This study establishes the new results for Cluster Width of probability Density functions (CWD). There are the upper and lower bounds of CWD and the relationships of CWD to other measures in statistical discriminant. The CWD for two and more two probability density functions is determined in the different cases. Based on CWD, we propose a measure called similar coefficient to evaluate the quality of the established clusters. Furthermore, CWD is also used as a criterion to build two algorithms: to determine the suitable number of clusters and to analyse the fuzzy clusters. The numerical examples are given to illustrate the proposed algorithms and to prove their advantages over existing methods.
ChenJ. and HungW., An automatic clustering algorithm for probability density functions, Journal of Statistical Computation and Simulation85(15) (2015), 3047–3063.
2.
DefaysD., An efficient algorithm for a complete link method, The Computer Journal20(4) (1977), 364–366.
3.
DuinR., On the choice of smoothing parameters for parzen estimators of probability density functions, IEEE Transactions on Computers25 (1997), 1175–1179.
4.
FukunagaF., Introduction to statistical pattern recognition (2nd Ed), Academic Press, New York, 1990.
5.
GlickN., Separation and probability of correct classification among two or more distributions, Annals of the Institute of Statistical Mathematics25(1) (1973), 373–382.
6.
GohA. and VidalR., Unsupervised Riemannian clustering of probability density functions, in: Joint European Conference on Machine Learning and Knowledge Discovery in Databases, 2008, pp. 377–392.
7.
KraftC.H., Some conditions for consistency and uniform consistency of statistical procedures, University of California Press, 1955.
8.
LuoJ.JiaoL. and ShangR., Learning simultaneous adaptive clustering and classification via moea, Pattern Recognition60(2) (2016), 37–50.
9.
MacQueenJ., Some methods for classification and analysis of multivariate observations, in: Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, Oakland, CA, USA, 1, 1967, pp. 281–297.
10.
MatusitaK., On the notion of affinity of several distributions and some of its applications, Annals of the Institute of Statistical Mathematics19(1) (1967), 181–192.
11.
MontanariA. and CaloD.G., Model-based clustering of probability density functions, Advances in Data Analysis and Classification7(3) (2013), 301–319.
12.
ParzenE., On estimation of a probability density function and mode, The Annals of Mathematical Statistics33(3) (1962), 1065–1076.
13.
Pham-GiaT. and NhatN.D., Statistical classification using the maximum function, Open Journal of Statistics5(7) (2015), 665–680.
14.
Pham-GiaT.TurkkanN. and BekkerA., Bayesian analysis in the L1 – norm of the mixing proportion using discriminant analysis, Metrika64(1) (2006), 1–22.
15.
Pham-GiaT.TurkkanN. and VoVanT., The maximum function in statistical discrimination analysis, Communication in Statistics: Simulation and Computation37 (2008), 320–336.
16.
ScottD., Multivariate density estimation: Theory, practice and visualisation, John Willey and Sons, New York, 1992.
17.
SilvermanB., Density estimation, Chapman & Hall, London, 2010.
18.
ThaoN.T. and VovanT., Fuzzy clustering of probability density functions, Journal of Applied Statistics44 (2017), 583–601.
19.
ToussaintG., Some inequalities between distance measures for feature, I.E.E.E Trans. Comput21 (1972), 409–410.
20.
VovanT., L1 – distance and classification problem by bayesian method, Journal of Applied Statistics44(3) (2017), 385–401.
21.
VovanT. and Pham-GiaT., Clustering probability distributions, Journal of Applied Statistics37(11) (2010), 1891–1910.
22.
WebbA., Statistical pattern recognition, John Wiley & Sons, 2002.
