Bayes discriminant analysis theory (BDAT) is used to create an evaluation method to determine the condition of urban road traffic safety. The resulting Bayes discriminant model (BDM) is designed to strictly adhere to BDAT. Three indexes including death ratio per ten thousand vehicles, death ratio per hundred thousand bicycles and death ratio per hundred thousand citizens are selected as the factors in the analysis of urban road traffic safety. The grade of condition of urban road traffic safety is divided into three grades that are regarded as three normal populations in Bayes discriminant analysis. Bayes discriminant functions rigorously constructed through training a set of samples are employed to compute the Bayes function values of the evaluating samples, and the maximal function value is used to judge which population the evaluating sample belongs to. The optimality of the proposed model is verified by back-substitution method. The study shows that the prediction accuracy of the proposed model is 100% and could be used in practice.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Assessment of Urban Road Traffic Safety Based on Bayes Discriminant Analysis Method



    Erschienen in:

    Advanced Materials Research ; 639-640 ; 544-547


    Erscheinungsdatum :

    11.01.2013


    Format / Umfang :

    4 pages




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Road Traffic Safety Micro-Evaluation Based on Bayes Theory

    Dai, Leilei / Pei, Yulong / Ping, Shaohua | ASCE | 2009


    Road Traffic Safety Micro-Evaluation Based on Bayes Theory

    Dai, L. / Pei, Y. / Ping, S. | British Library Conference Proceedings | 2009



    Study on Road Traffic Safety Evaluation Based on Improved Bayes Model

    Li, Yao Ping ;Li, Jian Lin ;Li, Bin | Trans Tech Publications | 2011


    Study on Road Traffic Safety Evaluation Based on Improved Bayes Model

    Li, Yao-Ping / Li, Jian-lin / Li, Bin et al. | Tema Archiv | 2011