Cite Article

Improved Self-Adaptive ACS Algorithm to Determine the Optimal Number of Clusters

Choose citation format

BibTeX

@article{IJASEIT11723,
   author = {Ayad Mohammed Jabbar and Ku Ruhana Ku-Mahamud and Rafid Sagban},
   title = {Improved Self-Adaptive ACS Algorithm to Determine the Optimal Number of Clusters},
   journal = {International Journal on Advanced Science, Engineering and Information Technology},
   volume = {11},
   number = {3},
   year = {2021},
   pages = {1092--1099},
   keywords = {Data clustering; parameter selection; optimization-based clustering; ant colony optimization.},
   abstract = {

A fundamental problem in data clustering is how to determine the correct number of clusters. The k-adaptive medoid set ant colony optimization (ACO) clustering (METACOC-K) algorithm is superior in solving clustering problems. However, METACOC-K does not guarantee in finding the best number of clusters. It assumed the number of clusters based on an adaptive parameter strategy that lacks feedback learning. This has restrained the algorithm in producing compact clusters and the optimal number of clusters. In this paper, a self-adaptive ACO clustering (S-ACOC) algorithm is proposed to produce the optimal number of clusters by incorporating a self-adaptive parameter strategy. The S-ACOC algorithm is a centroid-based algorithm that automatically adjusts the number of clusters during the algorithm run. The selection of the number of clusters is based on a construction graph that reflects the influence of a pheromone in algorithm learning. Experiments were conducted on real-world datasets to evaluate the performance of the proposed algorithm. The external evaluation metrics (purity, F-measure, and entropy) were used to compare the results of the proposed algorithm with other swarm clustering algorithms, including a genetic algorithm (GA), particle swarm optimization (PSO), and METACOC-K. Results showed that S-ACOC provides higher purity (50%) and lower entropy (40%) than GA, PSO, and METACOC-K. Experiments were also performed on several predefined clusters, and results demonstrate that the S-ACOC algorithm is superior to GA, PSO, and METACOC-K. Based on the superior performance, S-ACOC can be used to solve clustering problems in various application domains. 

},    issn = {2088-5334},    publisher = {INSIGHT - Indonesian Society for Knowledge and Human Development},    url = {http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=11723},    doi = {10.18517/ijaseit.11.3.11723} }

EndNote

%A Jabbar, Ayad Mohammed
%A Ku-Mahamud, Ku Ruhana
%A Sagban, Rafid
%D 2021
%T Improved Self-Adaptive ACS Algorithm to Determine the Optimal Number of Clusters
%B 2021
%9 Data clustering; parameter selection; optimization-based clustering; ant colony optimization.
%! Improved Self-Adaptive ACS Algorithm to Determine the Optimal Number of Clusters
%K Data clustering; parameter selection; optimization-based clustering; ant colony optimization.
%X 

A fundamental problem in data clustering is how to determine the correct number of clusters. The k-adaptive medoid set ant colony optimization (ACO) clustering (METACOC-K) algorithm is superior in solving clustering problems. However, METACOC-K does not guarantee in finding the best number of clusters. It assumed the number of clusters based on an adaptive parameter strategy that lacks feedback learning. This has restrained the algorithm in producing compact clusters and the optimal number of clusters. In this paper, a self-adaptive ACO clustering (S-ACOC) algorithm is proposed to produce the optimal number of clusters by incorporating a self-adaptive parameter strategy. The S-ACOC algorithm is a centroid-based algorithm that automatically adjusts the number of clusters during the algorithm run. The selection of the number of clusters is based on a construction graph that reflects the influence of a pheromone in algorithm learning. Experiments were conducted on real-world datasets to evaluate the performance of the proposed algorithm. The external evaluation metrics (purity, F-measure, and entropy) were used to compare the results of the proposed algorithm with other swarm clustering algorithms, including a genetic algorithm (GA), particle swarm optimization (PSO), and METACOC-K. Results showed that S-ACOC provides higher purity (50%) and lower entropy (40%) than GA, PSO, and METACOC-K. Experiments were also performed on several predefined clusters, and results demonstrate that the S-ACOC algorithm is superior to GA, PSO, and METACOC-K. Based on the superior performance, S-ACOC can be used to solve clustering problems in various application domains. 

%U http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=11723 %R doi:10.18517/ijaseit.11.3.11723 %J International Journal on Advanced Science, Engineering and Information Technology %V 11 %N 3 %@ 2088-5334

IEEE

Ayad Mohammed Jabbar,Ku Ruhana Ku-Mahamud and Rafid Sagban,"Improved Self-Adaptive ACS Algorithm to Determine the Optimal Number of Clusters," International Journal on Advanced Science, Engineering and Information Technology, vol. 11, no. 3, pp. 1092-1099, 2021. [Online]. Available: http://dx.doi.org/10.18517/ijaseit.11.3.11723.

