Multi-model hybrid traffic flow forecast algorithm based on multivariate data

Jie Zhou; Yuling Sun; Liang He

doi:10.1007/978-981-13-3044-5_14

Multi-model hybrid traffic flow forecast algorithm based on multivariate data

Jie Zhou, Yuling Sun, Liang He

School of Computer Science and Technology

East China Normal University

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

1 Scopus citations

Abstract

Traffic flow forecast is a fine-grained task in urban intelligent transportation systems. Accurate traffic flow forecast can effectively support the development of intelligent transportation systems, reduce congestion, and improve the quality of residents’ travel. The forecast of traffic flow is affected by many random factors such as weather, holidays and seasons. It has a certain degree of randomness and uncertainty, which makes the traditional single model prediction result extremely unstable, and the consideration of random factors is incomplete. As a result, the final forecast results are quite different from the actual situation. To address this problem, this paper proposes a multi-model hybrid traffic flow forecast algorithm based on multivariate data, which considers various random factors from multiple aspects, and captures different features through multiple models to improve the accuracy. The experiments on the dataset of KDD CUP 2017 demonstrate the effectiveness of our approach.

Original language	English
Title of host publication	Computer Supported Cooperative Work and Social Computing - 13th CCF Conference, ChineseCSCW 2018, Revised Selected Papers
Editors	Xiaolan Xie, Yuqing Sun, Tun Lu, Hongfei Fan, Liping Gao
Publisher	Springer Verlag
Pages	188-200
Number of pages	13
ISBN (Print)	9789811330438
DOIs	https://doi.org/10.1007/978-981-13-3044-5_14
State	Published - 2019
Event	13th CCF Conference on Computer Supported Cooperative Work and Social Computing, ChineseCSCW 2018 - Guilin, China Duration: 18 Aug 2018 → 19 Aug 2018

Publication series

Name	Communications in Computer and Information Science
Volume	917
ISSN (Print)	1865-0929

Conference

Conference	13th CCF Conference on Computer Supported Cooperative Work and Social Computing, ChineseCSCW 2018
Country/Territory	China
City	Guilin
Period	18/08/18 → 19/08/18

Keywords

Multi-model-based
Multivariate data
Traffic flow forecast

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1007/978-981-13-3044-5_14

Cite this

Zhou, J., Sun, Y., & He, L. (2019). Multi-model hybrid traffic flow forecast algorithm based on multivariate data. In X. Xie, Y. Sun, T. Lu, H. Fan, & L. Gao (Eds.), Computer Supported Cooperative Work and Social Computing - 13th CCF Conference, ChineseCSCW 2018, Revised Selected Papers (pp. 188-200). (Communications in Computer and Information Science; Vol. 917). Springer Verlag. https://doi.org/10.1007/978-981-13-3044-5_14

Zhou, Jie ; Sun, Yuling ; He, Liang. / Multi-model hybrid traffic flow forecast algorithm based on multivariate data. Computer Supported Cooperative Work and Social Computing - 13th CCF Conference, ChineseCSCW 2018, Revised Selected Papers. editor / Xiaolan Xie ; Yuqing Sun ; Tun Lu ; Hongfei Fan ; Liping Gao. Springer Verlag, 2019. pp. 188-200 (Communications in Computer and Information Science).

@inproceedings{15561416742d46fcae269a26eab6d25a,

title = "Multi-model hybrid traffic flow forecast algorithm based on multivariate data",

abstract = "Traffic flow forecast is a fine-grained task in urban intelligent transportation systems. Accurate traffic flow forecast can effectively support the development of intelligent transportation systems, reduce congestion, and improve the quality of residents{\textquoteright} travel. The forecast of traffic flow is affected by many random factors such as weather, holidays and seasons. It has a certain degree of randomness and uncertainty, which makes the traditional single model prediction result extremely unstable, and the consideration of random factors is incomplete. As a result, the final forecast results are quite different from the actual situation. To address this problem, this paper proposes a multi-model hybrid traffic flow forecast algorithm based on multivariate data, which considers various random factors from multiple aspects, and captures different features through multiple models to improve the accuracy. The experiments on the dataset of KDD CUP 2017 demonstrate the effectiveness of our approach.",

keywords = "Multi-model-based, Multivariate data, Traffic flow forecast",

author = "Jie Zhou and Yuling Sun and Liang He",

note = "Publisher Copyright: {\textcopyright} Springer Nature Singapore Pte Ltd. 2019.; 13th CCF Conference on Computer Supported Cooperative Work and Social Computing, ChineseCSCW 2018 ; Conference date: 18-08-2018 Through 19-08-2018",

