Article Search
닫기

Original Article

Split Viewer

International Journal of Fuzzy Logic and Intelligent Systems 2019; 19(4): 290-298

Published online December 25, 2019

https://doi.org/10.5391/IJFIS.2019.19.4.290

© The Korean Institute of Intelligent Systems

Meta-Heuristic Algorithms to Improve Fuzzy C-Means and K-Means Clustering for Location Allocation of Telecenters Under E-Governance in Developing Nations

Rajan Gupta1, Sunil Kumar Muttoo1, and Saibal K. Pal2

1Department of Computer Science, University of Delhi, India
2SAG Lab, Defence Research & Development Organization (DRDO), Delhi, India

Correspondence to :
Rajan Gupt (Guptarajan2000@gmail.com)

Received: January 19, 2019; Revised: November 14, 2019; Accepted: November 23, 2019

This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0/) which permits unrestricted noncommercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

The telecenter, popularly known as the rural kiosk or common service center, is an important building block for the improvement of e-governance in developing nations as they help in better citizen engagement. Setting up of these centers at appropriate locations is a challenging task; inappropriate locations can lead to a huge loss to the government and allied stakeholders. This study proposes the use of various meta-heuristic algorithms (particle swarm optimization, bat algorithm, and ant colony optimization) for the improvement of traditional clustering approaches (K-means and fuzzy C-means) used in the facility location allocation problem and maps them for the betterment of telecenter location allocation. A dataset from the Indian region was considered for the purpose of this experiment. The performance of the algorithms when applied to traditional facility location allocation problems such as set-cover, P-median, and the P-center problem was investigated, and it was found that their efficiency improved by 20%–25% over that of existing algorithms.

Keywords: Ant colony optimization, Bat algorithm, Common service center, E-governance, Fuzzy clustering, Meta-heuristic algorithm, Particle swarm optimization, Rural kiosk

Rajan Gupta is a Research and Analytics Professional. He has done his PhD (Information Systems) from Department of Computer Science, University of Delhi, INDIA. His area of interest includes E-Governance, Public Information Systems, Multimedia Data processing, Data Mining and Data Analytics. He has over 50 publications at various national and international forums in the form of books, book chapters, journal papers, conference papers and articles.

E-mail: guptarajan2000@gmail.com

Sunil Kumar Muttoo is Professor at Department of Computer Science, University of Delhi, INDIA. He received his PhD in Coding Theory and M.Tech. in Computer Science and Data Processing from IIT, Kharagpur. His areas of interest include Information Hiding, Coding Theory and E-Governance. He has over 100 publications at national and international forums.

E-mail: drskmuttoo@gmail.com

Saibal K. Pal is Senior Scientist with Scientific Analysis Group Lab, DRDO - Government of India. He received his PhD in Computer Science from University of Delhi, INDIA. His area of interest includes Information & Network Security, Computational Intelligence, Information Systems and EGovernance. He has more than 200 publications at various forums.

Email: skptech@yahoo.com

Article

Original Article

International Journal of Fuzzy Logic and Intelligent Systems 2019; 19(4): 290-298

Published online December 25, 2019 https://doi.org/10.5391/IJFIS.2019.19.4.290

Copyright © The Korean Institute of Intelligent Systems.

Meta-Heuristic Algorithms to Improve Fuzzy C-Means and K-Means Clustering for Location Allocation of Telecenters Under E-Governance in Developing Nations

Rajan Gupta1, Sunil Kumar Muttoo1, and Saibal K. Pal2

1Department of Computer Science, University of Delhi, India
2SAG Lab, Defence Research & Development Organization (DRDO), Delhi, India

Correspondence to:Rajan Gupt (Guptarajan2000@gmail.com)

Received: January 19, 2019; Revised: November 14, 2019; Accepted: November 23, 2019

This is an Open Access article distributed under the terms of the Creative Commons Attribution Non-Commercial License (http://creativecommons.org/licenses/by-nc/3.0/) which permits unrestricted noncommercial use, distribution, and reproduction in any medium, provided the original work is properly cited.

Abstract

The telecenter, popularly known as the rural kiosk or common service center, is an important building block for the improvement of e-governance in developing nations as they help in better citizen engagement. Setting up of these centers at appropriate locations is a challenging task; inappropriate locations can lead to a huge loss to the government and allied stakeholders. This study proposes the use of various meta-heuristic algorithms (particle swarm optimization, bat algorithm, and ant colony optimization) for the improvement of traditional clustering approaches (K-means and fuzzy C-means) used in the facility location allocation problem and maps them for the betterment of telecenter location allocation. A dataset from the Indian region was considered for the purpose of this experiment. The performance of the algorithms when applied to traditional facility location allocation problems such as set-cover, P-median, and the P-center problem was investigated, and it was found that their efficiency improved by 20%–25% over that of existing algorithms.

Keywords: Ant colony optimization, Bat algorithm, Common service center, E-governance, Fuzzy clustering, Meta-heuristic algorithm, Particle swarm optimization, Rural kiosk

Fig 1.

Figure 1.

Overall conceptualization of the optimization of the telecenter in the search space.

The International Journal of Fuzzy Logic and Intelligent Systems 2019; 19: 290-298https://doi.org/10.5391/IJFIS.2019.19.4.290

Table 1 . Cost comparison for various techniques implemented standalone and in combination for different regions.

AlgorithmR1R2R3R4Total
KM-R33825458353999020109139759
KM-C2346524957302341678495440
FCM-R32788448303899720023136639
FCM-C2299623981290921597192042
FCM-PSO2187022317284541318985832
FCM-Bat2072719665266271281679837
FCM-ACO2112420785276321298082521
P-center68470451203901814065166673
P-median22770250103899014580101350

Table 2 . Statistical measures of techniques for total cost of four regions over repeated experimentation (approx. values).

FCM-PSOFCM-BatFCM-ACO
Mean214582004721004
Standard deviation620561046139
Minimum2010019649200455
Maximum246232243223985
Range452327833940

Share this article on :

Related articles in IJFIS