Research Article
A New Binary Adaptive Elitist Differential
Evolution Based Automatic k-Medoids Clustering for
Probability Density Functions
D. Pham-Toan ,
1
T. Vo-Van,
1
A. T. Pham-Chau,
2,3
T. Nguyen-Trang ,
2,3
and D. Ho-Kieu
2,3
1
Natural Science College, Can To University, Can To, Vietnam
2
Division of Computational Mathematics and Engineering, Institute for Computational Science, Ton Duc Tang University,
Ho Chi Minh City, Vietnam
3
Faculty of Mathematics and Statistics, Ton Duc Tang University, Ho Chi Minh City, Vietnam
Correspondence should be addressed to D. Ho-Kieu; hokieudiem@tdtu.edu.vn
Received 22 December 2018; Accepted 24 March 2019; Published 22 April 2019
Academic Editor: Elio Masciari
Copyright © 2019 D. Pham-Toan et al. Tis is an open access article distributed under the Creative Commons Attribution License,
which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Tis paper proposes an evolutionary computing based automatic partitioned clustering of probability density function, the so-called
binary adaptive elitist diferential evolution for clustering of probability density functions (baeDE-CDFs). Herein, the k-medoids
based representative probability density functions (PDFs) are preferred to the k-means one for their capability of avoiding outlier
efectively. Moreover, addressing clustering problem in favor of an evolutionary optimization one permits determining number of
clusters “on the run”. Notably, the application of adaptive elitist diferential evolution (aeDE) algorithm with binary chromosome
representation not only decreases the computational burden remarkably, but also increases the quality of solution signifcantly.
Multiple numerical examples are designed and examined to verify the proposed algorithm’s performance, and the numerical results
are evaluated using numerous criteria to give a comprehensive conclusion. Afer some comparisons with other algorithms in the
literature, it is worth noticing that the proposed algorithm reveals an outstanding performance in both quality of solution and
computational time in a statistically signifcant way.
1. Introduction
Clustering aims to divide input data into multiple groups
such that elements in each group are similar and diferent
from elements in other groups as much as possible. Tere
are two primary objects of clustering, discrete element and
probability density function (PDF). Over the past few years,
discrete element is preferred in clustering with a lot of
works such as [1, 2]. However, with the explosion of digital
era, a massive amount of data is created each day [3, 4],
and how to present such data well is a challenge task for
discrete elements. Te main reason for this is that the discrete
element just presents whole data by a representative point
so that it is unlikely to fully demonstrate characteristic of
whole data, especially fuctuation data [5]. Meanwhile, the
remaining object-PDF shows its advantage in such digital
era like capturing the distribution of whole data, giving a
visible look of characteristic of the estimated objects [5].
However, regardless of the advantages of PDF, works related
to clustering for this interesting object are still very limited.
Terefore, this paper aims to contribute new approach for
clustering of probability density functions (CDFs).
Concerning CDFs, two main approaches can be found,
nonhierarchical and hierarchical [6]. With respect to non-
hierarchical approach, k-means and k-medoids based algo-
rithms can be seen as the typical ones [7]. However, k-means
based approach shows its disadvantage when addressing out-
liers or noises [7]. In contrast, k-medoids based approach can
handle outliers efectively as shown in the work of [8] since
it directly employs objects in input data as the centers. Te
k-medoids is then applied to various felds. For example, in
[9], Zhang B et al. presented an improved ranked k-medoids
Hindawi
Mathematical Problems in Engineering
Volume 2019, Article ID 6380568, 16 pages
https://doi.org/10.1155/2019/6380568