Predicting vehicular travel times by modeling heterogeneous influences between arterial roads

Avinash Achar, Venkatesh Sarangan, Rohith Regikumar, Anand Sivasubramaniam

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Citations (Scopus)

Abstract

Predicting travel times of vehicles in urban settings is a useful and tangible quantity of interest in the context of intelligent transportation systems. We address the problem of travel time prediction in arterial roads using data sampled from probe vehicles. There is only a limited literature on methods using data input from probe vehicles. The spatio-temporal dependencies captured by existing data driven approaches are either too detailed or very simplistic. We strike a balance of the existing data driven approaches to account for varying degrees of influence a given road may experience from its neighbors, while controlling the number of parameters to be learnt. Specifically, we use a NoisyOR conditional probability distribution (CPD) in conjunction with a dynamic Bayesian network (DBN) to model state transitions of various roads. We propose an efficient algorithm to learn model parameters. We also propose an algorithm for predicting travel times on trips of arbitrary durations. Using synthetic and real world data traces we demonstrate the superior performance of the proposed method under different traffic conditions.

Original languageEnglish (US)
Title of host publication32nd AAAI Conference on Artificial Intelligence, AAAI 2018
PublisherAAAI press
Pages2063-2070
Number of pages8
ISBN (Electronic)9781577358008
StatePublished - Jan 1 2018
Event32nd AAAI Conference on Artificial Intelligence, AAAI 2018 - New Orleans, United States
Duration: Feb 2 2018Feb 7 2018

Publication series

Name32nd AAAI Conference on Artificial Intelligence, AAAI 2018

Other

Other32nd AAAI Conference on Artificial Intelligence, AAAI 2018
CountryUnited States
CityNew Orleans
Period2/2/182/7/18

Fingerprint

Travel time
Bayesian networks
Probability distributions

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Cite this

Achar, A., Sarangan, V., Regikumar, R., & Sivasubramaniam, A. (2018). Predicting vehicular travel times by modeling heterogeneous influences between arterial roads. In 32nd AAAI Conference on Artificial Intelligence, AAAI 2018 (pp. 2063-2070). (32nd AAAI Conference on Artificial Intelligence, AAAI 2018). AAAI press.
Achar, Avinash ; Sarangan, Venkatesh ; Regikumar, Rohith ; Sivasubramaniam, Anand. / Predicting vehicular travel times by modeling heterogeneous influences between arterial roads. 32nd AAAI Conference on Artificial Intelligence, AAAI 2018. AAAI press, 2018. pp. 2063-2070 (32nd AAAI Conference on Artificial Intelligence, AAAI 2018).
@inproceedings{731d707b89854aa6ada2157ff13a032b,
title = "Predicting vehicular travel times by modeling heterogeneous influences between arterial roads",
abstract = "Predicting travel times of vehicles in urban settings is a useful and tangible quantity of interest in the context of intelligent transportation systems. We address the problem of travel time prediction in arterial roads using data sampled from probe vehicles. There is only a limited literature on methods using data input from probe vehicles. The spatio-temporal dependencies captured by existing data driven approaches are either too detailed or very simplistic. We strike a balance of the existing data driven approaches to account for varying degrees of influence a given road may experience from its neighbors, while controlling the number of parameters to be learnt. Specifically, we use a NoisyOR conditional probability distribution (CPD) in conjunction with a dynamic Bayesian network (DBN) to model state transitions of various roads. We propose an efficient algorithm to learn model parameters. We also propose an algorithm for predicting travel times on trips of arbitrary durations. Using synthetic and real world data traces we demonstrate the superior performance of the proposed method under different traffic conditions.",
author = "Avinash Achar and Venkatesh Sarangan and Rohith Regikumar and Anand Sivasubramaniam",
year = "2018",
month = "1",
day = "1",
language = "English (US)",
series = "32nd AAAI Conference on Artificial Intelligence, AAAI 2018",
publisher = "AAAI press",
pages = "2063--2070",
booktitle = "32nd AAAI Conference on Artificial Intelligence, AAAI 2018",

}

Achar, A, Sarangan, V, Regikumar, R & Sivasubramaniam, A 2018, Predicting vehicular travel times by modeling heterogeneous influences between arterial roads. in 32nd AAAI Conference on Artificial Intelligence, AAAI 2018. 32nd AAAI Conference on Artificial Intelligence, AAAI 2018, AAAI press, pp. 2063-2070, 32nd AAAI Conference on Artificial Intelligence, AAAI 2018, New Orleans, United States, 2/2/18.

Predicting vehicular travel times by modeling heterogeneous influences between arterial roads. / Achar, Avinash; Sarangan, Venkatesh; Regikumar, Rohith; Sivasubramaniam, Anand.

32nd AAAI Conference on Artificial Intelligence, AAAI 2018. AAAI press, 2018. p. 2063-2070 (32nd AAAI Conference on Artificial Intelligence, AAAI 2018).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Predicting vehicular travel times by modeling heterogeneous influences between arterial roads

AU - Achar, Avinash

AU - Sarangan, Venkatesh

AU - Regikumar, Rohith

AU - Sivasubramaniam, Anand

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Predicting travel times of vehicles in urban settings is a useful and tangible quantity of interest in the context of intelligent transportation systems. We address the problem of travel time prediction in arterial roads using data sampled from probe vehicles. There is only a limited literature on methods using data input from probe vehicles. The spatio-temporal dependencies captured by existing data driven approaches are either too detailed or very simplistic. We strike a balance of the existing data driven approaches to account for varying degrees of influence a given road may experience from its neighbors, while controlling the number of parameters to be learnt. Specifically, we use a NoisyOR conditional probability distribution (CPD) in conjunction with a dynamic Bayesian network (DBN) to model state transitions of various roads. We propose an efficient algorithm to learn model parameters. We also propose an algorithm for predicting travel times on trips of arbitrary durations. Using synthetic and real world data traces we demonstrate the superior performance of the proposed method under different traffic conditions.

AB - Predicting travel times of vehicles in urban settings is a useful and tangible quantity of interest in the context of intelligent transportation systems. We address the problem of travel time prediction in arterial roads using data sampled from probe vehicles. There is only a limited literature on methods using data input from probe vehicles. The spatio-temporal dependencies captured by existing data driven approaches are either too detailed or very simplistic. We strike a balance of the existing data driven approaches to account for varying degrees of influence a given road may experience from its neighbors, while controlling the number of parameters to be learnt. Specifically, we use a NoisyOR conditional probability distribution (CPD) in conjunction with a dynamic Bayesian network (DBN) to model state transitions of various roads. We propose an efficient algorithm to learn model parameters. We also propose an algorithm for predicting travel times on trips of arbitrary durations. Using synthetic and real world data traces we demonstrate the superior performance of the proposed method under different traffic conditions.

UR - http://www.scopus.com/inward/record.url?scp=85060480485&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85060480485&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85060480485

T3 - 32nd AAAI Conference on Artificial Intelligence, AAAI 2018

SP - 2063

EP - 2070

BT - 32nd AAAI Conference on Artificial Intelligence, AAAI 2018

PB - AAAI press

ER -

Achar A, Sarangan V, Regikumar R, Sivasubramaniam A. Predicting vehicular travel times by modeling heterogeneous influences between arterial roads. In 32nd AAAI Conference on Artificial Intelligence, AAAI 2018. AAAI press. 2018. p. 2063-2070. (32nd AAAI Conference on Artificial Intelligence, AAAI 2018).