Skip to main navigation Skip to search Skip to main content

Model-based machine learning for transportation

Research output: Chapter in Book/Report/Conference proceeding › Book chapter › Research › peer-review

Abstract

The world around us is rich with uncertainty, possibly because of innate nondeterminism. In the transportation domain alone, one finds uncertainty in, for example, road safety, train delays, bus dwell times, or passengers’ choice of travel mode. Models of reality must therefore account for such prevalent uncertainty. Consequently, at the heart of modern machine learning is probability theory, which provides a consistent framework for quantifying and manipulating uncertainty.
Original languageEnglish
Title of host publicationMobility Patterns, Big Data and Transport Analytics : Tools and Applications for Modeling
Publication date2026
Pages151-181
Chapter7
DOIs
Publication statusPublished - 2026

Keywords

  • Probabilistic graphical models
  • Bayesian framework
  • Domain knowledge
  • Machine learning theory

Fingerprint

Dive into the research topics of 'Model-based machine learning for transportation'. Together they form a unique fingerprint.

Cite this