LGMLSep 15, 2018

Modelling Latent Travel Behaviour Characteristics with Generative Machine Learning

arXiv:1809.05781v15 citations
Originality Synthesis-oriented
AI Analysis

This work addresses travel behavior analysis for transportation researchers, but it is incremental as it applies an existing generative method to a new domain-specific dataset.

The paper tackled the problem of identifying latent characteristics in travel decision making by introducing a generative modelling framework based on a Restricted Boltzmann Machine, applied to mode choice survey data from Quebec, Canada. Results showed a significant impact on model likelihood statistics, indicating the suitability of machine learning for modelling complex behavior interactions.

In this paper, we implement an information-theoretic approach to travel behaviour analysis by introducing a generative modelling framework to identify informative latent characteristics in travel decision making. It involves developing a joint tri-partite Bayesian graphical network model using a Restricted Boltzmann Machine (RBM) generative modelling framework. We apply this framework on a mode choice survey data to identify abstract latent variables and compare the performance with a traditional latent variable model with specific latent preferences -- safety, comfort, and environmental. Data collected from a joint stated and revealed preference mode choice survey in Quebec, Canada were used to calibrate the RBM model. Results show that a signficant impact on model likelihood statistics and suggests that machine learning tools are highly suitable for modelling complex networks of conditional independent behaviour interactions.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes