A Neural Network-based Approach for Public Transportation Prediction with Traffic Density Matrix

Dancho Panovski; Veronica Scurtu; Titus Zaharia

doi:10.1109/EUVIP.2018.8611683

A Neural Network-based Approach for Public Transportation Prediction with Traffic Density Matrix

Dancho Panovski
, Veronica Scurtu
, Titus Zaharia

CNRS UMR 5157 SAMOVAR

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

9 Citations (Scopus)

Abstract

In today's modern cities, mobility is of crucial importance, and public transportation is particularly concerned. The main objective is to propose solutions to a given, practical problem, which specifically concerns the bus arrival time at various bus stop stations, by taking to account local traffic conditions. We show that a global prediction approach, under some global macro-parameters (e.g., total number of vehicles or pedestrians) is not feasible. This observation leads us to the introduction of a finer granularity approach, where the traffic conditions are represented in terms of a traffic density matrix. Under this new paradigm, the experimental results obtained with both linear and neural networks (NN) approaches show promising prediction performances. Thus, the NN approach yields 24% more accurate prediction performances than a basic, linear regression.

Original language	English
Title of host publication	Proceedings of the 2018 7th European Workshop on Visual Information Processing, EUVIP 2018
Editors	K. Egiazarian, A. Beghdadi, I. Tabus, C. Larabi, F. Battisti, L. Oudre
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781538668979
DOIs	https://doi.org/10.1109/EUVIP.2018.8611683
Publication status	Published - 2 Jul 2018
Event	7th European Workshop on Visual Information Processing, EUVIP 2018 - Tampere, Finland Duration: 26 Nov 2018 → 28 Nov 2018

Publication series

Name	Proceedings - European Workshop on Visual Information Processing, EUVIP
Volume	2018-November
ISSN (Print)	2471-8963

Conference

Conference	7th European Workshop on Visual Information Processing, EUVIP 2018
Country/Territory	Finland
City	Tampere
Period	26/11/18 → 28/11/18

UN SDGs

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

SDG 11 Sustainable Cities and Communities

Keywords

Machine Learning
Neural Networks
Public Transportation
Traffic Prediction
Traffic Simulation

Access to Document

10.1109/EUVIP.2018.8611683

Cite this

Panovski, D., Scurtu, V., & Zaharia, T. (2018). A Neural Network-based Approach for Public Transportation Prediction with Traffic Density Matrix. In K. Egiazarian, A. Beghdadi, I. Tabus, C. Larabi, F. Battisti, & L. Oudre (Eds.), Proceedings of the 2018 7th European Workshop on Visual Information Processing, EUVIP 2018 Article 8611683 (Proceedings - European Workshop on Visual Information Processing, EUVIP; Vol. 2018-November). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/EUVIP.2018.8611683

Panovski, Dancho ; Scurtu, Veronica ; Zaharia, Titus. / A Neural Network-based Approach for Public Transportation Prediction with Traffic Density Matrix. Proceedings of the 2018 7th European Workshop on Visual Information Processing, EUVIP 2018. editor / K. Egiazarian ; A. Beghdadi ; I. Tabus ; C. Larabi ; F. Battisti ; L. Oudre. Institute of Electrical and Electronics Engineers Inc., 2018. (Proceedings - European Workshop on Visual Information Processing, EUVIP).

@inproceedings{a1dd4da101c24b55bfcd966450d52f4f,

title = "A Neural Network-based Approach for Public Transportation Prediction with Traffic Density Matrix",

abstract = "In today's modern cities, mobility is of crucial importance, and public transportation is particularly concerned. The main objective is to propose solutions to a given, practical problem, which specifically concerns the bus arrival time at various bus stop stations, by taking to account local traffic conditions. We show that a global prediction approach, under some global macro-parameters (e.g., total number of vehicles or pedestrians) is not feasible. This observation leads us to the introduction of a finer granularity approach, where the traffic conditions are represented in terms of a traffic density matrix. Under this new paradigm, the experimental results obtained with both linear and neural networks (NN) approaches show promising prediction performances. Thus, the NN approach yields 24\% more accurate prediction performances than a basic, linear regression.",

keywords = "Machine Learning, Neural Networks, Public Transportation, Traffic Prediction, Traffic Simulation",

author = "Dancho Panovski and Veronica Scurtu and Titus Zaharia",

note = "Publisher Copyright: {\textcopyright} 2018 IEEE.; 7th European Workshop on Visual Information Processing, EUVIP 2018 ; Conference date: 26-11-2018 Through 28-11-2018",

year = "2018",

month = jul,

day = "2",

doi = "10.1109/EUVIP.2018.8611683",

language = "English",

series = "Proceedings - European Workshop on Visual Information Processing, EUVIP",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

editor = "K. Egiazarian and A. Beghdadi and I. Tabus and C. Larabi and F. Battisti and L. Oudre",

booktitle = "Proceedings of the 2018 7th European Workshop on Visual Information Processing, EUVIP 2018",

