M-ANFIS model to determine the urban travel time with uncertain edges
In this paper, we propose a method to solve the shortest path problem using imprecise variables. The model calculates values for each edge of the network utilize base a fuzzy logic scheme and an adaptive architecture with neural networks. For the uncertainty, the effect of three variables for each street considers the state of the streets, traffic zones, and rainfall (intensity of rain) with an adaptable neural networks architecture. The membership functions experimentally calculate, getting times closer to the real. The model evaluates the uncertainty for each of the network's edges (streets), intending to adjust the set route travel time; finally, the model updates and modifies the membership functions, making it adaptable to new scenarios. The validation is compared with the M-ANFIS travel time model with the fuzzy logic model, probabilistic model, and desired travel time. The mean absolute percentage error of the three models and the travel time compared, obtaining the ANFIS model a lower result.
Copyright (c) 2021 International Journal of Combinatorial Optimization Problems and Informatics
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.