Predicting Real-Time Roadside CO and $\hbox{NO}_{2}$ Concentrations Using Neural Networks
Authors:
- Pietro ZitoPZPietro Zito
- Haibo ChenHCHaibo Chen
- Margaret C. BellMBMargaret C. Bell
- 1 August 2008
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Intelligent Transportation Systems
- Vol. 9 (3) , 514-522
Abstract
The main aim of this paper is to develop a model based on neural network (NN) theory to estimate real-time roadside CO and NO2 concentrations using traffic and meteorological condition data. The location of the study site is at a road intersection in Melton Mowbray, which is a town in Leicestershire, U.K. Several NNs, which can be classified into three types, namely, the multilayer perceptron, the radial basis function, and the modular network, were developed to model the nonlinear relationships that exist in the pollutant concentrations. Their performances are analyzed and compared. The transferability of the developed models is studied using data collected from a road intersection in another city. It was concluded that all NNs provide reliable estimates of pollutant concentrations using limited information and noisy data.Keywords
This publication has 16 references indexed in Scilit:
- Neuroadaptive Combined Lateral and Longitudinal Control of Highway Vehicles Using RBF NetworksIEEE Transactions on Intelligent Transportation Systems, 2006
- Air dispersion model and neural network: A new perspective for integrated models in the simulation of complex situationsEnvironmental Modelling & Software, 2006
- Evaluation of Adaptive Neural Network Models for Freeway Incident DetectionIEEE Transactions on Intelligent Transportation Systems, 2004
- Using Improved Neural Network Model to Analyze RSP, NOx and NO2 Levels in Urban Air in Mong Kok, Hong KongEnvironmental Monitoring and Assessment, 2003
- Prediction of NO and NO2 concentrations near a street with heavy traffic in Santiago, ChileAtmospheric Environment, 2001
- Towards a real-time microscopic emissions modelTransportation Research Part D: Transport and Environment, 2001
- Regression modelling of hourly NOx and NO2 concentrations in urban air in LondonAtmospheric Environment, 1997
- Forecasting carbon monoxide concentrations near a sheltered intersection using video traffic surveillance and neural networksTransportation Research Part D: Transport and Environment, 1996
- Adaptive Mixtures of Local ExpertsNeural Computation, 1991
- Networks for approximation and learningProceedings of the IEEE, 1990