Limits...
Automatic Clustering Using Multi-objective Particle Swarm and Simulated Annealing.

Abubaker A, Baharum A, Alrefaei M - PLoS ONE (2015)

Bottom Line: Three cluster validity indices were optimized simultaneously to establish the suitable number of clusters and the appropriate clustering for a dataset.The first cluster validity index is centred on Euclidean distance, the second on the point symmetry distance, and the last cluster validity index is based on short distance.Computational experiments were carried out to study fourteen artificial and five real life datasets.

View Article: PubMed Central - PubMed

Affiliation: School of Mathematical Sciences, University Sains Malaysia, 11800 USM Penang, Malaysia; Department of Mathematics & Statistics, Al-Imam Muhammad Ibn Saud Islamic University, P.O. Box 90950, 11623 Riyadh, Saudi Arabia.

ABSTRACT
This paper puts forward a new automatic clustering algorithm based on Multi-Objective Particle Swarm Optimization and Simulated Annealing, "MOPSOSA". The proposed algorithm is capable of automatic clustering which is appropriate for partitioning datasets to a suitable number of clusters. MOPSOSA combines the features of the multi-objective based particle swarm optimization (PSO) and the Multi-Objective Simulated Annealing (MOSA). Three cluster validity indices were optimized simultaneously to establish the suitable number of clusters and the appropriate clustering for a dataset. The first cluster validity index is centred on Euclidean distance, the second on the point symmetry distance, and the last cluster validity index is based on short distance. A number of algorithms have been compared with the MOPSOSA algorithm in resolving clustering problems by determining the actual number of clusters and optimal clustering. Computational experiments were carried out to study fourteen artificial and five real life datasets.

No MeSH data available.


Graphs of the artificial datasets.(a) Sph_5_2. (b) Sph_4_3. (c) Sph_6_2. (d) Sph_10_2. (e) Sph_9_2. (f) Pat1. (g) Pat2. (h) Long1. (i) Sizes5. (j) Spiral. (k) Square1. (l) Square4. (m) Twenty. (n) Fourty.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4488466&req=5

pone.0130995.g004: Graphs of the artificial datasets.(a) Sph_5_2. (b) Sph_4_3. (c) Sph_6_2. (d) Sph_10_2. (e) Sph_9_2. (f) Pat1. (g) Pat2. (h) Long1. (i) Sizes5. (j) Spiral. (k) Square1. (l) Square4. (m) Twenty. (n) Fourty.

Mentions: Sph_5_2 [2] dataset (Appendix A in S1 File): This dataset consists of 250-point 2D distributed over five overlapping spherically shaped clusters. Each cluster contains 50 points. Fig 4a illustrates this dataset.


Automatic Clustering Using Multi-objective Particle Swarm and Simulated Annealing.

Abubaker A, Baharum A, Alrefaei M - PLoS ONE (2015)

Graphs of the artificial datasets.(a) Sph_5_2. (b) Sph_4_3. (c) Sph_6_2. (d) Sph_10_2. (e) Sph_9_2. (f) Pat1. (g) Pat2. (h) Long1. (i) Sizes5. (j) Spiral. (k) Square1. (l) Square4. (m) Twenty. (n) Fourty.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4488466&req=5

pone.0130995.g004: Graphs of the artificial datasets.(a) Sph_5_2. (b) Sph_4_3. (c) Sph_6_2. (d) Sph_10_2. (e) Sph_9_2. (f) Pat1. (g) Pat2. (h) Long1. (i) Sizes5. (j) Spiral. (k) Square1. (l) Square4. (m) Twenty. (n) Fourty.
Mentions: Sph_5_2 [2] dataset (Appendix A in S1 File): This dataset consists of 250-point 2D distributed over five overlapping spherically shaped clusters. Each cluster contains 50 points. Fig 4a illustrates this dataset.

Bottom Line: Three cluster validity indices were optimized simultaneously to establish the suitable number of clusters and the appropriate clustering for a dataset.The first cluster validity index is centred on Euclidean distance, the second on the point symmetry distance, and the last cluster validity index is based on short distance.Computational experiments were carried out to study fourteen artificial and five real life datasets.

View Article: PubMed Central - PubMed

Affiliation: School of Mathematical Sciences, University Sains Malaysia, 11800 USM Penang, Malaysia; Department of Mathematics & Statistics, Al-Imam Muhammad Ibn Saud Islamic University, P.O. Box 90950, 11623 Riyadh, Saudi Arabia.

ABSTRACT
This paper puts forward a new automatic clustering algorithm based on Multi-Objective Particle Swarm Optimization and Simulated Annealing, "MOPSOSA". The proposed algorithm is capable of automatic clustering which is appropriate for partitioning datasets to a suitable number of clusters. MOPSOSA combines the features of the multi-objective based particle swarm optimization (PSO) and the Multi-Objective Simulated Annealing (MOSA). Three cluster validity indices were optimized simultaneously to establish the suitable number of clusters and the appropriate clustering for a dataset. The first cluster validity index is centred on Euclidean distance, the second on the point symmetry distance, and the last cluster validity index is based on short distance. A number of algorithms have been compared with the MOPSOSA algorithm in resolving clustering problems by determining the actual number of clusters and optimal clustering. Computational experiments were carried out to study fourteen artificial and five real life datasets.

No MeSH data available.