RefMan/ProCite (RIS)

TY  - JOUR
AU  - Jabbar, Ayad Mohammed
AU  - Ku-Mahamud, Ku Ruhana
AU  - Sagban, Rafid
PY  - 2021
TI  - Improved Self-Adaptive ACS Algorithm to Determine the Optimal Number of Clusters
JF  - International Journal on Advanced Science, Engineering and Information Technology; Vol. 11 (2021) No. 3
Y2  - 2021
SP  - 1092
EP  - 1099
SN  - 2088-5334
PB  - INSIGHT - Indonesian Society for Knowledge and Human Development
KW  - Data clustering; parameter selection; optimization-based clustering; ant colony optimization.
N2  - 

A fundamental problem in data clustering is how to determine the correct number of clusters. The k-adaptive medoid set ant colony optimization (ACO) clustering (METACOC-K) algorithm is superior in solving clustering problems. However, METACOC-K does not guarantee in finding the best number of clusters. It assumed the number of clusters based on an adaptive parameter strategy that lacks feedback learning. This has restrained the algorithm in producing compact clusters and the optimal number of clusters. In this paper, a self-adaptive ACO clustering (S-ACOC) algorithm is proposed to produce the optimal number of clusters by incorporating a self-adaptive parameter strategy. The S-ACOC algorithm is a centroid-based algorithm that automatically adjusts the number of clusters during the algorithm run. The selection of the number of clusters is based on a construction graph that reflects the influence of a pheromone in algorithm learning. Experiments were conducted on real-world datasets to evaluate the performance of the proposed algorithm. The external evaluation metrics (purity, F-measure, and entropy) were used to compare the results of the proposed algorithm with other swarm clustering algorithms, including a genetic algorithm (GA), particle swarm optimization (PSO), and METACOC-K. Results showed that S-ACOC provides higher purity (50%) and lower entropy (40%) than GA, PSO, and METACOC-K. Experiments were also performed on several predefined clusters, and results demonstrate that the S-ACOC algorithm is superior to GA, PSO, and METACOC-K. Based on the superior performance, S-ACOC can be used to solve clustering problems in various application domains. 

UR - http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=11723 DO - 10.18517/ijaseit.11.3.11723

RefWorks

RT Journal Article
ID 11723
A1 Jabbar, Ayad Mohammed
A1 Ku-Mahamud, Ku Ruhana
A1 Sagban, Rafid
T1 Improved Self-Adaptive ACS Algorithm to Determine the Optimal Number of Clusters
JF International Journal on Advanced Science, Engineering and Information Technology
VO 11
IS 3
YR 2021
SP 1092
OP 1099
SN 2088-5334
PB INSIGHT - Indonesian Society for Knowledge and Human Development
K1 Data clustering; parameter selection; optimization-based clustering; ant colony optimization.
AB 

A fundamental problem in data clustering is how to determine the correct number of clusters. The k-adaptive medoid set ant colony optimization (ACO) clustering (METACOC-K) algorithm is superior in solving clustering problems. However, METACOC-K does not guarantee in finding the best number of clusters. It assumed the number of clusters based on an adaptive parameter strategy that lacks feedback learning. This has restrained the algorithm in producing compact clusters and the optimal number of clusters. In this paper, a self-adaptive ACO clustering (S-ACOC) algorithm is proposed to produce the optimal number of clusters by incorporating a self-adaptive parameter strategy. The S-ACOC algorithm is a centroid-based algorithm that automatically adjusts the number of clusters during the algorithm run. The selection of the number of clusters is based on a construction graph that reflects the influence of a pheromone in algorithm learning. Experiments were conducted on real-world datasets to evaluate the performance of the proposed algorithm. The external evaluation metrics (purity, F-measure, and entropy) were used to compare the results of the proposed algorithm with other swarm clustering algorithms, including a genetic algorithm (GA), particle swarm optimization (PSO), and METACOC-K. Results showed that S-ACOC provides higher purity (50%) and lower entropy (40%) than GA, PSO, and METACOC-K. Experiments were also performed on several predefined clusters, and results demonstrate that the S-ACOC algorithm is superior to GA, PSO, and METACOC-K. Based on the superior performance, S-ACOC can be used to solve clustering problems in various application domains. 

LK http://ijaseit.insightsociety.org/index.php?option=com_content&view=article&id=9&Itemid=1&article_id=11723 DO - 10.18517/ijaseit.11.3.11723