Adaptable anomaly detection in traffic flow time series

Md Rakibul Alam, Ilias Gerostathopoulos, Sasan Amini, Christian Prehofer, Alessandro Attanasi

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

Abstract

Analysis of traffic data is an essential component of many intelligent transportation system applications where the quality of data plays an important role. Traffic data collected through sensors such as loop detectors often contain anomalies, e.g. due to malfunctioning detectors or anomalous traffic conditions. Regardless of the rooting cause, such data can heavily affect the results of the subsequent analysis (e.g.Traffic prediction). There are several challenges regarding anomaly detection, including absence of universal definition of anomaly, change of traffic pattern over time, as well as unavailability of labeled data, use-case driven analysis. In this paper, a new anomaly detection method for traffic univariate time-series is proposed which does not assume labeled historical data yet uses expert feedback to deal with the fluid definition of anomaly. The method is exemplified and evaluated by applying it on real traffic time series data collected through loop detectors installed in an urban road network in Europe. Employing the proposed method as a pre-process of traffic state estimation can increase the accuracy measure as well as ease the learning of different traffic patterns.

Original languageEnglish
Title of host publicationMT-ITS 2019 - 6th International Conference on Models and Technologies for Intelligent Transportation Systems
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538694848
DOIs
Publication statusPublished - 1 Jun 2019
Externally publishedYes
Event6th International Conference on Models and Technologies for Intelligent Transportation Systems, MT-ITS 2019 - Krakow, Poland
Duration: 5 Jun 20197 Jun 2019

Publication series

NameMT-ITS 2019 - 6th International Conference on Models and Technologies for Intelligent Transportation Systems

Conference

Conference6th International Conference on Models and Technologies for Intelligent Transportation Systems, MT-ITS 2019
CountryPoland
CityKrakow
Period5/06/197/06/19

Fingerprint

Flow Time
Anomaly Detection
Traffic Flow
time series
Time series
Traffic
traffic
Detectors
State estimation
Anomaly
Detector
Feedback
Fluids
Sensors
Traffic Analysis
Intelligent Transportation Systems
Essential Component
Road Network
Historical Data
State Estimation

Keywords

  • anomaly detection
  • clustering
  • loop detectors
  • traffic flow time-series

Cite this

Alam, M. R., Gerostathopoulos, I., Amini, S., Prehofer, C., & Attanasi, A. (2019). Adaptable anomaly detection in traffic flow time series. In MT-ITS 2019 - 6th International Conference on Models and Technologies for Intelligent Transportation Systems [8883338] (MT-ITS 2019 - 6th International Conference on Models and Technologies for Intelligent Transportation Systems). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/MTITS.2019.8883338
Alam, Md Rakibul ; Gerostathopoulos, Ilias ; Amini, Sasan ; Prehofer, Christian ; Attanasi, Alessandro. / Adaptable anomaly detection in traffic flow time series. MT-ITS 2019 - 6th International Conference on Models and Technologies for Intelligent Transportation Systems. Institute of Electrical and Electronics Engineers Inc., 2019. (MT-ITS 2019 - 6th International Conference on Models and Technologies for Intelligent Transportation Systems).
@inproceedings{6d9f6ba395b74840a1fc30a163411a3a,
title = "Adaptable anomaly detection in traffic flow time series",
abstract = "Analysis of traffic data is an essential component of many intelligent transportation system applications where the quality of data plays an important role. Traffic data collected through sensors such as loop detectors often contain anomalies, e.g. due to malfunctioning detectors or anomalous traffic conditions. Regardless of the rooting cause, such data can heavily affect the results of the subsequent analysis (e.g.Traffic prediction). There are several challenges regarding anomaly detection, including absence of universal definition of anomaly, change of traffic pattern over time, as well as unavailability of labeled data, use-case driven analysis. In this paper, a new anomaly detection method for traffic univariate time-series is proposed which does not assume labeled historical data yet uses expert feedback to deal with the fluid definition of anomaly. The method is exemplified and evaluated by applying it on real traffic time series data collected through loop detectors installed in an urban road network in Europe. Employing the proposed method as a pre-process of traffic state estimation can increase the accuracy measure as well as ease the learning of different traffic patterns.",
keywords = "anomaly detection, clustering, loop detectors, traffic flow time-series",
author = "Alam, {Md Rakibul} and Ilias Gerostathopoulos and Sasan Amini and Christian Prehofer and Alessandro Attanasi",
year = "2019",
month = "6",
day = "1",
doi = "10.1109/MTITS.2019.8883338",
language = "English",
series = "MT-ITS 2019 - 6th International Conference on Models and Technologies for Intelligent Transportation Systems",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "MT-ITS 2019 - 6th International Conference on Models and Technologies for Intelligent Transportation Systems",
address = "United States",

