Variance-based differential evolution algorithm with an optional crossover for data clustering

The differential evolution optimization-based clustering techniques are powerful, robust and more sophisticated than the conventional clustering methods due to their stochastic and heuristic characteristics. Unfortunately, these algorithms suffer from several drawbacks such as the tendency to be tra...

Full description

Saved in:
Bibliographic Details
Published in:Applied soft computing Vol. 80; pp. 1 - 17
Main Authors: Alswaitti, Mohammed, Albughdadi, Mohanad, Mat Isa, Nor Ashidi
Format: Journal Article
Language:English
Published: Elsevier B.V 01.07.2019
Subjects:
Convergence speed
Data clustering
Differential evolution
Exploitation and exploration
Optional crossover
Switchable mutation
Optional crossover
Differential evolution
Switchable mutation
Exploitation and exploration
Data clustering
Convergence speed
ISSN:1568-4946, 1872-9681
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The differential evolution optimization-based clustering techniques are powerful, robust and more sophisticated than the conventional clustering methods due to their stochastic and heuristic characteristics. Unfortunately, these algorithms suffer from several drawbacks such as the tendency to be trapped or stagnated into local optima and slow convergence rates. These drawbacks are consequences of the difficulty in balancing the exploitation and exploration processes which directly affects the final quality of the clustering solutions. Hence, a variance-based differential evolution algorithm with an optional crossover for data clustering is presented in this paper to further enhance the quality of the clustering solutions along with the convergence speed. The proposed algorithm considers the balance between the exploitation and exploration processes by introducing (i) a single-based solution representation, (ii) a switchable mutation scheme, (iii) a vector-based estimation of the mutation factor, and (iv) an optional crossover strategy. The performance of the proposed algorithm is compared with current state-of-the-art differential evolution-based clustering techniques on 15 benchmark datasets from the UCI repository. The experimental results are also thoroughly evaluated and verified via non-parametric statistical analysis. Based on the obtained experimental results, the proposed algorithm achieves an average enhancement up to 11.98% of classification accuracy and obtains a significant improvement in terms of cluster compactness over the competing algorithms. Moreover, the proposed algorithm outperforms its peers in terms of the convergence speed and provides repeatable clustering results over 50 independent runs. •A single solution representation is adopted to avoid setting the initial solutions’ sizes and positions.•A new switchable mutation scheme is employed to enhance the balance of the search behavior.•Multidimensional mutation factor is introduced to enhance the mutant solution quality.•A new optional crossover strategy is proposed to increase the convergence rate.•Integration of the four proposals in one DE-based clustering algorithm.
ISSN:1568-4946
1872-9681
DOI:10.1016/j.asoc.2019.03.013