TCPModel

A Short-Term Traffic Congestion Prediction Model Based on Deep Learning

Xiujuan Xu, Xiaobo Gao, Zhenzhen Xu, Xiaowei Zhao, Wei Pang, Hongmei Zhou

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

Abstract

With the progress of the urbanization, a series of traffic problems have occurred because of the growing urban population and the far lower growth rate of roads than that of cars. One of the most prominent problems is traffic congestion problem. The prediction of traffic congestion is the key to alleviate traffic congestion. To ensure the real-time performance and accuracy of the traffic congestion prediction, we propose a short-term traffic congestion prediction model called TCPModel based on deep learning. By processing a massive amount of urban taxi transportation data, we extract the traffic volume and average speed of taxis which are the most important parameters for assessing of traffic flow prediction. After analyzing the temporal and spatial distribution characteristics of the traffic flow and average speed, we present a short-term traffic volume prediction model called TVPModel, and a short-term traffic speed prediction model called TSPModel. Both models are based on a deep learning method Stacked Auto Encoder (SAE). By comparing the other traffic flow forecasting methods and average speed forecasting methods, the methods proposed by this paper have improved the accuracy rate. For traffic congestion recognition, we use a novel model called TCPModel based on three traffic parameters (average speed, traffic flow and density), which uses standard function method to standardize the parameters and calculate the congestion comprehensive threshold to determine the congestion level by thresholds. According to the experiments, TVPModel and TSPModel in this paper got satisfied accuracy compared with other prediction models.
Original languageEnglish
Title of host publicationArtificial Intelligence
Subtitle of host publicationSecond CCF International Conference, ICAI 2019, Xuzhou, China, August 22-23, 2019, Proceedings
EditorsKevin Knight, Changshui Zhang, Geoff Holmes, Min-Ling Zhang
Place of PublicationSingapore
PublisherSpringer
Pages66-79
Number of pages14
ISBN (Electronic)9789813292987
ISBN (Print)9789813292970
DOIs
Publication statusPublished - Aug 2019
EventThe 2nd CCF International Conference on Artificial Intelligence (CCF-ICAI 2019) - China University of Mining and Technology, Xuzhou, China
Duration: 22 Aug 201923 Aug 2019

Publication series

NameCommunications in Computer and Information Science
PublisherSpringer
Volume1001
ISSN (Print)1865-0929
ISSN (Electronic)1865-0937

Conference

ConferenceThe 2nd CCF International Conference on Artificial Intelligence (CCF-ICAI 2019)
Abbreviated titleICAI 2019
CountryChina
CityXuzhou
Period22/08/1923/08/19

Fingerprint

Traffic congestion
Deep learning
Spatial distribution
Railroad cars

Keywords

  • Short-term traffic congestion prediction
  • Traffic data
  • Deep learning
  • Stacked autoencoder

ASJC Scopus subject areas

  • Mathematics(all)
  • Computer Science(all)

Cite this

Xu, X., Gao, X., Xu, Z., Zhao, X., Pang, W., & Zhou, H. (2019). TCPModel: A Short-Term Traffic Congestion Prediction Model Based on Deep Learning. In K. Knight, C. Zhang, G. Holmes, & M-L. Zhang (Eds.), Artificial Intelligence: Second CCF International Conference, ICAI 2019, Xuzhou, China, August 22-23, 2019, Proceedings (pp. 66-79). (Communications in Computer and Information Science; Vol. 1001). Singapore: Springer . https://doi.org/10.1007/978-981-32-9298-7_6

TCPModel : A Short-Term Traffic Congestion Prediction Model Based on Deep Learning. / Xu, Xiujuan; Gao, Xiaobo; Xu, Zhenzhen; Zhao, Xiaowei; Pang, Wei; Zhou, Hongmei.

Artificial Intelligence: Second CCF International Conference, ICAI 2019, Xuzhou, China, August 22-23, 2019, Proceedings. ed. / Kevin Knight; Changshui Zhang; Geoff Holmes; Min-Ling Zhang. Singapore : Springer , 2019. p. 66-79 (Communications in Computer and Information Science; Vol. 1001).

