Public Transportation Prediction with Convolutional Neural Networks

Dancho Panovski; Titus Zaharia

doi:10.1007/978-3-030-38822-5_10

Public Transportation Prediction with Convolutional Neural Networks

Dancho Panovski
, Titus Zaharia

CNRS UMR 5157 SAMOVAR

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

Abstract

Good, efficient and reliable public transportation systems are of crucial importance for all major cities today. In this paper, we propose a concrete solution to a particular problem: improve the prediction of the bus arrival time at each bus stop station on a given itinerary, by taking to account global and local traffic contexts. The main principle consists of modeling the traffic data as an image structure, adapted for applying CNN deep neural networks. The results obtained shows that the proposed approach outperforms traditional machine learning techniques, such as OLS (Ordinary Least Squares) or SVR (Support Vector Regression) with different kernels (RBF or Polynomial), with more than 18% better accuracy prediction, while being computationally faster.

Original language	English
Title of host publication	Intelligent Transport Systems. From Research and Development to the Market Uptake - 3rd EAI International Conference, INTSYS 2019
Editors	Ana Lúcia Martins, Joao Carlos Ferreira, Alexander Kocian
Publisher	Springer
Pages	150-161
Number of pages	12
ISBN (Print)	9783030388218
DOIs	https://doi.org/10.1007/978-3-030-38822-5_10
Publication status	Published - 1 Jan 2020
Event	3rd EAI International Conference on Intelligent Transport Systems, INTSYS 2019 - Braga, Portugal Duration: 4 Dec 2019 → 6 Dec 2019

Publication series

Name	Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST
Volume	310 LNICST
ISSN (Print)	1867-8211

Conference

Conference	3rd EAI International Conference on Intelligent Transport Systems, INTSYS 2019
Country/Territory	Portugal
City	Braga
Period	4/12/19 → 6/12/19

UN SDGs

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

SDG 11 Sustainable Cities and Communities

Keywords

Convolutional neural networks
Deep learning
Machine learning
Public transportation
Traffic prediction
Traffic simulation

Access to Document

10.1007/978-3-030-38822-5_10

Cite this

Panovski, D., & Zaharia, T. (2020). Public Transportation Prediction with Convolutional Neural Networks. In A. L. Martins, J. C. Ferreira, & A. Kocian (Eds.), Intelligent Transport Systems. From Research and Development to the Market Uptake - 3rd EAI International Conference, INTSYS 2019 (pp. 150-161). (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST; Vol. 310 LNICST). Springer. https://doi.org/10.1007/978-3-030-38822-5_10

Panovski, Dancho ; Zaharia, Titus. / Public Transportation Prediction with Convolutional Neural Networks. Intelligent Transport Systems. From Research and Development to the Market Uptake - 3rd EAI International Conference, INTSYS 2019. editor / Ana Lúcia Martins ; Joao Carlos Ferreira ; Alexander Kocian. Springer, 2020. pp. 150-161 (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST).

@inproceedings{b920b65efeaf497990404bdeb4cc9a8f,

title = "Public Transportation Prediction with Convolutional Neural Networks",

abstract = "Good, efficient and reliable public transportation systems are of crucial importance for all major cities today. In this paper, we propose a concrete solution to a particular problem: improve the prediction of the bus arrival time at each bus stop station on a given itinerary, by taking to account global and local traffic contexts. The main principle consists of modeling the traffic data as an image structure, adapted for applying CNN deep neural networks. The results obtained shows that the proposed approach outperforms traditional machine learning techniques, such as OLS (Ordinary Least Squares) or SVR (Support Vector Regression) with different kernels (RBF or Polynomial), with more than 18\% better accuracy prediction, while being computationally faster.",

keywords = "Convolutional neural networks, Deep learning, Machine learning, Public transportation, Traffic prediction, Traffic simulation",

author = "Dancho Panovski and Titus Zaharia",

note = "Publisher Copyright: {\textcopyright} 2020, ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering.; 3rd EAI International Conference on Intelligent Transport Systems, INTSYS 2019 ; Conference date: 04-12-2019 Through 06-12-2019",

year = "2020",

month = jan,

day = "1",

doi = "10.1007/978-3-030-38822-5\_10",

language = "English",

isbn = "9783030388218",

series = "Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST",

publisher = "Springer",

pages = "150--161",

editor = "Martins, \{Ana L{\'u}cia\} and Ferreira, \{Joao Carlos\} and Alexander Kocian",

booktitle = "Intelligent Transport Systems. From Research and Development to the Market Uptake - 3rd EAI International Conference, INTSYS 2019",

