Tutorial: Recent Advances and Programs in Swarm Intelligence Algorithms

Self-Organizing Migrating Algorithm (SOMA) belongs to the class of swarm intelligence techniques. SOMA is inspired by competitive-cooperative behavior, uses inherent self-adaptation of movement over the search space, as well as discrete perturbation mimicking the mutation process. The SOMA performs significantly well in both continuous as well as discrete domains. The tutorial will cover several parts.
Firstly, state of the art on the field of swarm intelligence algorithms, similarities and differences between various algorithms and SOMA will be discussed.
The main part of the tutorial will show a collection of principal findings from original research papers discussing current research trends in parameters control, discrete perturbation, novel improvements approaches on and with SOMA from the latest scientific events. New and very efficient strategies like SOMA-T3A (4th place in 100-digit competition), recently published SASOMA, or SOMA-Pareto (6th place in 100-digit competition) will be discussed in detail with demonstrations.
Also, the description of our original concept for the transformation of internal dynamics of swarm algorithms (including SOMA) into the social-like network (social interaction amongst individuals) will be discussed here. Analysis of such a network can be then straightforwardly used as direct feedback into the algorithm for improving its performance.
Finally, the experiences from more than the last 10 years with SOMA, demonstrated on various applications like control engineering, cybersecurity, combinatorial optimization, or computer games, conclude the tutorial