year = "2019",

doi = "10.1007/978-981-13-3044-5\_14",

language = "英语",

isbn = "9789811330438",

series = "Communications in Computer and Information Science",

publisher = "Springer Verlag",

pages = "188--200",

editor = "Xiaolan Xie and Yuqing Sun and Tun Lu and Hongfei Fan and Liping Gao",

booktitle = "Computer Supported Cooperative Work and Social Computing - 13th CCF Conference, ChineseCSCW 2018, Revised Selected Papers",

address = "德国",

}

Zhou, J, Sun, Y & He, L 2019, Multi-model hybrid traffic flow forecast algorithm based on multivariate data. in X Xie, Y Sun, T Lu, H Fan & L Gao (eds), Computer Supported Cooperative Work and Social Computing - 13th CCF Conference, ChineseCSCW 2018, Revised Selected Papers. Communications in Computer and Information Science, vol. 917, Springer Verlag, pp. 188-200, 13th CCF Conference on Computer Supported Cooperative Work and Social Computing, ChineseCSCW 2018, Guilin, China, 18/08/18. https://doi.org/10.1007/978-981-13-3044-5_14

Multi-model hybrid traffic flow forecast algorithm based on multivariate data. / Zhou, Jie; Sun, Yuling; He, Liang.
Computer Supported Cooperative Work and Social Computing - 13th CCF Conference, ChineseCSCW 2018, Revised Selected Papers. ed. / Xiaolan Xie; Yuqing Sun; Tun Lu; Hongfei Fan; Liping Gao. Springer Verlag, 2019. p. 188-200 (Communications in Computer and Information Science; Vol. 917).

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

TY - GEN

T1 - Multi-model hybrid traffic flow forecast algorithm based on multivariate data

AU - Zhou, Jie

AU - Sun, Yuling

AU - He, Liang

N1 - Publisher Copyright: © Springer Nature Singapore Pte Ltd. 2019.

PY - 2019

Y1 - 2019

N2 - Traffic flow forecast is a fine-grained task in urban intelligent transportation systems. Accurate traffic flow forecast can effectively support the development of intelligent transportation systems, reduce congestion, and improve the quality of residents’ travel. The forecast of traffic flow is affected by many random factors such as weather, holidays and seasons. It has a certain degree of randomness and uncertainty, which makes the traditional single model prediction result extremely unstable, and the consideration of random factors is incomplete. As a result, the final forecast results are quite different from the actual situation. To address this problem, this paper proposes a multi-model hybrid traffic flow forecast algorithm based on multivariate data, which considers various random factors from multiple aspects, and captures different features through multiple models to improve the accuracy. The experiments on the dataset of KDD CUP 2017 demonstrate the effectiveness of our approach.

AB - Traffic flow forecast is a fine-grained task in urban intelligent transportation systems. Accurate traffic flow forecast can effectively support the development of intelligent transportation systems, reduce congestion, and improve the quality of residents’ travel. The forecast of traffic flow is affected by many random factors such as weather, holidays and seasons. It has a certain degree of randomness and uncertainty, which makes the traditional single model prediction result extremely unstable, and the consideration of random factors is incomplete. As a result, the final forecast results are quite different from the actual situation. To address this problem, this paper proposes a multi-model hybrid traffic flow forecast algorithm based on multivariate data, which considers various random factors from multiple aspects, and captures different features through multiple models to improve the accuracy. The experiments on the dataset of KDD CUP 2017 demonstrate the effectiveness of our approach.

KW - Multi-model-based

KW - Multivariate data

KW - Traffic flow forecast

UR - https://www.scopus.com/pages/publications/85059083669

U2 - 10.1007/978-981-13-3044-5_14

DO - 10.1007/978-981-13-3044-5_14

M3 - 会议稿件

AN - SCOPUS:85059083669

SN - 9789811330438

T3 - Communications in Computer and Information Science

SP - 188

EP - 200

BT - Computer Supported Cooperative Work and Social Computing - 13th CCF Conference, ChineseCSCW 2018, Revised Selected Papers

A2 - Xie, Xiaolan

A2 - Sun, Yuqing

A2 - Lu, Tun

A2 - Fan, Hongfei

A2 - Gao, Liping

PB - Springer Verlag

T2 - 13th CCF Conference on Computer Supported Cooperative Work and Social Computing, ChineseCSCW 2018

Y2 - 18 August 2018 through 19 August 2018

ER -

Zhou J, Sun Y, He L. Multi-model hybrid traffic flow forecast algorithm based on multivariate data. In Xie X, Sun Y, Lu T, Fan H, Gao L, editors, Computer Supported Cooperative Work and Social Computing - 13th CCF Conference, ChineseCSCW 2018, Revised Selected Papers. Springer Verlag. 2019. p. 188-200. (Communications in Computer and Information Science). doi: 10.1007/978-981-13-3044-5_14

Multi-model hybrid traffic flow forecast algorithm based on multivariate data

Abstract

Publication series

Conference

Keywords

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this