2013 | OriginalPaper | Buchkapitel
SRCS: A Technique for Comparing Multiple Algorithms under Several Factors in Dynamic Optimization Problems
verfasst von : Ignacio G. del Amo, David A. Pelta
Erschienen in: Metaheuristics for Dynamic Optimization
Verlag: Springer Berlin Heidelberg
Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.
Wählen Sie Textabschnitte aus um mit Künstlicher Intelligenz passenden Patente zu finden. powered by
Markieren Sie Textabschnitte, um KI-gestützt weitere passende Inhalte zu finden. powered by
Performance comparison among several algorithms is an essential task. This is already a difficult process when dealing with stationary problems where the researcher usually tests many algorithms, with several parameters, under different problems. The situation is even more complex when dynamic optimization problems are considered, since additional dynamism-specific configurations should also be analyzed (e.g. severity, frequency and type of the changes, etc). In this work, we present a technique to compact those results in a visual way, improving their understanding and providing an easy way to detect algorithms’ behavioral patterns. However, as every form of compression, it implies the loss of part of the information. The pros and cons of this technique are explained, with a special emphasis on some statistical issues that commonly arise when dealing with random-nature algorithms.