Short term traffic flow prediction based on on-line sequential extreme learning machine

Zhiyuan Ma, Guangchun Luo, Dijiang Huang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

17 Citations (Scopus)

Abstract

Traffic flow cannot be predicted solely based on historical data due to its high dynamics and sensitivity to emergency situations. In this paper, a real traffic data collected from 2011 to 2014 is used, and an adaptive prediction model based on a variant of Extreme Learning Machine (ELM), namely On-line Sequential ELM with forgetting mechanism, is built. The model has the capability of updating itself using incoming data, and adapts to the changes in real time. However, limitations, such as the requirements of large number of neurons and dataset size for initialization, are discovered in practice. To improve the applicability, another scheme involving sequential updating and network reconstruction is proposed. The experimental results show that, compared with the previous method, the proposed one has better performance in time while achieving the similar accuracy.

Original languageEnglish (US)
Title of host publicationProceedings of the 8th International Conference on Advanced Computational Intelligence, ICACI 2016
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages143-149
Number of pages7
ISBN (Print)9781467377829
DOIs
StatePublished - Apr 7 2016
Event8th International Conference on Advanced Computational Intelligence, ICACI 2016 - Chiang Mai, Thailand
Duration: Feb 14 2016Feb 16 2016

Other

Other8th International Conference on Advanced Computational Intelligence, ICACI 2016
CountryThailand
CityChiang Mai
Period2/14/162/16/16

Fingerprint

Learning systems
Neurons

Keywords

  • adaptive model
  • ELM
  • online sequential ELM
  • Traffic flow prediction

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications
  • Artificial Intelligence

Cite this

Ma, Z., Luo, G., & Huang, D. (2016). Short term traffic flow prediction based on on-line sequential extreme learning machine. In Proceedings of the 8th International Conference on Advanced Computational Intelligence, ICACI 2016 (pp. 143-149). [7449818] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICACI.2016.7449818

Short term traffic flow prediction based on on-line sequential extreme learning machine. / Ma, Zhiyuan; Luo, Guangchun; Huang, Dijiang.

Proceedings of the 8th International Conference on Advanced Computational Intelligence, ICACI 2016. Institute of Electrical and Electronics Engineers Inc., 2016. p. 143-149 7449818.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ma, Z, Luo, G & Huang, D 2016, Short term traffic flow prediction based on on-line sequential extreme learning machine. in Proceedings of the 8th International Conference on Advanced Computational Intelligence, ICACI 2016., 7449818, Institute of Electrical and Electronics Engineers Inc., pp. 143-149, 8th International Conference on Advanced Computational Intelligence, ICACI 2016, Chiang Mai, Thailand, 2/14/16. https://doi.org/10.1109/ICACI.2016.7449818
Ma Z, Luo G, Huang D. Short term traffic flow prediction based on on-line sequential extreme learning machine. In Proceedings of the 8th International Conference on Advanced Computational Intelligence, ICACI 2016. Institute of Electrical and Electronics Engineers Inc. 2016. p. 143-149. 7449818 https://doi.org/10.1109/ICACI.2016.7449818
Ma, Zhiyuan ; Luo, Guangchun ; Huang, Dijiang. / Short term traffic flow prediction based on on-line sequential extreme learning machine. Proceedings of the 8th International Conference on Advanced Computational Intelligence, ICACI 2016. Institute of Electrical and Electronics Engineers Inc., 2016. pp. 143-149
@inproceedings{bf0a5aef9523443f8eb113ee74e66d7e,
title = "Short term traffic flow prediction based on on-line sequential extreme learning machine",
abstract = "Traffic flow cannot be predicted solely based on historical data due to its high dynamics and sensitivity to emergency situations. In this paper, a real traffic data collected from 2011 to 2014 is used, and an adaptive prediction model based on a variant of Extreme Learning Machine (ELM), namely On-line Sequential ELM with forgetting mechanism, is built. The model has the capability of updating itself using incoming data, and adapts to the changes in real time. However, limitations, such as the requirements of large number of neurons and dataset size for initialization, are discovered in practice. To improve the applicability, another scheme involving sequential updating and network reconstruction is proposed. The experimental results show that, compared with the previous method, the proposed one has better performance in time while achieving the similar accuracy.",
keywords = "adaptive model, ELM, online sequential ELM, Traffic flow prediction",
author = "Zhiyuan Ma and Guangchun Luo and Dijiang Huang",
year = "2016",
month = "4",
day = "7",
doi = "10.1109/ICACI.2016.7449818",
language = "English (US)",
isbn = "9781467377829",
pages = "143--149",
booktitle = "Proceedings of the 8th International Conference on Advanced Computational Intelligence, ICACI 2016",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Short term traffic flow prediction based on on-line sequential extreme learning machine

AU - Ma, Zhiyuan

AU - Luo, Guangchun

AU - Huang, Dijiang

PY - 2016/4/7

Y1 - 2016/4/7

N2 - Traffic flow cannot be predicted solely based on historical data due to its high dynamics and sensitivity to emergency situations. In this paper, a real traffic data collected from 2011 to 2014 is used, and an adaptive prediction model based on a variant of Extreme Learning Machine (ELM), namely On-line Sequential ELM with forgetting mechanism, is built. The model has the capability of updating itself using incoming data, and adapts to the changes in real time. However, limitations, such as the requirements of large number of neurons and dataset size for initialization, are discovered in practice. To improve the applicability, another scheme involving sequential updating and network reconstruction is proposed. The experimental results show that, compared with the previous method, the proposed one has better performance in time while achieving the similar accuracy.

AB - Traffic flow cannot be predicted solely based on historical data due to its high dynamics and sensitivity to emergency situations. In this paper, a real traffic data collected from 2011 to 2014 is used, and an adaptive prediction model based on a variant of Extreme Learning Machine (ELM), namely On-line Sequential ELM with forgetting mechanism, is built. The model has the capability of updating itself using incoming data, and adapts to the changes in real time. However, limitations, such as the requirements of large number of neurons and dataset size for initialization, are discovered in practice. To improve the applicability, another scheme involving sequential updating and network reconstruction is proposed. The experimental results show that, compared with the previous method, the proposed one has better performance in time while achieving the similar accuracy.

KW - adaptive model

KW - ELM

KW - online sequential ELM

KW - Traffic flow prediction

UR - http://www.scopus.com/inward/record.url?scp=84966671670&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84966671670&partnerID=8YFLogxK

U2 - 10.1109/ICACI.2016.7449818

DO - 10.1109/ICACI.2016.7449818

M3 - Conference contribution

AN - SCOPUS:84966671670

SN - 9781467377829

SP - 143

EP - 149

BT - Proceedings of the 8th International Conference on Advanced Computational Intelligence, ICACI 2016

PB - Institute of Electrical and Electronics Engineers Inc.

ER -