}

Panovski, D & Zaharia, T 2020, Public Transportation Prediction with Convolutional Neural Networks. in AL Martins, JC Ferreira & A Kocian (eds), Intelligent Transport Systems. From Research and Development to the Market Uptake - 3rd EAI International Conference, INTSYS 2019. Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST, vol. 310 LNICST, Springer, pp. 150-161, 3rd EAI International Conference on Intelligent Transport Systems, INTSYS 2019, Braga, Portugal, 4/12/19. https://doi.org/10.1007/978-3-030-38822-5_10

Public Transportation Prediction with Convolutional Neural Networks. / Panovski, Dancho; Zaharia, Titus.
Intelligent Transport Systems. From Research and Development to the Market Uptake - 3rd EAI International Conference, INTSYS 2019. ed. / Ana Lúcia Martins; Joao Carlos Ferreira; Alexander Kocian. Springer, 2020. p. 150-161 (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST; Vol. 310 LNICST).

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

TY - GEN

T1 - Public Transportation Prediction with Convolutional Neural Networks

AU - Panovski, Dancho

AU - Zaharia, Titus

PY - 2020/1/1

Y1 - 2020/1/1

N2 - Good, efficient and reliable public transportation systems are of crucial importance for all major cities today. In this paper, we propose a concrete solution to a particular problem: improve the prediction of the bus arrival time at each bus stop station on a given itinerary, by taking to account global and local traffic contexts. The main principle consists of modeling the traffic data as an image structure, adapted for applying CNN deep neural networks. The results obtained shows that the proposed approach outperforms traditional machine learning techniques, such as OLS (Ordinary Least Squares) or SVR (Support Vector Regression) with different kernels (RBF or Polynomial), with more than 18% better accuracy prediction, while being computationally faster.

AB - Good, efficient and reliable public transportation systems are of crucial importance for all major cities today. In this paper, we propose a concrete solution to a particular problem: improve the prediction of the bus arrival time at each bus stop station on a given itinerary, by taking to account global and local traffic contexts. The main principle consists of modeling the traffic data as an image structure, adapted for applying CNN deep neural networks. The results obtained shows that the proposed approach outperforms traditional machine learning techniques, such as OLS (Ordinary Least Squares) or SVR (Support Vector Regression) with different kernels (RBF or Polynomial), with more than 18% better accuracy prediction, while being computationally faster.

KW - Convolutional neural networks

KW - Deep learning

KW - Machine learning

KW - Public transportation

KW - Traffic prediction

KW - Traffic simulation

U2 - 10.1007/978-3-030-38822-5_10

DO - 10.1007/978-3-030-38822-5_10

M3 - Conference contribution

AN - SCOPUS:85079525580

SN - 9783030388218

T3 - Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST

SP - 150

EP - 161

BT - Intelligent Transport Systems. From Research and Development to the Market Uptake - 3rd EAI International Conference, INTSYS 2019

A2 - Martins, Ana Lúcia

A2 - Ferreira, Joao Carlos

A2 - Kocian, Alexander

PB - Springer

T2 - 3rd EAI International Conference on Intelligent Transport Systems, INTSYS 2019

Y2 - 4 December 2019 through 6 December 2019

ER -

Panovski D, Zaharia T. Public Transportation Prediction with Convolutional Neural Networks. In Martins AL, Ferreira JC, Kocian A, editors, Intelligent Transport Systems. From Research and Development to the Market Uptake - 3rd EAI International Conference, INTSYS 2019. Springer. 2020. p. 150-161. (Lecture Notes of the Institute for Computer Sciences, Social-Informatics and Telecommunications Engineering, LNICST). doi: 10.1007/978-3-030-38822-5_10

Public Transportation Prediction with Convolutional Neural Networks

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Fingerprint

Cite this