Modelling Latent Travel Behaviour Characteristics with Generative Machine Learning

Melvin Wong; Bilal Farooq

doi:10.1109/ITSC.2018.8569581

Modelling Latent Travel Behaviour Characteristics with Generative Machine Learning

Melvin Wong
, Bilal Farooq

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

3 Citations (Scopus)

Abstract

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 significant impact on model likelihood statistics and suggests that machine learning tools are highly suitable for modelling complex networks of conditional independent behaviour interactions.

Original language	English
Title of host publication	2018 21st International Conference on Intelligent Transportation Systems (ITSC)
Publisher	IEEE/LEOS
Pages	749-754
Number of pages	6
ISBN (Electronic)	9781728103235
ISBN (Print)	978-1-7281-0324-2
DOIs	https://doi.org/10.1109/ITSC.2018.8569581
Publication status	Published - 7 Nov 2018
Externally published	Yes
Event	21st IEEE International Conference on Intelligent Transportation Systems, ITSC 2018 - Maui, HI, USA, Maui, United States Duration: 4 Nov 2018 → 7 Nov 2018

Conference

Conference	21st IEEE International Conference on Intelligent Transportation Systems, ITSC 2018
Country/Territory	United States
City	Maui
Period	4/11/18 → 7/11/18

Keywords

Mathematical model
Data models
Numerical analysis
Computational modeling
Stochastic processes
Estimation
Decision making
Restricted Boltzmann machine
latent variable model
semi-supervised learning
statistical methods

Access to Document

10.1109/ITSC.2018.8569581

Cite this

@inproceedings{9eadae9c30e640b6871c37b0d8d4386b,

title = "Modelling Latent Travel Behaviour Characteristics with Generative Machine Learning",

abstract = "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 significant impact on model likelihood statistics and suggests that machine learning tools are highly suitable for modelling complex networks of conditional independent behaviour interactions.",

keywords = "Mathematical model, Data models, Numerical analysis, Computational modeling, Stochastic processes, Estimation, Decision making, Restricted Boltzmann machine, latent variable model, semi-supervised learning, statistical methods",

author = "Melvin Wong and Bilal Farooq",

year = "2018",

month = nov,

day = "7",

doi = "10.1109/ITSC.2018.8569581",

language = "English",

isbn = "978-1-7281-0324-2",

pages = "749--754",

booktitle = "2018 21st International Conference on Intelligent Transportation Systems (ITSC)",

publisher = "IEEE/LEOS",

note = "21st IEEE International Conference on Intelligent Transportation Systems, ITSC 2018 ; Conference date: 04-11-2018 Through 07-11-2018",

}

Wong, M & Farooq, B 2018, Modelling Latent Travel Behaviour Characteristics with Generative Machine Learning. in 2018 21st International Conference on Intelligent Transportation Systems (ITSC)., 8569581, IEEE/LEOS, pp. 749-754, 21st IEEE International Conference on Intelligent Transportation Systems, ITSC 2018, Maui, United States, 4/11/18. https://doi.org/10.1109/ITSC.2018.8569581

TY - GEN

T1 - Modelling Latent Travel Behaviour Characteristics with Generative Machine Learning

AU - Wong, Melvin

AU - Farooq, Bilal

PY - 2018/11/7

Y1 - 2018/11/7

N2 - 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 significant impact on model likelihood statistics and suggests that machine learning tools are highly suitable for modelling complex networks of conditional independent behaviour interactions.

AB - 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 significant impact on model likelihood statistics and suggests that machine learning tools are highly suitable for modelling complex networks of conditional independent behaviour interactions.

KW - Mathematical model

KW - Data models

KW - Numerical analysis

KW - Computational modeling

KW - Stochastic processes

KW - Estimation

KW - Decision making

KW - Restricted Boltzmann machine

KW - latent variable model

KW - semi-supervised learning

KW - statistical methods

UR - https://www.scopus.com/pages/publications/85060432401

U2 - 10.1109/ITSC.2018.8569581

DO - 10.1109/ITSC.2018.8569581

M3 - Conference contribution

SN - 978-1-7281-0324-2

SP - 749

EP - 754

BT - 2018 21st International Conference on Intelligent Transportation Systems (ITSC)

PB - IEEE/LEOS

T2 - 21st IEEE International Conference on Intelligent Transportation Systems, ITSC 2018

Y2 - 4 November 2018 through 7 November 2018

ER -

Modelling Latent Travel Behaviour Characteristics with Generative Machine Learning

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this