In-Cognitive: A web-based Python application for fuzzy cognitive map design, simulation, and uncertainty analysis based on the Monte Carlo method
Themistoklis Koutsellis,
Georgios Xexakis,
Konstantinos Koasidis,
Natasha Frilingou,
Anastasios Karamaneas,
Alexandros Nikas,
Haris Doukas
Affiliations
Themistoklis Koutsellis
Decision Support Systems Laboratory, School of Electrical & Computer Engineering, National Technical University of Athens, Iroon Politechniou 9, 15780, Athens, Greece
Decision Support Systems Laboratory, School of Electrical & Computer Engineering, National Technical University of Athens, Iroon Politechniou 9, 15780, Athens, Greece
Natasha Frilingou
Decision Support Systems Laboratory, School of Electrical & Computer Engineering, National Technical University of Athens, Iroon Politechniou 9, 15780, Athens, Greece
Anastasios Karamaneas
Decision Support Systems Laboratory, School of Electrical & Computer Engineering, National Technical University of Athens, Iroon Politechniou 9, 15780, Athens, Greece
Alexandros Nikas
Decision Support Systems Laboratory, School of Electrical & Computer Engineering, National Technical University of Athens, Iroon Politechniou 9, 15780, Athens, Greece
Haris Doukas
Decision Support Systems Laboratory, School of Electrical & Computer Engineering, National Technical University of Athens, Iroon Politechniou 9, 15780, Athens, Greece
Fuzzy Cognitive Mapping is a semi-quantitative modelling method, widely used for decision support in various domains. However, existing software applications have been criticised over inadequate handling of uncertain information, lack of accessibility, and inability to converge to solutions for all modelled systems. Here we present In-Cognitive, an open-source, web-based application for the creation, visualisation, and simulation of Fuzzy Cognitive Maps, ensuring solution convergence and allowing for Monte Carlo uncertainty analysis. The application is built in Python and Bokeh and provides an accessible and user-friendly interface to model various systems quickly and reliably and evaluate the robustness of the modelling solutions.
