Development a Quantitative Framework for Multilayer Fuzzy Cognitive Maps by combining "Self-Organizing Map" and "Graph Theory and Matrix Approach" (SOM-GTMA)

Objective: The purpose of this study is to develop and improve the multilayer fuzzy cognitive maps in structuring and analysis of problems with high dimensions by providing a quantitative framework. Methods: In this study, the Self-Organizing Map method and Graph Theory and Matrix Approach has been...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autores principales: Mohammad Ali Sangbor, Mohammad Reza Safi, Adel Azar, Masood Rabieh
Formato: article
Lenguaje:FA
Publicado: University of Tehran 2021
Materias:
Acceso en línea:https://doaj.org/article/995171f85b434d1faee90100d3e48c4e
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
Descripción
Sumario:Objective: The purpose of this study is to develop and improve the multilayer fuzzy cognitive maps in structuring and analysis of problems with high dimensions by providing a quantitative framework. Methods: In this study, the Self-Organizing Map method and Graph Theory and Matrix Approach has been combined in the multilayer fuzzy cognitive maps approach. Based on this approach, problem structuring is done by clustering and creating a multilayer structure for cognitive mapping. Results: The developed method in the present study has been used to analyze the problem of sustainable supply chain management achievement in the petrochemical industry. According to the results of data analysis based on the presented approach, "cooperation in the supply chain", "organizational development" and "management commitment to sustainable development" are the most effective factors in enabling sustainable supply chain management. Conclusion: Based on the method presented in the present study, the problem is modeled by clustering components and creating a multilayer structure for cognitive mapping. The method presented in the present study can model problems with a large number of intervening variables. The proposed method in this study can model problems with a high number of variables.