Integrating rough sets with neural networks for weighting road safety performance indicators

Tianrui Li; Yongjun Shen; Da Ruan; Elke Hermans; Geert Wets

doi:10.1007/978-3-642-02962-2_8

Integrating rough sets with neural networks for weighting road safety performance indicators

Tianrui Li, Yongjun Shen, Da Ruan, Elke Hermans, Geert Wets

Research output › peer-review

Abstract

This paper aims at improving two main uncertain factors in neural networks training in developing a composite road safety performance indicator. These factors are the initial value of network weights and the iteration time. More specially, rough sets theory is applied for rule induction and feature selection in decision situations, and the concepts of reduct and core are utilized to generate decision rules from the data to guide the self-training of neural networks. By means of simulation, optimal weights are assigned to seven indicators in a road safety data set for 21 European countries. Countries are ranked in terms of their composite indicator score. A comparison study shows the feasibility of this hybrid framework for road safety performance indicators.

Original language	English
Title of host publication	Rough Sets and Knowledge Technology
Subtitle of host publication	4th International Conference, RSKT 2009, Proceedings
Place of Publication	Berlin Heidelberg, Germany
Pages	60-67
Number of pages	8
DOIs	https://doi.org/10.1007/978-3-642-02962-2_8
State	Published - 2009
Event	The Fourth International Conferenec on Rough Set and Knowledge Technology - Gold Coast Duration: 14 Jul 2009 → 16 Jul 2009

Publication series

Name	Lecture notes in Computer Science
Number	5589

Conference

Conference	The Fourth International Conferenec on Rough Set and Knowledge Technology
Country/Territory	Australia
City	Gold Coast
Period	2009-07-14 → 2009-07-16

Funding

This work is partially supported by NSFC (No.60873108,60875034), the Research Fund for the Doctoral Program of Higher Education (No.20060613007) and the Basic Science Foundation of Southwest Jiaotong University (No.2007B13), China.

Funders	Funder number
Southwest Jiaotong University	2007B13
NSFC - National Natural Science Foundation of China	60873108,60875034
Specialized Research Fund for the Doctoral Program of Higher Education of China	20060613007

ASJC Scopus subject areas

Theoretical Computer Science
General Computer Science

Access to Document

10.1007/978-3-642-02962-2_8License: Unspecified

Cite this

@inproceedings{fe6f1dd32d1b43c7b06d48356ecd9caa,

title = "Integrating rough sets with neural networks for weighting road safety performance indicators",

abstract = "This paper aims at improving two main uncertain factors in neural networks training in developing a composite road safety performance indicator. These factors are the initial value of network weights and the iteration time. More specially, rough sets theory is applied for rule induction and feature selection in decision situations, and the concepts of reduct and core are utilized to generate decision rules from the data to guide the self-training of neural networks. By means of simulation, optimal weights are assigned to seven indicators in a road safety data set for 21 European countries. Countries are ranked in terms of their composite indicator score. A comparison study shows the feasibility of this hybrid framework for road safety performance indicators.",

keywords = "Composite indicator, Neural networks, Road safety performance indicators, Rough sets",

author = "Tianrui Li and Yongjun Shen and Da Ruan and Elke Hermans and Geert Wets",

note = "Score = 3; The Fourth International Conferenec on Rough Set and Knowledge Technology ; Conference date: 14-07-2009 Through 16-07-2009",

year = "2009",

doi = "10.1007/978-3-642-02962-2_8",

language = "English",

isbn = "3642029612",

series = "Lecture notes in Computer Science",

number = "5589",

pages = "60--67",

booktitle = "Rough Sets and Knowledge Technology",

}

Li, T, Shen, Y, Ruan, D, Hermans, E & Wets, G 2009, Integrating rough sets with neural networks for weighting road safety performance indicators. in Rough Sets and Knowledge Technology: 4th International Conference, RSKT 2009, Proceedings. Lecture notes in Computer Science, no. 5589, Berlin Heidelberg, Germany, pp. 60-67, The Fourth International Conferenec on Rough Set and Knowledge Technology, Gold Coast, Australia, 2009-07-14. https://doi.org/10.1007/978-3-642-02962-2_8

TY - GEN

T1 - Integrating rough sets with neural networks for weighting road safety performance indicators

AU - Li, Tianrui

AU - Shen, Yongjun

AU - Ruan, Da

AU - Hermans, Elke

AU - Wets, Geert

N1 - Score = 3

PY - 2009

Y1 - 2009

N2 - This paper aims at improving two main uncertain factors in neural networks training in developing a composite road safety performance indicator. These factors are the initial value of network weights and the iteration time. More specially, rough sets theory is applied for rule induction and feature selection in decision situations, and the concepts of reduct and core are utilized to generate decision rules from the data to guide the self-training of neural networks. By means of simulation, optimal weights are assigned to seven indicators in a road safety data set for 21 European countries. Countries are ranked in terms of their composite indicator score. A comparison study shows the feasibility of this hybrid framework for road safety performance indicators.

AB - This paper aims at improving two main uncertain factors in neural networks training in developing a composite road safety performance indicator. These factors are the initial value of network weights and the iteration time. More specially, rough sets theory is applied for rule induction and feature selection in decision situations, and the concepts of reduct and core are utilized to generate decision rules from the data to guide the self-training of neural networks. By means of simulation, optimal weights are assigned to seven indicators in a road safety data set for 21 European countries. Countries are ranked in terms of their composite indicator score. A comparison study shows the feasibility of this hybrid framework for road safety performance indicators.

KW - Composite indicator

KW - Neural networks

KW - Road safety performance indicators

KW - Rough sets

UR - http://ecm.sckcen.be/OTCS/llisapi.dll/open/ezp_99554

U2 - 10.1007/978-3-642-02962-2_8

DO - 10.1007/978-3-642-02962-2_8

M3 - In-proceedings paper

SN - 3642029612

SN - 9783642029615

T3 - Lecture notes in Computer Science

SP - 60

EP - 67

BT - Rough Sets and Knowledge Technology

CY - Berlin Heidelberg, Germany

T2 - The Fourth International Conferenec on Rough Set and Knowledge Technology

Y2 - 14 July 2009 through 16 July 2009

ER -