Heterogeneous ensemble learning for enhanced crash forecasts - A frequentist and machine learning based stacking framework.

Journal: Journal of safety research
Published Date: Dec 14, 2022

Abstract

INTRODUCTION: This study aims to increase the prediction accuracy of crash frequency on roadway segments that can forecast future safety on roadway facilities. A variety of statistical and machine learning (ML) methods are used to model crash frequency with ML methods generally having a higher prediction accuracy. Recently, heterogeneous ensemble methods (HEM), including "stacking," have emerged as more accurate and robust intelligent techniques providing more reliable and accurate predictions.

Authors

  • Numan Ahmad
    Department of Civil & Environmental Engineering, The University of Tennessee, Knoxville, TN 37996, USA. Electronic address: nahmad1@vols.utk.edu.
  • Behram Wali
    Urban Design 4 Health, Inc., 24 Jackie Circle, East Rochester, NY 14612, USA. Electronic address: bwali@ud4h.com.
  • Asad J Khattak
    Department of Civil and Environmental Engineering, The University of Tennessee, United States. Electronic address: akhattak@utk.edu.

Keywords

External Resources

Popular Topics
Recent Journals