SOMA
Self-Organizing Migrating Algorithm

Publications

Do not see your publication? Then contact us...

New papers:
​TOP and Strong improvements of SOMA performance!!!
Quoc Bao Diep, Ivan Zelinka, and Swagatam Das. 2019. Self-Organizing Migrating Algorithm for the 100-Digit Challenge. In Proceedings of the Genetic and Evolutionary Computation Conference 2019 (GECCO ’19). ACM, New York, NY, USA
ABSTRACT
In this paper, we apply the SOMA T3A algorithm to solve 10 hard problems of the 100-Digit Challenge of the GECCO 2019 Competition. With effective improvements in choosing Migrants and Leader in the organization process, as well as the Step and PRT adaptive parameters in the migration process, the algorithm has achieved promising results. The total score that the algorithm achieved is 92.04 points.The source code of the SOMA T3A algorithm is publicly available at  https://www.mathworks.com/matlabcentral/fileexchange/71328-soma-t3a-for-the-100-digit-challenge-gecco-2019

​TOP and Strong improvements of SOMA performance!!!

Quoc Bao Diep, 2019. Self-Organizing Migrating Algorithm Team To Team Adaptive – SOMA T3A. In Proceedings of the CEC 2019, Wellington, New Zealand
ABSTRACT
Swarm intelligence algorithm and its variants are constantly evolving over the years, the SOMA algorithm is also not out of that trend. In this paper, we propose a novel strategy of SOMA, called SOMA T3A. The proposed algorithm is divided into three main processes, namely Organization, Migration, and Update. Migrants are selected from the initial population and migrate towards the selected Leader according to the organization process. The Step and PRT parameters are no longer fixed like in the original version; instead, they are adapted through each migration loop. The performance of the algorithm is proven on the 58 well-known benchmark problems from the CEC2013 as well as CEC2017 benchmark suites. The results are compared with the SOMA family and compared with the state-of-the-art algorithms to show its promising performance. The source code of the SOMA T3A algorithm is publicly available at  https://www.mathworks.com/matlabcentral/fileexchange/71155-soma-t3a.

TOP and Strong improvements of SOMA performance!!!
Quoc Bao Diep, Ivan Zelinka, and Swagatam Das. 2019. PARETO-BASED SELF-ORGANIZING MIGRATING ALGORITHM. In the  Mendel journal 2019 Brno, Czech Republic
ABSTRACT
In this paper, we propose a new method named Pareto-based self-organizing migrating algorithm (SOMA Pareto), in which the algorithm is divided into the Organization, Migration, and Update processes. The important key in the Organization process is the application of the Pareto Principle to select the Migrant and the Leader, increasing the performance of the algorithm. The adaptive PRT, Step, and PRTVector parameters are applied to enhance the ability to search for promising subspaces and then to focus on exploiting that subspaces. Based on the testing results on the well-known benchmark suites such as CEC’13, CEC’15, and CEC’17, the superior performance of the proposed algorithm compared to the SOMA family and the state-of-the-art algorithms such as variant DE and PSO are confirmed. These results demonstrate that SOMA Pareto is an effective, promising algorithm.The source code of the PSOMA algorithm is publicly available at  https://www.mathworks.com/matlabcentral/fileexchange/71724-soma-pareto

Older papers: