Dynamic Spatio-temporal Integration of Traffic Accident Data

Ove Andersen, Kristian Torp

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

Abstract

Up to 50% of delay in traffic is due to non-reoccurring events such as traffic accidents. Accidents lead to delays, which can be costly for transport companies. Road authorities are also very interested in warning drivers about accidents, e.g., to reroute them. This paper presents a novel and efficient approach and system for uncovering effects from traffic accidents by dynamic integration of GPS, weather, and traffic-accident data. This integration makes it possible to explore and quantify how accidents affects traffic. Dynamic integration means that data is combined at query time as it becomes available. This is necessary, because data can be missing (weather station down) or late arriving (accident not officially reported by the police yet). Further, the integration can be parameterized by the user, e.g., distance to accident, which is important due to inaccuracy in reporting. We present the integrated data on a map and show the
effectiveness of the integration by allowing users to interactively browse all accidents or pick a single accident to study it in very fine-grained details. Using information from 31 433 road accidents and 38 billion GPS records, we show that the proposed dynamic data integration scales so very large data sets.
Original languageEnglish
Title of host publicationProceedings of the 26th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems
EditorsLi Xiong, Roberto Tamassia, Kashani Farnoush Banaei, Ralf Hartmut Guting, Erik Hoel
Number of pages4
PublisherAssociation for Computing Machinery
Publication date6 Nov 2018
Pages596-599
ISBN (Print)978-1-4503-5889-7
ISBN (Electronic)9781450358897
DOIs
Publication statusPublished - 6 Nov 2018
EventACM SIGSPATIAL GIS 2018 - Seattle Marriott Waterfront, Seattle, United States
Duration: 6 Nov 20189 Nov 2018
Conference number: 26
https://sigspatial2018.sigspatial.org/

Conference

ConferenceACM SIGSPATIAL GIS 2018
Number26
Location Seattle Marriott Waterfront
CountryUnited States
CitySeattle
Period06/11/201809/11/2018
Internet address

Keywords

  • Data integration
  • GPS
  • Spatio-temporal
  • Traffic accidents
  • Weather

Cite this

Andersen, O., & Torp, K. (2018). Dynamic Spatio-temporal Integration of Traffic Accident Data. In L. Xiong, R. Tamassia, K. F. Banaei, R. H. Guting, & E. Hoel (Eds.), Proceedings of the 26th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems (pp. 596-599). Association for Computing Machinery. https://doi.org/10.1145/3274895.3274972
Andersen, Ove ; Torp, Kristian. / Dynamic Spatio-temporal Integration of Traffic Accident Data. Proceedings of the 26th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems . editor / Li Xiong ; Roberto Tamassia ; Kashani Farnoush Banaei ; Ralf Hartmut Guting ; Erik Hoel. Association for Computing Machinery, 2018. pp. 596-599
@inproceedings{5a10df48a4d5444480ef4d8e97e66db2,
title = "Dynamic Spatio-temporal Integration of Traffic Accident Data",
abstract = "Up to 50{\%} of delay in traffic is due to non-reoccurring events such as traffic accidents. Accidents lead to delays, which can be costly for transport companies. Road authorities are also very interested in warning drivers about accidents, e.g., to reroute them. This paper presents a novel and efficient approach and system for uncovering effects from traffic accidents by dynamic integration of GPS, weather, and traffic-accident data. This integration makes it possible to explore and quantify how accidents affects traffic. Dynamic integration means that data is combined at query time as it becomes available. This is necessary, because data can be missing (weather station down) or late arriving (accident not officially reported by the police yet). Further, the integration can be parameterized by the user, e.g., distance to accident, which is important due to inaccuracy in reporting. We present the integrated data on a map and show theeffectiveness of the integration by allowing users to interactively browse all accidents or pick a single accident to study it in very fine-grained details. Using information from 31 433 road accidents and 38 billion GPS records, we show that the proposed dynamic data integration scales so very large data sets.",
keywords = "Data integration, GPS, Spatio-temporal, Traffic accidents, Weather",
author = "Ove Andersen and Kristian Torp",
year = "2018",
month = "11",
day = "6",
doi = "10.1145/3274895.3274972",
language = "English",
isbn = "978-1-4503-5889-7",
pages = "596--599",
editor = "Li Xiong and Roberto Tamassia and Banaei, {Kashani Farnoush} and Guting, {Ralf Hartmut} and Erik Hoel",
booktitle = "Proceedings of the 26th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems",
publisher = "Association for Computing Machinery",
address = "United States",

