A novel data-driven algorithm for the automated detection of unexpectedly high traffic flow in uncongested traffic states

Bo Klaasse, Rik Timmerman (Corresponding author), Tessel van Ballegooijen, Marko Boon, Gerard Eijkelenboom

Research output: Contribution to journalArticleAcademic

5 Downloads (Pure)

Abstract

We present an algorithm to identify days that exhibit the seemingly paradoxical behaviour of high traffic flow and, simultaneously, a striking absence of traffic jams, such days we name high-performance days. The developed algorithm consists of three steps: step 1, based on the fundamental diagram (i.e. an empirical relation between the traffic flow and traffic density), we estimate the critical speed; step 2, based on a labelling of the data, the breakdown probability can be estimated (i.e. the probability that the average speed drops below the critical speed); step 3, we identify unperturbed moments (i.e. moments when a breakdown is expected, but does not occur) and subsequently identify the high-performance days based on the number of unperturbed moments. The algorithm relies on a novel approach to estimate the critical speed; we exploit the roughly linear relation between traffic flow and traffic density in case of no congestion using robust regression as a tool for labelling. In addition, we introduce the notion of high-performance days. Identifying high-performance days could be a building block in the quest for traffic jam reduction; using more detailed data one might be able to identify specific characteristics of high-performance days. The algorithm is applied to a case study featuring the highly congested A15 motorway in the Netherlands.
Original languageEnglish
Article number1909.12782v1
Number of pages15
JournalarXiv
Publication statusPublished - 26 Sep 2019

Fingerprint

Labeling

Cite this

@article{42c1f485df7b444cbe43dee22dd639c7,
title = "A novel data-driven algorithm for the automated detection of unexpectedly high traffic flow in uncongested traffic states",
abstract = "We present an algorithm to identify days that exhibit the seemingly paradoxical behaviour of high traffic flow and, simultaneously, a striking absence of traffic jams, such days we name high-performance days. The developed algorithm consists of three steps: step 1, based on the fundamental diagram (i.e. an empirical relation between the traffic flow and traffic density), we estimate the critical speed; step 2, based on a labelling of the data, the breakdown probability can be estimated (i.e. the probability that the average speed drops below the critical speed); step 3, we identify unperturbed moments (i.e. moments when a breakdown is expected, but does not occur) and subsequently identify the high-performance days based on the number of unperturbed moments. The algorithm relies on a novel approach to estimate the critical speed; we exploit the roughly linear relation between traffic flow and traffic density in case of no congestion using robust regression as a tool for labelling. In addition, we introduce the notion of high-performance days. Identifying high-performance days could be a building block in the quest for traffic jam reduction; using more detailed data one might be able to identify specific characteristics of high-performance days. The algorithm is applied to a case study featuring the highly congested A15 motorway in the Netherlands.",
keywords = "physics.soc-ph",
author = "Bo Klaasse and Rik Timmerman and {van Ballegooijen}, Tessel and Marko Boon and Gerard Eijkelenboom",
year = "2019",
month = "9",
day = "26",
language = "English",
journal = "arXiv",
publisher = "Cornell University Library",

}

A novel data-driven algorithm for the automated detection of unexpectedly high traffic flow in uncongested traffic states. / Klaasse, Bo; Timmerman, Rik (Corresponding author); van Ballegooijen, Tessel ; Boon, Marko; Eijkelenboom, Gerard.

In: arXiv, 26.09.2019.

Research output: Contribution to journalArticleAcademic

TY - JOUR

T1 - A novel data-driven algorithm for the automated detection of unexpectedly high traffic flow in uncongested traffic states

AU - Klaasse, Bo

AU - Timmerman, Rik

AU - van Ballegooijen, Tessel

AU - Boon, Marko

AU - Eijkelenboom, Gerard

PY - 2019/9/26

Y1 - 2019/9/26

N2 - We present an algorithm to identify days that exhibit the seemingly paradoxical behaviour of high traffic flow and, simultaneously, a striking absence of traffic jams, such days we name high-performance days. The developed algorithm consists of three steps: step 1, based on the fundamental diagram (i.e. an empirical relation between the traffic flow and traffic density), we estimate the critical speed; step 2, based on a labelling of the data, the breakdown probability can be estimated (i.e. the probability that the average speed drops below the critical speed); step 3, we identify unperturbed moments (i.e. moments when a breakdown is expected, but does not occur) and subsequently identify the high-performance days based on the number of unperturbed moments. The algorithm relies on a novel approach to estimate the critical speed; we exploit the roughly linear relation between traffic flow and traffic density in case of no congestion using robust regression as a tool for labelling. In addition, we introduce the notion of high-performance days. Identifying high-performance days could be a building block in the quest for traffic jam reduction; using more detailed data one might be able to identify specific characteristics of high-performance days. The algorithm is applied to a case study featuring the highly congested A15 motorway in the Netherlands.

AB - We present an algorithm to identify days that exhibit the seemingly paradoxical behaviour of high traffic flow and, simultaneously, a striking absence of traffic jams, such days we name high-performance days. The developed algorithm consists of three steps: step 1, based on the fundamental diagram (i.e. an empirical relation between the traffic flow and traffic density), we estimate the critical speed; step 2, based on a labelling of the data, the breakdown probability can be estimated (i.e. the probability that the average speed drops below the critical speed); step 3, we identify unperturbed moments (i.e. moments when a breakdown is expected, but does not occur) and subsequently identify the high-performance days based on the number of unperturbed moments. The algorithm relies on a novel approach to estimate the critical speed; we exploit the roughly linear relation between traffic flow and traffic density in case of no congestion using robust regression as a tool for labelling. In addition, we introduce the notion of high-performance days. Identifying high-performance days could be a building block in the quest for traffic jam reduction; using more detailed data one might be able to identify specific characteristics of high-performance days. The algorithm is applied to a case study featuring the highly congested A15 motorway in the Netherlands.

KW - physics.soc-ph

UR - https://arxiv.org/abs/1909.12782

M3 - Article

JO - arXiv

JF - arXiv

M1 - 1909.12782v1

ER -