In a large number of experimental problems the high dimensionality of the search space and economical constraints can severely limit the number of experiment points that can be tested. Under this constraints, optimization techniques perform poorly in particular when little a priori knowledge is available. In this work we investigate the possibility of combining approaches from advanced statistics and optimization algorithms to effectively explore a combinatorial search space sampling a limited number of experimental points. To this purpose we propose the Naïve Bayes Ant Colony Optimization (NACO) procedure. We tested its performance in a simulation study. © 2013 Springer-Verlag.
CITATION STYLE
Borrotti, M., & Poli, I. (2013). Naïve Bayes ant colony optimization for experimental design. In Advances in Intelligent Systems and Computing (Vol. 190 AISC, pp. 489–497). Springer Verlag. https://doi.org/10.1007/978-3-642-33042-1_52
Mendeley helps you to discover research relevant for your work.