Machine Learning Approach to Decomposing Arterial Travel Time Using a Hidden Markov Model with Genetic Algorithm

Shu Yang, Ming Chen, Yao-jan Wu, Chengchuan An

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

Bluetooth-based traffic detection is an emerging travel time collection technique; however, its use on arterials has been limited due to several challenges. In particular, data missing not at random (MNAR) is a common data set problem caused by system network failure or sensor malfunctioning. Solving the MNAR problem requires travel-time decomposition (TTD) using complete travel times spanning successive links. Previous work has focused on TTD methodologies that use probe vehicle data. However, these approaches may be unsuitable for Bluetooth-based data. Therefore, this study proposes a machine learning-based approach to decomposing Bluetooth-based travel time. A modified hidden Markov model was developed to model travel-time distributions and traffic-state transitions. A genetic algorithm (GA) was applied to solve a numerical optimal decomposition based on maximum likelihood. Two real-world travel-time data sets were used for validation of the approach. The proposed hidden Markov chain with GA (HMMGA) approach and Gaussian mixture model with GA (GMMGA) were compared with a benchmark approach using distance-based allocation. The results showed that the HMMGA significantly outperformed both the GMMGA and benchmark approaches. Using the HMMGA, the average mean absolute percentage error was up to 72% lower compared to the benchmark approach.

Original languageEnglish (US)
Article number04018005
JournalJournal of Computing in Civil Engineering
Volume32
Issue number3
DOIs
StatePublished - May 1 2018

Fingerprint

Travel time
Hidden Markov models
Learning systems
Genetic algorithms
Bluetooth
Decomposition
Markov processes
Maximum likelihood
Sensors

Keywords

  • Bluetooth-based travel time
  • Gaussian mixture model
  • Genetic algorithm
  • Hidden Markov model
  • Missing not at random
  • Travel-time decomposition

ASJC Scopus subject areas

  • Civil and Structural Engineering
  • Computer Science Applications

Cite this

Machine Learning Approach to Decomposing Arterial Travel Time Using a Hidden Markov Model with Genetic Algorithm. / Yang, Shu; Chen, Ming; Wu, Yao-jan; An, Chengchuan.

In: Journal of Computing in Civil Engineering, Vol. 32, No. 3, 04018005, 01.05.2018.

Research output: Contribution to journalArticle

@article{47baf37292a940b8a5e1b3ff01482c48,
title = "Machine Learning Approach to Decomposing Arterial Travel Time Using a Hidden Markov Model with Genetic Algorithm",
abstract = "Bluetooth-based traffic detection is an emerging travel time collection technique; however, its use on arterials has been limited due to several challenges. In particular, data missing not at random (MNAR) is a common data set problem caused by system network failure or sensor malfunctioning. Solving the MNAR problem requires travel-time decomposition (TTD) using complete travel times spanning successive links. Previous work has focused on TTD methodologies that use probe vehicle data. However, these approaches may be unsuitable for Bluetooth-based data. Therefore, this study proposes a machine learning-based approach to decomposing Bluetooth-based travel time. A modified hidden Markov model was developed to model travel-time distributions and traffic-state transitions. A genetic algorithm (GA) was applied to solve a numerical optimal decomposition based on maximum likelihood. Two real-world travel-time data sets were used for validation of the approach. The proposed hidden Markov chain with GA (HMMGA) approach and Gaussian mixture model with GA (GMMGA) were compared with a benchmark approach using distance-based allocation. The results showed that the HMMGA significantly outperformed both the GMMGA and benchmark approaches. Using the HMMGA, the average mean absolute percentage error was up to 72{\%} lower compared to the benchmark approach.",
keywords = "Bluetooth-based travel time, Gaussian mixture model, Genetic algorithm, Hidden Markov model, Missing not at random, Travel-time decomposition",
author = "Shu Yang and Ming Chen and Yao-jan Wu and Chengchuan An",
year = "2018",
month = "5",
day = "1",
doi = "10.1061/(ASCE)CP.1943-5487.0000749",
language = "English (US)",
volume = "32",
journal = "Journal of Computing in Civil Engineering",
issn = "0887-3801",
publisher = "American Society of Civil Engineers (ASCE)",
number = "3",

}

TY - JOUR

T1 - Machine Learning Approach to Decomposing Arterial Travel Time Using a Hidden Markov Model with Genetic Algorithm

AU - Yang, Shu

AU - Chen, Ming

AU - Wu, Yao-jan

AU - An, Chengchuan

PY - 2018/5/1

Y1 - 2018/5/1

N2 - Bluetooth-based traffic detection is an emerging travel time collection technique; however, its use on arterials has been limited due to several challenges. In particular, data missing not at random (MNAR) is a common data set problem caused by system network failure or sensor malfunctioning. Solving the MNAR problem requires travel-time decomposition (TTD) using complete travel times spanning successive links. Previous work has focused on TTD methodologies that use probe vehicle data. However, these approaches may be unsuitable for Bluetooth-based data. Therefore, this study proposes a machine learning-based approach to decomposing Bluetooth-based travel time. A modified hidden Markov model was developed to model travel-time distributions and traffic-state transitions. A genetic algorithm (GA) was applied to solve a numerical optimal decomposition based on maximum likelihood. Two real-world travel-time data sets were used for validation of the approach. The proposed hidden Markov chain with GA (HMMGA) approach and Gaussian mixture model with GA (GMMGA) were compared with a benchmark approach using distance-based allocation. The results showed that the HMMGA significantly outperformed both the GMMGA and benchmark approaches. Using the HMMGA, the average mean absolute percentage error was up to 72% lower compared to the benchmark approach.

AB - Bluetooth-based traffic detection is an emerging travel time collection technique; however, its use on arterials has been limited due to several challenges. In particular, data missing not at random (MNAR) is a common data set problem caused by system network failure or sensor malfunctioning. Solving the MNAR problem requires travel-time decomposition (TTD) using complete travel times spanning successive links. Previous work has focused on TTD methodologies that use probe vehicle data. However, these approaches may be unsuitable for Bluetooth-based data. Therefore, this study proposes a machine learning-based approach to decomposing Bluetooth-based travel time. A modified hidden Markov model was developed to model travel-time distributions and traffic-state transitions. A genetic algorithm (GA) was applied to solve a numerical optimal decomposition based on maximum likelihood. Two real-world travel-time data sets were used for validation of the approach. The proposed hidden Markov chain with GA (HMMGA) approach and Gaussian mixture model with GA (GMMGA) were compared with a benchmark approach using distance-based allocation. The results showed that the HMMGA significantly outperformed both the GMMGA and benchmark approaches. Using the HMMGA, the average mean absolute percentage error was up to 72% lower compared to the benchmark approach.

KW - Bluetooth-based travel time

KW - Gaussian mixture model

KW - Genetic algorithm

KW - Hidden Markov model

KW - Missing not at random

KW - Travel-time decomposition

UR - http://www.scopus.com/inward/record.url?scp=85041455353&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85041455353&partnerID=8YFLogxK

U2 - 10.1061/(ASCE)CP.1943-5487.0000749

DO - 10.1061/(ASCE)CP.1943-5487.0000749

M3 - Article

VL - 32

JO - Journal of Computing in Civil Engineering

JF - Journal of Computing in Civil Engineering

SN - 0887-3801

IS - 3

M1 - 04018005

ER -