Context-aware mobile intelligent transportation systems

Minh Quang Tran, Muhammad Ariff Baharudin, Eiji Kamioka

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

Abstract

This paper proposes a practical quantification model for mobile phone based traffic state estimation systems (M-TES). The low penetration rate issue, an inherent issue impeding the realization of a mobile phone based application such as the M-TES, is thoroughly discussed. A notable solution framework, namely the intelligent context-aware velocity-density inference circuit (ICIC), is proposed to effectively resolve the low penetration rate issue. In the ICIC model, velocities and densities calculated directly from the sensed data and inferred by using different inference models such as the Greeshields or the moving average model are appropriately integrated. In addition, appropriate contexts extracted from data reported by mobile devices are utilized to identify the optimal estimation parameters leading to the optimal estimation effectiveness. The experimental evaluations reveal the effectiveness and the robustness of the proposed solutions.

Original languageEnglish
Title of host publicationIEEE Vehicular Technology Conference
DOIs
Publication statusPublished - 2012
Event76th IEEE Vehicular Technology Conference, VTC Fall 2012 - Quebec City, QC
Duration: 2012 Sep 32012 Sep 6

Other

Other76th IEEE Vehicular Technology Conference, VTC Fall 2012
CityQuebec City, QC
Period12/9/312/9/6

Fingerprint

Mobile phones
Networks (circuits)
State estimation
Mobile devices
Parameter estimation

Keywords

  • ANN
  • Context-aware
  • GA
  • Genetic algorithm
  • ITS
  • Low penetration rate
  • M-ITS
  • Mobile probes
  • Neural network

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Applied Mathematics

Cite this

Tran, M. Q., Baharudin, M. A., & Kamioka, E. (2012). Context-aware mobile intelligent transportation systems. In IEEE Vehicular Technology Conference [6398916] https://doi.org/10.1109/VTCFall.2012.6398916

Context-aware mobile intelligent transportation systems. / Tran, Minh Quang; Baharudin, Muhammad Ariff; Kamioka, Eiji.

IEEE Vehicular Technology Conference. 2012. 6398916.

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

Tran, MQ, Baharudin, MA & Kamioka, E 2012, Context-aware mobile intelligent transportation systems. in IEEE Vehicular Technology Conference., 6398916, 76th IEEE Vehicular Technology Conference, VTC Fall 2012, Quebec City, QC, 12/9/3. https://doi.org/10.1109/VTCFall.2012.6398916
Tran MQ, Baharudin MA, Kamioka E. Context-aware mobile intelligent transportation systems. In IEEE Vehicular Technology Conference. 2012. 6398916 https://doi.org/10.1109/VTCFall.2012.6398916
Tran, Minh Quang ; Baharudin, Muhammad Ariff ; Kamioka, Eiji. / Context-aware mobile intelligent transportation systems. IEEE Vehicular Technology Conference. 2012.
@inproceedings{f721c70d8dd24a8986f878a74f8d746a,
title = "Context-aware mobile intelligent transportation systems",
abstract = "This paper proposes a practical quantification model for mobile phone based traffic state estimation systems (M-TES). The low penetration rate issue, an inherent issue impeding the realization of a mobile phone based application such as the M-TES, is thoroughly discussed. A notable solution framework, namely the intelligent context-aware velocity-density inference circuit (ICIC), is proposed to effectively resolve the low penetration rate issue. In the ICIC model, velocities and densities calculated directly from the sensed data and inferred by using different inference models such as the Greeshields or the moving average model are appropriately integrated. In addition, appropriate contexts extracted from data reported by mobile devices are utilized to identify the optimal estimation parameters leading to the optimal estimation effectiveness. The experimental evaluations reveal the effectiveness and the robustness of the proposed solutions.",
keywords = "ANN, Context-aware, GA, Genetic algorithm, ITS, Low penetration rate, M-ITS, Mobile probes, Neural network",
author = "Tran, {Minh Quang} and Baharudin, {Muhammad Ariff} and Eiji Kamioka",
year = "2012",
doi = "10.1109/VTCFall.2012.6398916",
language = "English",
isbn = "9781467318815",
booktitle = "IEEE Vehicular Technology Conference",

}

TY - GEN

T1 - Context-aware mobile intelligent transportation systems

AU - Tran, Minh Quang

AU - Baharudin, Muhammad Ariff

AU - Kamioka, Eiji

PY - 2012

Y1 - 2012

N2 - This paper proposes a practical quantification model for mobile phone based traffic state estimation systems (M-TES). The low penetration rate issue, an inherent issue impeding the realization of a mobile phone based application such as the M-TES, is thoroughly discussed. A notable solution framework, namely the intelligent context-aware velocity-density inference circuit (ICIC), is proposed to effectively resolve the low penetration rate issue. In the ICIC model, velocities and densities calculated directly from the sensed data and inferred by using different inference models such as the Greeshields or the moving average model are appropriately integrated. In addition, appropriate contexts extracted from data reported by mobile devices are utilized to identify the optimal estimation parameters leading to the optimal estimation effectiveness. The experimental evaluations reveal the effectiveness and the robustness of the proposed solutions.

AB - This paper proposes a practical quantification model for mobile phone based traffic state estimation systems (M-TES). The low penetration rate issue, an inherent issue impeding the realization of a mobile phone based application such as the M-TES, is thoroughly discussed. A notable solution framework, namely the intelligent context-aware velocity-density inference circuit (ICIC), is proposed to effectively resolve the low penetration rate issue. In the ICIC model, velocities and densities calculated directly from the sensed data and inferred by using different inference models such as the Greeshields or the moving average model are appropriately integrated. In addition, appropriate contexts extracted from data reported by mobile devices are utilized to identify the optimal estimation parameters leading to the optimal estimation effectiveness. The experimental evaluations reveal the effectiveness and the robustness of the proposed solutions.

KW - ANN

KW - Context-aware

KW - GA

KW - Genetic algorithm

KW - ITS

KW - Low penetration rate

KW - M-ITS

KW - Mobile probes

KW - Neural network

UR - http://www.scopus.com/inward/record.url?scp=84878941575&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878941575&partnerID=8YFLogxK

U2 - 10.1109/VTCFall.2012.6398916

DO - 10.1109/VTCFall.2012.6398916

M3 - Conference contribution

AN - SCOPUS:84878941575

SN - 9781467318815

BT - IEEE Vehicular Technology Conference

ER -