}

Alam, MR, Gerostathopoulos, I, Amini, S, Prehofer, C & Attanasi, A 2019, Adaptable anomaly detection in traffic flow time series. in MT-ITS 2019 - 6th International Conference on Models and Technologies for Intelligent Transportation Systems., 8883338, MT-ITS 2019 - 6th International Conference on Models and Technologies for Intelligent Transportation Systems, Institute of Electrical and Electronics Engineers Inc., 6th International Conference on Models and Technologies for Intelligent Transportation Systems, MT-ITS 2019, Krakow, Poland, 5/06/19. https://doi.org/10.1109/MTITS.2019.8883338

Adaptable anomaly detection in traffic flow time series. / Alam, Md Rakibul; Gerostathopoulos, Ilias; Amini, Sasan; Prehofer, Christian; Attanasi, Alessandro.

MT-ITS 2019 - 6th International Conference on Models and Technologies for Intelligent Transportation Systems. Institute of Electrical and Electronics Engineers Inc., 2019. 8883338 (MT-ITS 2019 - 6th International Conference on Models and Technologies for Intelligent Transportation Systems).

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Adaptable anomaly detection in traffic flow time series

AU - Alam, Md Rakibul

AU - Gerostathopoulos, Ilias

AU - Amini, Sasan

AU - Prehofer, Christian

AU - Attanasi, Alessandro

PY - 2019/6/1

Y1 - 2019/6/1

N2 - Analysis of traffic data is an essential component of many intelligent transportation system applications where the quality of data plays an important role. Traffic data collected through sensors such as loop detectors often contain anomalies, e.g. due to malfunctioning detectors or anomalous traffic conditions. Regardless of the rooting cause, such data can heavily affect the results of the subsequent analysis (e.g.Traffic prediction). There are several challenges regarding anomaly detection, including absence of universal definition of anomaly, change of traffic pattern over time, as well as unavailability of labeled data, use-case driven analysis. In this paper, a new anomaly detection method for traffic univariate time-series is proposed which does not assume labeled historical data yet uses expert feedback to deal with the fluid definition of anomaly. The method is exemplified and evaluated by applying it on real traffic time series data collected through loop detectors installed in an urban road network in Europe. Employing the proposed method as a pre-process of traffic state estimation can increase the accuracy measure as well as ease the learning of different traffic patterns.

AB - Analysis of traffic data is an essential component of many intelligent transportation system applications where the quality of data plays an important role. Traffic data collected through sensors such as loop detectors often contain anomalies, e.g. due to malfunctioning detectors or anomalous traffic conditions. Regardless of the rooting cause, such data can heavily affect the results of the subsequent analysis (e.g.Traffic prediction). There are several challenges regarding anomaly detection, including absence of universal definition of anomaly, change of traffic pattern over time, as well as unavailability of labeled data, use-case driven analysis. In this paper, a new anomaly detection method for traffic univariate time-series is proposed which does not assume labeled historical data yet uses expert feedback to deal with the fluid definition of anomaly. The method is exemplified and evaluated by applying it on real traffic time series data collected through loop detectors installed in an urban road network in Europe. Employing the proposed method as a pre-process of traffic state estimation can increase the accuracy measure as well as ease the learning of different traffic patterns.

KW - anomaly detection

KW - clustering

KW - loop detectors

KW - traffic flow time-series

UR - http://www.scopus.com/inward/record.url?scp=85074928639&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85074928639&partnerID=8YFLogxK

U2 - 10.1109/MTITS.2019.8883338

DO - 10.1109/MTITS.2019.8883338

M3 - Conference contribution

T3 - MT-ITS 2019 - 6th International Conference on Models and Technologies for Intelligent Transportation Systems

BT - MT-ITS 2019 - 6th International Conference on Models and Technologies for Intelligent Transportation Systems

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Alam MR, Gerostathopoulos I, Amini S, Prehofer C, Attanasi A. Adaptable anomaly detection in traffic flow time series. In MT-ITS 2019 - 6th International Conference on Models and Technologies for Intelligent Transportation Systems. Institute of Electrical and Electronics Engineers Inc. 2019. 8883338. (MT-ITS 2019 - 6th International Conference on Models and Technologies for Intelligent Transportation Systems). https://doi.org/10.1109/MTITS.2019.8883338