}

Andersen, O & Torp, K 2018, Dynamic Spatio-temporal Integration of Traffic Accident Data. in L Xiong, R Tamassia, KF Banaei, RH Guting & E Hoel (eds), Proceedings of the 26th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems . Association for Computing Machinery, pp. 596-599, ACM SIGSPATIAL GIS 2018, Seattle, United States, 06/11/2018. https://doi.org/10.1145/3274895.3274972

Dynamic Spatio-temporal Integration of Traffic Accident Data. / Andersen, Ove; Torp, Kristian.

Proceedings of the 26th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems . ed. / Li Xiong; Roberto Tamassia; Kashani Farnoush Banaei; Ralf Hartmut Guting; Erik Hoel. Association for Computing Machinery, 2018. p. 596-599.

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - Dynamic Spatio-temporal Integration of Traffic Accident Data

AU - Andersen, Ove

AU - Torp, Kristian

PY - 2018/11/6

Y1 - 2018/11/6

N2 - Up to 50% of delay in traffic is due to non-reoccurring events such as traffic accidents. Accidents lead to delays, which can be costly for transport companies. Road authorities are also very interested in warning drivers about accidents, e.g., to reroute them. This paper presents a novel and efficient approach and system for uncovering effects from traffic accidents by dynamic integration of GPS, weather, and traffic-accident data. This integration makes it possible to explore and quantify how accidents affects traffic. Dynamic integration means that data is combined at query time as it becomes available. This is necessary, because data can be missing (weather station down) or late arriving (accident not officially reported by the police yet). Further, the integration can be parameterized by the user, e.g., distance to accident, which is important due to inaccuracy in reporting. We present the integrated data on a map and show theeffectiveness of the integration by allowing users to interactively browse all accidents or pick a single accident to study it in very fine-grained details. Using information from 31 433 road accidents and 38 billion GPS records, we show that the proposed dynamic data integration scales so very large data sets.

AB - Up to 50% of delay in traffic is due to non-reoccurring events such as traffic accidents. Accidents lead to delays, which can be costly for transport companies. Road authorities are also very interested in warning drivers about accidents, e.g., to reroute them. This paper presents a novel and efficient approach and system for uncovering effects from traffic accidents by dynamic integration of GPS, weather, and traffic-accident data. This integration makes it possible to explore and quantify how accidents affects traffic. Dynamic integration means that data is combined at query time as it becomes available. This is necessary, because data can be missing (weather station down) or late arriving (accident not officially reported by the police yet). Further, the integration can be parameterized by the user, e.g., distance to accident, which is important due to inaccuracy in reporting. We present the integrated data on a map and show theeffectiveness of the integration by allowing users to interactively browse all accidents or pick a single accident to study it in very fine-grained details. Using information from 31 433 road accidents and 38 billion GPS records, we show that the proposed dynamic data integration scales so very large data sets.

KW - Data integration

KW - GPS

KW - Spatio-temporal

KW - Traffic accidents

KW - Weather

UR - http://www.scopus.com/inward/record.url?scp=85058646228&partnerID=8YFLogxK

U2 - 10.1145/3274895.3274972

DO - 10.1145/3274895.3274972

M3 - Article in proceeding

SN - 978-1-4503-5889-7

SP - 596

EP - 599

BT - Proceedings of the 26th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems

A2 - Xiong, Li

A2 - Tamassia, Roberto

A2 - Banaei, Kashani Farnoush

A2 - Guting, Ralf Hartmut

A2 - Hoel, Erik

PB - Association for Computing Machinery

ER -

Andersen O, Torp K. Dynamic Spatio-temporal Integration of Traffic Accident Data. In Xiong L, Tamassia R, Banaei KF, Guting RH, Hoel E, editors, Proceedings of the 26th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems . Association for Computing Machinery. 2018. p. 596-599 https://doi.org/10.1145/3274895.3274972