2D-STR: Reducing Spatio-temporal Traffic Datasets by Partitioning and Modelling

Liam Steadman; Nathan Griffiths; Stephen Jarvis; Stuart McRobbie; Caroline Wallbank

doi:10.5220/0007679100410052

2D-STR: Reducing Spatio-temporal Traffic Datasets by Partitioning and Modelling

Liam Steadman, Nathan Griffiths, Stephen Jarvis, Stuart McRobbie, Caroline Wallbank

Engineering and Physical Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

1 Citation (Scopus)

Abstract

Spatio-temporal data generated by sensors in the environment, such as traffic data, is widely used in the transportation domain. However, learning from and analysing such data is increasingly problematic as the volume of data grows. Therefore, methods are required to reduce the quantity of data needed for multiple types of subsequent analysis without losing significant information. In this paper, we present the 2-Dimensional Spatio-Temporal Reduction method (2D-STR), which partitions the spatio-temporal matrix of a dataset into regions of similar instances, and reduces each region to a model of its instances. The method is shown to be effective at reducing the volume of a traffic dataset to <5% of its original volume whilst achieving a normalise root mean squared error of <5% when reproducing the original features of the dataset.

Original language	English
Title of host publication	GISTAM 2019 - Proceedings of the 5th International Conference on Geographical Information Systems Theory, Applications and Management
Editors	Cedric Grueau, Robert Laurini, Lemonia Ragia
Publisher	SciTePress
Pages	41-52
Number of pages	12
ISBN (Electronic)	9789897583711
DOIs	https://doi.org/10.5220/0007679100410052
Publication status	Published - 2019
Event	5th International Conference on Geographical Information Systems Theory, Applications and Management, GISTAM 2019 - Heraklion, Crete, Greece Duration: 3 May 2019 → 5 May 2019

Publication series

Name	GISTAM 2019 - Proceedings of the 5th International Conference on Geographical Information Systems Theory, Applications and Management

Conference

Conference	5th International Conference on Geographical Information Systems Theory, Applications and Management, GISTAM 2019
Country/Territory	Greece
City	Heraklion, Crete
Period	3/05/19 → 5/05/19

Bibliographical note

Funding Information:
The lead author gratefully acknowledges funding by the UK Engineering and Physical Sciences Research Council (grant no. EP/L016400/1), the EPSRC Centre for Doctoral Training in Urban Science. The lead author also gratefully acknowledges funding by TRL.

Publisher Copyright:
Copyright © 2019 by SCITEPRESS - Science and Technology Publications, Lda. All rights reserved

Keywords

Data Partitioning
Data Reduction
Spatio-temporal Data

ASJC Scopus subject areas

Information Systems
Geography, Planning and Development
Computer Networks and Communications
Computer Graphics and Computer-Aided Design
Computer Science Applications
Computer Vision and Pattern Recognition
Signal Processing

Access to Document

10.5220/0007679100410052

Cite this

Steadman, L., Griffiths, N., Jarvis, S., McRobbie, S., & Wallbank, C. (2019). 2D-STR: Reducing Spatio-temporal Traffic Datasets by Partitioning and Modelling. In C. Grueau, R. Laurini, & L. Ragia (Eds.), GISTAM 2019 - Proceedings of the 5th International Conference on Geographical Information Systems Theory, Applications and Management (pp. 41-52). (GISTAM 2019 - Proceedings of the 5th International Conference on Geographical Information Systems Theory, Applications and Management). SciTePress. https://doi.org/10.5220/0007679100410052

Steadman, Liam ; Griffiths, Nathan ; Jarvis, Stephen et al. / 2D-STR : Reducing Spatio-temporal Traffic Datasets by Partitioning and Modelling. GISTAM 2019 - Proceedings of the 5th International Conference on Geographical Information Systems Theory, Applications and Management. editor / Cedric Grueau ; Robert Laurini ; Lemonia Ragia. SciTePress, 2019. pp. 41-52 (GISTAM 2019 - Proceedings of the 5th International Conference on Geographical Information Systems Theory, Applications and Management).

@inproceedings{05103dfc5d1342bb8c05376731f0d50d,

title = "2D-STR: Reducing Spatio-temporal Traffic Datasets by Partitioning and Modelling",

abstract = "Spatio-temporal data generated by sensors in the environment, such as traffic data, is widely used in the transportation domain. However, learning from and analysing such data is increasingly problematic as the volume of data grows. Therefore, methods are required to reduce the quantity of data needed for multiple types of subsequent analysis without losing significant information. In this paper, we present the 2-Dimensional Spatio-Temporal Reduction method (2D-STR), which partitions the spatio-temporal matrix of a dataset into regions of similar instances, and reduces each region to a model of its instances. The method is shown to be effective at reducing the volume of a traffic dataset to <5% of its original volume whilst achieving a normalise root mean squared error of <5% when reproducing the original features of the dataset.",

keywords = "Data Partitioning, Data Reduction, Spatio-temporal Data",

author = "Liam Steadman and Nathan Griffiths and Stephen Jarvis and Stuart McRobbie and Caroline Wallbank",

note = "Funding Information: The lead author gratefully acknowledges funding by the UK Engineering and Physical Sciences Research Council (grant no. EP/L016400/1), the EPSRC Centre for Doctoral Training in Urban Science. The lead author also gratefully acknowledges funding by TRL. Publisher Copyright: Copyright {\textcopyright} 2019 by SCITEPRESS - Science and Technology Publications, Lda. All rights reserved; 5th International Conference on Geographical Information Systems Theory, Applications and Management, GISTAM 2019 ; Conference date: 03-05-2019 Through 05-05-2019",

year = "2019",

doi = "10.5220/0007679100410052",

language = "English",

series = "GISTAM 2019 - Proceedings of the 5th International Conference on Geographical Information Systems Theory, Applications and Management",

publisher = "SciTePress",

pages = "41--52",

editor = "Cedric Grueau and Robert Laurini and Lemonia Ragia",

booktitle = "GISTAM 2019 - Proceedings of the 5th International Conference on Geographical Information Systems Theory, Applications and Management",