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

Xu, X, Gao, X, Xu, Z, Zhao, X, Pang, W & Zhou, H 2019, TCPModel: A Short-Term Traffic Congestion Prediction Model Based on Deep Learning. in K Knight, C Zhang, G Holmes & M-L Zhang (eds), Artificial Intelligence: Second CCF International Conference, ICAI 2019, Xuzhou, China, August 22-23, 2019, Proceedings. Communications in Computer and Information Science, vol. 1001, Springer , Singapore, pp. 66-79, The 2nd CCF International Conference on Artificial Intelligence (CCF-ICAI 2019), Xuzhou, China, 22/08/19. https://doi.org/10.1007/978-981-32-9298-7_6
Xu X, Gao X, Xu Z, Zhao X, Pang W, Zhou H. TCPModel: A Short-Term Traffic Congestion Prediction Model Based on Deep Learning. In Knight K, Zhang C, Holmes G, Zhang M-L, editors, Artificial Intelligence: Second CCF International Conference, ICAI 2019, Xuzhou, China, August 22-23, 2019, Proceedings. Singapore: Springer . 2019. p. 66-79. (Communications in Computer and Information Science). https://doi.org/10.1007/978-981-32-9298-7_6
Xu, Xiujuan ; Gao, Xiaobo ; Xu, Zhenzhen ; Zhao, Xiaowei ; Pang, Wei ; Zhou, Hongmei. / TCPModel : A Short-Term Traffic Congestion Prediction Model Based on Deep Learning. Artificial Intelligence: Second CCF International Conference, ICAI 2019, Xuzhou, China, August 22-23, 2019, Proceedings. editor / Kevin Knight ; Changshui Zhang ; Geoff Holmes ; Min-Ling Zhang. Singapore : Springer , 2019. pp. 66-79 (Communications in Computer and Information Science).
@inproceedings{fa66de81f7cd44f6b13aba00c5e6b3cc,
title = "TCPModel: A Short-Term Traffic Congestion Prediction Model Based on Deep Learning",
abstract = "With the progress of the urbanization, a series of traffic problems have occurred because of the growing urban population and the far lower growth rate of roads than that of cars. One of the most prominent problems is traffic congestion problem. The prediction of traffic congestion is the key to alleviate traffic congestion. To ensure the real-time performance and accuracy of the traffic congestion prediction, we propose a short-term traffic congestion prediction model called TCPModel based on deep learning. By processing a massive amount of urban taxi transportation data, we extract the traffic volume and average speed of taxis which are the most important parameters for assessing of traffic flow prediction. After analyzing the temporal and spatial distribution characteristics of the traffic flow and average speed, we present a short-term traffic volume prediction model called TVPModel, and a short-term traffic speed prediction model called TSPModel. Both models are based on a deep learning method Stacked Auto Encoder (SAE). By comparing the other traffic flow forecasting methods and average speed forecasting methods, the methods proposed by this paper have improved the accuracy rate. For traffic congestion recognition, we use a novel model called TCPModel based on three traffic parameters (average speed, traffic flow and density), which uses standard function method to standardize the parameters and calculate the congestion comprehensive threshold to determine the congestion level by thresholds. According to the experiments, TVPModel and TSPModel in this paper got satisfied accuracy compared with other prediction models.",
keywords = "Short-term traffic congestion prediction, Traffic data, Deep learning, Stacked autoencoder",
author = "Xiujuan Xu and Xiaobo Gao and Zhenzhen Xu and Xiaowei Zhao and Wei Pang and Hongmei Zhou",
note = "Acknowledgment This work was supported in part by the Natural Science Foundation of China grant 61502069, 61672128, 61702076; the Fundamental Research Funds for the Central Universities DUT18JC39.",
year = "2019",
month = "8",
doi = "10.1007/978-981-32-9298-7_6",
language = "English",
isbn = "9789813292970",
series = "Communications in Computer and Information Science",
publisher = "Springer",
pages = "66--79",
editor = "Kevin Knight and Changshui Zhang and Geoff Holmes and Min-Ling Zhang",
booktitle = "Artificial Intelligence",

