A fuzzy neural approach for vehicle guidance in real-time

Authored by Bo Mi, Dongyan Liu

Date Published: 2017

DOI: 10.1080/10798587.2015.1118274

Sponsors: No sponsors listed

Platforms: No platforms listed

Model Documentation: Other Narrative Mathematical description

Model Code URLs: Model code not found

Abstract

In recent years, neural network has allured much attention of transportation studies due to its competence of addressing traffic complexity. However, design and implementation of such system remains intractable in terms of its opaqueness. Instead, adopting a knowledge-based approach, which can automatically generate a set of expert rules to model the problems, could be a possible solution. To this extent, we devised a fuzzy neural network strategy to optimize the route decision on urban roads in this paper. Our scheme works on an evolutionarily weighted network model, whose resource requirements are adequately alleviated. We also introduced a GA (Genetic Algorithm)-based learning algorithm to obtain the weights of fuzzy system and validated its performance by agent-based modeling.
Tags
Congestion Genetic algorithm decision-support traffic System Vehicle routing guidance Fuzzy neural network Traffic control