}

Steadman, L, Griffiths, N, Jarvis, S, McRobbie, S & Wallbank, C 2019, 2D-STR: Reducing Spatio-temporal Traffic Datasets by Partitioning and Modelling. in C Grueau, R Laurini & L Ragia (eds), GISTAM 2019 - Proceedings of the 5th International Conference on Geographical Information Systems Theory, Applications and Management. GISTAM 2019 - Proceedings of the 5th International Conference on Geographical Information Systems Theory, Applications and Management, SciTePress, pp. 41-52, 5th International Conference on Geographical Information Systems Theory, Applications and Management, GISTAM 2019, Heraklion, Crete, Greece, 3/05/19. https://doi.org/10.5220/0007679100410052

2D-STR: Reducing Spatio-temporal Traffic Datasets by Partitioning and Modelling. / Steadman, Liam; Griffiths, Nathan; Jarvis, Stephen et al.
GISTAM 2019 - Proceedings of the 5th International Conference on Geographical Information Systems Theory, Applications and Management. ed. / Cedric Grueau; Robert Laurini; Lemonia Ragia. SciTePress, 2019. p. 41-52 (GISTAM 2019 - Proceedings of the 5th International Conference on Geographical Information Systems Theory, Applications and Management).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

TY - GEN

T1 - 2D-STR

T2 - 5th International Conference on Geographical Information Systems Theory, Applications and Management, GISTAM 2019

AU - Steadman, Liam

AU - Griffiths, Nathan

AU - Jarvis, Stephen

AU - McRobbie, Stuart

AU - Wallbank, Caroline

N1 - Funding Information: The lead author gratefully acknowledges funding by the UK Engineering and Physical Sciences Research Council (grant no. EP/L016400/1), the EPSRC Centre for Doctoral Training in Urban Science. The lead author also gratefully acknowledges funding by TRL. Publisher Copyright: Copyright © 2019 by SCITEPRESS - Science and Technology Publications, Lda. All rights reserved

PY - 2019

Y1 - 2019

N2 - Spatio-temporal data generated by sensors in the environment, such as traffic data, is widely used in the transportation domain. However, learning from and analysing such data is increasingly problematic as the volume of data grows. Therefore, methods are required to reduce the quantity of data needed for multiple types of subsequent analysis without losing significant information. In this paper, we present the 2-Dimensional Spatio-Temporal Reduction method (2D-STR), which partitions the spatio-temporal matrix of a dataset into regions of similar instances, and reduces each region to a model of its instances. The method is shown to be effective at reducing the volume of a traffic dataset to <5% of its original volume whilst achieving a normalise root mean squared error of <5% when reproducing the original features of the dataset.

AB - Spatio-temporal data generated by sensors in the environment, such as traffic data, is widely used in the transportation domain. However, learning from and analysing such data is increasingly problematic as the volume of data grows. Therefore, methods are required to reduce the quantity of data needed for multiple types of subsequent analysis without losing significant information. In this paper, we present the 2-Dimensional Spatio-Temporal Reduction method (2D-STR), which partitions the spatio-temporal matrix of a dataset into regions of similar instances, and reduces each region to a model of its instances. The method is shown to be effective at reducing the volume of a traffic dataset to <5% of its original volume whilst achieving a normalise root mean squared error of <5% when reproducing the original features of the dataset.

KW - Data Partitioning

KW - Data Reduction

KW - Spatio-temporal Data

UR - http://www.scopus.com/inward/record.url?scp=85067464076&partnerID=8YFLogxK

U2 - 10.5220/0007679100410052

DO - 10.5220/0007679100410052

M3 - Conference contribution

AN - SCOPUS:85067464076

T3 - GISTAM 2019 - Proceedings of the 5th International Conference on Geographical Information Systems Theory, Applications and Management

SP - 41

EP - 52

BT - GISTAM 2019 - Proceedings of the 5th International Conference on Geographical Information Systems Theory, Applications and Management

A2 - Grueau, Cedric

A2 - Laurini, Robert

A2 - Ragia, Lemonia

PB - SciTePress

Y2 - 3 May 2019 through 5 May 2019

ER -

Steadman L, Griffiths N, Jarvis S, McRobbie S, Wallbank C. 2D-STR: Reducing Spatio-temporal Traffic Datasets by Partitioning and Modelling. In Grueau C, Laurini R, Ragia L, editors, GISTAM 2019 - Proceedings of the 5th International Conference on Geographical Information Systems Theory, Applications and Management. SciTePress. 2019. p. 41-52. (GISTAM 2019 - Proceedings of the 5th International Conference on Geographical Information Systems Theory, Applications and Management). doi: 10.5220/0007679100410052

2D-STR: Reducing Spatio-temporal Traffic Datasets by Partitioning and Modelling

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this