}

Panovski, D, Scurtu, V & Zaharia, T 2018, A Neural Network-based Approach for Public Transportation Prediction with Traffic Density Matrix. in K Egiazarian, A Beghdadi, I Tabus, C Larabi, F Battisti & L Oudre (eds), Proceedings of the 2018 7th European Workshop on Visual Information Processing, EUVIP 2018., 8611683, Proceedings - European Workshop on Visual Information Processing, EUVIP, vol. 2018-November, Institute of Electrical and Electronics Engineers Inc., 7th European Workshop on Visual Information Processing, EUVIP 2018, Tampere, Finland, 26/11/18. https://doi.org/10.1109/EUVIP.2018.8611683

A Neural Network-based Approach for Public Transportation Prediction with Traffic Density Matrix. / Panovski, Dancho; Scurtu, Veronica; Zaharia, Titus.
Proceedings of the 2018 7th European Workshop on Visual Information Processing, EUVIP 2018. ed. / K. Egiazarian; A. Beghdadi; I. Tabus; C. Larabi; F. Battisti; L. Oudre. Institute of Electrical and Electronics Engineers Inc., 2018. 8611683 (Proceedings - European Workshop on Visual Information Processing, EUVIP; Vol. 2018-November).

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

TY - GEN

T1 - A Neural Network-based Approach for Public Transportation Prediction with Traffic Density Matrix

AU - Panovski, Dancho

AU - Scurtu, Veronica

AU - Zaharia, Titus

PY - 2018/7/2

Y1 - 2018/7/2

N2 - In today's modern cities, mobility is of crucial importance, and public transportation is particularly concerned. The main objective is to propose solutions to a given, practical problem, which specifically concerns the bus arrival time at various bus stop stations, by taking to account local traffic conditions. We show that a global prediction approach, under some global macro-parameters (e.g., total number of vehicles or pedestrians) is not feasible. This observation leads us to the introduction of a finer granularity approach, where the traffic conditions are represented in terms of a traffic density matrix. Under this new paradigm, the experimental results obtained with both linear and neural networks (NN) approaches show promising prediction performances. Thus, the NN approach yields 24% more accurate prediction performances than a basic, linear regression.

AB - In today's modern cities, mobility is of crucial importance, and public transportation is particularly concerned. The main objective is to propose solutions to a given, practical problem, which specifically concerns the bus arrival time at various bus stop stations, by taking to account local traffic conditions. We show that a global prediction approach, under some global macro-parameters (e.g., total number of vehicles or pedestrians) is not feasible. This observation leads us to the introduction of a finer granularity approach, where the traffic conditions are represented in terms of a traffic density matrix. Under this new paradigm, the experimental results obtained with both linear and neural networks (NN) approaches show promising prediction performances. Thus, the NN approach yields 24% more accurate prediction performances than a basic, linear regression.

KW - Machine Learning

KW - Neural Networks

KW - Public Transportation

KW - Traffic Prediction

KW - Traffic Simulation

U2 - 10.1109/EUVIP.2018.8611683

DO - 10.1109/EUVIP.2018.8611683

M3 - Conference contribution

AN - SCOPUS:85062735414

T3 - Proceedings - European Workshop on Visual Information Processing, EUVIP

BT - Proceedings of the 2018 7th European Workshop on Visual Information Processing, EUVIP 2018

A2 - Egiazarian, K.

A2 - Beghdadi, A.

A2 - Tabus, I.

A2 - Larabi, C.

A2 - Battisti, F.

A2 - Oudre, L.

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 7th European Workshop on Visual Information Processing, EUVIP 2018

Y2 - 26 November 2018 through 28 November 2018

ER -

Panovski D, Scurtu V, Zaharia T. A Neural Network-based Approach for Public Transportation Prediction with Traffic Density Matrix. In Egiazarian K, Beghdadi A, Tabus I, Larabi C, Battisti F, Oudre L, editors, Proceedings of the 2018 7th European Workshop on Visual Information Processing, EUVIP 2018. Institute of Electrical and Electronics Engineers Inc. 2018. 8611683. (Proceedings - European Workshop on Visual Information Processing, EUVIP). doi: 10.1109/EUVIP.2018.8611683

A Neural Network-based Approach for Public Transportation Prediction with Traffic Density Matrix

Abstract

Publication series

Conference

UN SDGs

Keywords

Access to Document

Fingerprint

Cite this