Comparative Analysis on the Prediction Model of Near-Road CO and PM2.5 Concentration

The time series of particulate matter at urban intersection consists of complex linear and non-linear patterns and are difficult to predict. Wavelet neural network (WNN) model has been applied to air quality prediction in urban areas, but it has limited accuracy owing to the co-linearity between the input variables. To overcome it, a novel hybrid model combining WNN model and factor analysis (FA) is proposed to improve the prediction accuracy. The FC was applied before the WNN model was implemented to generate principal components as input variables, rather than using the original data, to reduce the complexity and eliminate data co-linearity.

Language

  • English

Media Info

  • Media Type: Web
  • Features: References;
  • Pagination: pp 1951-1966
  • Monograph Title: CICTP 2016: Green and Multimodal Transportation and Logistics

Subject/Index Terms

Filing Info

  • Accession Number: 01609285
  • Record Type: Publication
  • ISBN: 9780784479896
  • Files: TRIS, ASCE
  • Created Date: Jun 29 2016 3:07PM