Publications / 2015 Proceedings of the 32nd ISARC, Oulu, Finland

Predicting Carbon Monoxide Emissions with Multivariate Adaptive Regression Splines (MARS) and Artificial Neural Networks (ANNs)

Seth Daniel Oduro, Santanu Metia, Hiep Duc, Quang P. Ha
Pages 1-9 (2015 Proceedings of the 32nd ISARC, Oulu, Finland, ISBN 978-951-758-597-2, ISSN 2413-5844)
Abstract:

Emissions from motor vehicles need to be predicted to ensure appropriate air quality plans. Two most popular techniques for emission data collection are the on-board measurement and dynamometer testing. This research work explores the use of a nonparametric regression algorithm known as the multivariate adaptive regression splines (MARS) in comparison with the artificial neural networks (ANN) for the purpose of best approximation of the relationship between the input and output from datasets recorded. The performance of the models was evaluated by comparing the MARS and ANN predictions to the measured data using several performance indices. The results are evaluated in terms of accuracy, flexibility and computational efficiency. They indicate that MARS are more computationally-efficient in terms of computing time to reach the final model while ANN are slightly more accurate. The proposed techniques may be used to assist in a decision-making policy regarding urban air pollution.

Keywords: Carbon Monoxide, On-Board Emission Measurement System, Chassis Dyanamometer Testing System, Emission.