D. H. Grass Boada, J. López Fidalgo
With the growing complexity of today's large-scale problems, it has become more fitting to find near-optimal solutions in an acceptable time frame using heuristic approaches. The multiobjective evolutionary algorithms are one of the approaches to the community detection problem in an acceptable time and well effectiveness. However, these algorithms have several parameters that need to be "tuned" before they can reach good results. The problem then turns into "finding best parameter setting" for the algorithm to solve the problems efficiently and timely. In this light, the optimal design techniques can be applied to choose the optimal initial parameters of an algorithm. Hence, Design of Experiments tools can be instead employed to tune the parameters more effectively. A mathematical model is created using regression analysis, and solved to obtain the best parameter setting. After verification runs using the tuned parameter setting, the community structures are were found efficiently.
Palabras clave: parameter tuning problem, multiobjective optimization algoritms, design of experiments
Programado
GT07 Diseño de Experimentos I
8 de junio de 2022 12:40
Sala de Conferencias
