An ordinal regression approach for the Unequal Area Facility Layout Problem

Áreas de investigación:

• Methodology - Machine learning

Año:

2012

Tipo de publicación:

Artículo en conferencia

Autores:

• Pérez-Ortiz, María
• García-Hernández, Laura
• Salas-Morera, Lorenzo
• Arauzo-Azofra, Antonio
• Hervás-Martínez, César

Título del libro:

Proceedings on the Int. Conference on Soft Computing Models in Industrial and Environmental Applications (SOCO'12)

BibTex:

@conference{UAFLPPerez-2012, author = "Mar{\'i}a P{\'e}rez-Ortiz and Laura Garc{\'i}a-Hern{\'a}ndez and Lorenzo Salas-Morera and Antonio Arauzo-Azofra and C{\'e}sar Herv{\'a}s-Mart{\'i}nez", abstract = "This paper proposes the use of ordinal regression for helping the evaluation of Unequal Area Facility Layouts generated by an interactive genetic algorithm. Using this approach, a model obtained taking into account some objective factors and the subjective evaluation of the experts is constructed. Ordinal regression is used in this case because of the ordinal ranking between the different possible evaluations of the facility layouts made by the experts: {very deficient, deficient, intermediate, good, very good}. To do so, we will also make an approximation to some of the most successful ordinal classification methods in the machine learning literature. The best model obtained will be used in order to guide the searching of a genetic algorithm for generating new facility layouts. ", booktitle = "Proceedings on the Int. Conference on Soft Computing Models in Industrial and Environmental Applications (SOCO{\&}#039;12)", title = "{A}n ordinal regression approach for the {U}nequal {A}rea {F}acility {L}ayout {P}roblem", year = "2012", }

Abstract:

This paper proposes the use of ordinal regression for helping the evaluation of Unequal Area Facility Layouts generated by an interactive genetic algorithm. Using this approach, a model obtained taking into account some objective factors and the subjective evaluation of the experts is constructed. Ordinal regression is used in this case because of the ordinal ranking between the different possible evaluations of the facility layouts made by the experts: {very deficient, deficient, intermediate, good, very good}. To do so, we will also make an approximation to some of the most successful ordinal classification methods in the machine learning literature. The best model obtained will be used in order to guide the searching of a genetic algorithm for generating new facility layouts.