}

TY - GEN

T1 - TCPModel

T2 - A Short-Term Traffic Congestion Prediction Model Based on Deep Learning

AU - Xu, Xiujuan

AU - Gao, Xiaobo

AU - Xu, Zhenzhen

AU - Zhao, Xiaowei

AU - Pang, Wei

AU - Zhou, Hongmei

N1 - Acknowledgment This work was supported in part by the Natural Science Foundation of China grant 61502069, 61672128, 61702076; the Fundamental Research Funds for the Central Universities DUT18JC39.

PY - 2019/8

Y1 - 2019/8

N2 - With the progress of the urbanization, a series of traffic problems have occurred because of the growing urban population and the far lower growth rate of roads than that of cars. One of the most prominent problems is traffic congestion problem. The prediction of traffic congestion is the key to alleviate traffic congestion. To ensure the real-time performance and accuracy of the traffic congestion prediction, we propose a short-term traffic congestion prediction model called TCPModel based on deep learning. By processing a massive amount of urban taxi transportation data, we extract the traffic volume and average speed of taxis which are the most important parameters for assessing of traffic flow prediction. After analyzing the temporal and spatial distribution characteristics of the traffic flow and average speed, we present a short-term traffic volume prediction model called TVPModel, and a short-term traffic speed prediction model called TSPModel. Both models are based on a deep learning method Stacked Auto Encoder (SAE). By comparing the other traffic flow forecasting methods and average speed forecasting methods, the methods proposed by this paper have improved the accuracy rate. For traffic congestion recognition, we use a novel model called TCPModel based on three traffic parameters (average speed, traffic flow and density), which uses standard function method to standardize the parameters and calculate the congestion comprehensive threshold to determine the congestion level by thresholds. According to the experiments, TVPModel and TSPModel in this paper got satisfied accuracy compared with other prediction models.

AB - With the progress of the urbanization, a series of traffic problems have occurred because of the growing urban population and the far lower growth rate of roads than that of cars. One of the most prominent problems is traffic congestion problem. The prediction of traffic congestion is the key to alleviate traffic congestion. To ensure the real-time performance and accuracy of the traffic congestion prediction, we propose a short-term traffic congestion prediction model called TCPModel based on deep learning. By processing a massive amount of urban taxi transportation data, we extract the traffic volume and average speed of taxis which are the most important parameters for assessing of traffic flow prediction. After analyzing the temporal and spatial distribution characteristics of the traffic flow and average speed, we present a short-term traffic volume prediction model called TVPModel, and a short-term traffic speed prediction model called TSPModel. Both models are based on a deep learning method Stacked Auto Encoder (SAE). By comparing the other traffic flow forecasting methods and average speed forecasting methods, the methods proposed by this paper have improved the accuracy rate. For traffic congestion recognition, we use a novel model called TCPModel based on three traffic parameters (average speed, traffic flow and density), which uses standard function method to standardize the parameters and calculate the congestion comprehensive threshold to determine the congestion level by thresholds. According to the experiments, TVPModel and TSPModel in this paper got satisfied accuracy compared with other prediction models.

KW - Short-term traffic congestion prediction

KW - Traffic data

KW - Deep learning

KW - Stacked autoencoder

UR - http://www.scopus.com/inward/record.url?scp=85071471127&partnerID=8YFLogxK

UR - http://www.mendeley.com/research/tcpmodel-shortterm-traffic-congestion-prediction-model-based-deep-learning

U2 - 10.1007/978-981-32-9298-7_6

DO - 10.1007/978-981-32-9298-7_6

M3 - Conference contribution

SN - 9789813292970

T3 - Communications in Computer and Information Science

SP - 66

EP - 79

BT - Artificial Intelligence

A2 - Knight, Kevin

A2 - Zhang, Changshui

A2 - Holmes, Geoff

A2 - Zhang, Min-Ling

PB - Springer

CY - Singapore

ER -