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

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

    Research outputpeer-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 languageEnglish
    Title of host publicationRough Sets and Knowledge Technology
    Subtitle of host publication4th International Conference, RSKT 2009, Proceedings
    Place of PublicationBerlin Heidelberg, Germany
    Pages60-67
    Number of pages8
    DOIs
    StatePublished - 2009
    EventThe Fourth International Conferenec on Rough Set and Knowledge Technology - Gold Coast
    Duration: 14 Jul 200916 Jul 2009

    Publication series

    NameLecture notes in Computer Science
    Number5589

    Conference

    ConferenceThe Fourth International Conferenec on Rough Set and Knowledge Technology
    Country/TerritoryAustralia
    CityGold Coast
    Period2009-07-142009-07-16

    ASJC Scopus subject areas

    • Theoretical Computer Science
    • General Computer Science

    Cite this