The invention relates to the technical field of traffic safety, and discloses a traffic accident prediction method based on time and geographically weighted regression, and the method comprises the steps: 1, obtaining point-of-interest data, traffic accident data and coordinates of a prediction position; 2, making a buffer area for the position to be subjected to traffic accident prediction; 3, calculating the density of various interest point data in the buffer area and obtaining the traffic accident frequency; 4, performing global spatial autocorrelation analysis, Pearson's correlation coefficient calculation, multi-collinearity test and significance test on the densities of all the interest points one by one, and rejecting the densities of the interest points which do not meet the requirements according to analysis and test results; and 5, taking the interest point density meeting the requirement as an independent variable, taking the traffic accident frequency as a dependent variable, and obtaining a prediction result by using a time and geographically weighted regression model.

    本发明涉及交通安全技术领域,公开了一种基于时间和地理加权回归的交通事故预测方法,所述方法为:步骤1:获取兴趣点数据、交通事故数据以及预测位置的坐标;步骤2:对准备进行交通事故预测的位置做缓冲区;步骤3:计算缓冲区内的各种兴趣点数据的密度以及得到交通事故频次;步骤4:对所有兴趣点的密度一一进行全局空间自相关分析、皮尔逊相关系数计算、多重共线性检验和显著性检验,根据分析与检验的结果剔除不满足要求的兴趣点密度;步骤5:将满足要求的兴趣点密度作为自变量,交通事故频次作为因变量,运用时间和地理加权回归模型得出预测结果。


    Access

    Download


    Export, share and cite



    Title :

    Traffic accident prediction method based on time and geographically weighted regression


    Additional title:

    一种基于时间和地理加权回归的交通事故预测方法


    Contributors:
    LIN ZIXIN (author) / YIN HAO (author) / ZHU TONG (author) / WEI TIANZHENG (author)

    Publication date :

    2022-01-14


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    G06Q Datenverarbeitungssysteme oder -verfahren, besonders angepasst an verwaltungstechnische, geschäftliche, finanzielle oder betriebswirtschaftliche Zwecke, sowie an geschäftsbezogene Überwachungs- oder Voraussagezwecke , DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTING PURPOSES / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS



    Transit Ridership Model Based on Geographically Weighted Regression

    Chow, Lee-Fang / Zhao, Fang / Liu, Xuemei et al. | Transportation Research Record | 2006



    Using Geographically Weighted Regression Models to Estimate Annual Average Daily Traffic

    Zhao, Fang / Park, Nokil | Transportation Research Record | 2004


    Transit Ridership Model Based on Geographically Weighted Regression

    Chow, Lee-Fang / Zhao, Fang / Liu, Xuemei et al. | Transportation Research Record | 2006