Highlights A multi-objective heterogeneous genetically optimized surrogate modeling approach is proposed. An application of the proposed framework to short-term travel speed forecasting in presented. Support Vector Machines, Radial Base Functions and Neural Networks are jointly optimized. Results are discussed in both a univariate and multivariate framework. Surrogate models may accurately predict speeds with limited sampling attempts.
Abstract Transportation modelers are frequently faced with several optimization challenges related to model selection and parameter optimization for forecasting. The concept of surrogate modeling is discussed in order to tackle some limitations related to the practice of developing short-term forecasting algorithms. An automated meta-modeling technique is presented that uses heterogeneous information from multiple types of statistical and computationally intelligent models, along with multi-objective evolutionary strategies to optimize the model and parameter selection. A number of different models from the family of Support Vector Machines, Radial Base Functions and Neural Networks are jointly considered and optimized with the aim to improve the short-term predictability of travel speed. Results are presented and discussed in both a univariate and multivariate framework.
Optimization of traffic forecasting: Intelligent surrogate modeling
2015-03-10
10 pages
Article (Journal)
Electronic Resource
English
Optimization of traffic forecasting: Intelligent surrogate modeling
Online Contents | 2015
|TRAFFIC FORECASTING SYSTEM, TRAFFIC FORECASTING DEVICE, AND TRAFFIC FORECASTING METHOD
European Patent Office | 2021
|Optimization of traffic signal timings based on surrogate measures of safety
Online Contents | 2013
|Surrogate-based optimization of cordon toll levels in congested traffic networks
Online Contents | 2016
|