}
	}

Abstract

In this paper, we propose a novel dimensionality reduction method of representing the set of features using smaller set of symbolic features. The intersection of intervals of pair samples is computed and using which a similarity value is generated. For these similarity values, the coefficient of variation is computed which is considered for subsequent clustering. Experimental results on the standard datasets City Temperature and CORN SOYBEAN show that the proposed method achieves better classification performance.

References

[1] Betrand P ,Goupil F, Descriptive statistics for symbolic data, analysis of symbolic data, Bock H.H and Diday E(eds) Springer, 1999.
[2] Bock H.H , Diday E, Analysis of symbolic data, Springer Verlag, 2000.
[3] De Carvalho.F.A.T, Souza R, New metrics for constrained Boolean symbolic objects, Proc of KESDA98, Eurostat, Luxemberg 1998.
[4] Diday E, An introduction to symbolic data analysis, Tutorial of 4th Conf of IFCS, Paris, 1993.
[5] Gowda.K.C ,Diday.E, Symbolic clustering using a new dissimilarity measure, Pattern Recognition, Vol 24, no.6, pp 567-578, 1991.
[6] Gowda.K.C ,Diday.E, Symbolic clustering using a new similarity measure, IEEE Trans on SMC, Vol 22, No.2, Mar/April 1992.
[7] Ichino.M, Yaguchi.H, Generalized Minkowsi’s metrics for mixed feature type data analysis, IEEE Trans on SMC, 24(4), pp 698-708, 1994.
[8] Jain A.K, Dubes.R.C, Algorithm for clustering data, Prentice Hall, pp 23-46, 143-220, 1988.
[9] Jolliffe.I.T, “Principal Component Analysis” Springer Verlag, NY, 1986.
[10] Lalitha Rangarajan ,Nagabhusha.P, Dimensionality reduction of multi dimensional temporal data through regression, Pattern Recognition Letters, Vol 25/8, pp.899-910, 2004.
[11] Michalski R.S, Diday E, Stepp R.E, A recent advance in data analysis: Clustering objects into classes characterized by conjunctive concepts, Pattern Recognition, vol.1, pp33-56, 1981.
[12] Nagabhushan P, Gowda K C and Diday E, Dimensionality reduction of symbolic data, Pattern Recognition Letters, Vol 16, pp 219-213, 1995.
[13] Nagabhushan P, An efficient method for classifying remotely sensed data, incorporating Dimensionality Reduction, PhD Thesis, University of Mysore, Mysore, 1988.


Keywords

Dimensionality Reduction, intersection of intervals, symbolic data, Coefficient of variation, Association, disassociation, cluster tendency index.