The invention belongs to the technical field of vehicle safe driving, and provides a black spot identification method and system based on Bayesian and clustering and a map generation method, and the method comprises the steps: obtaining vehicle alarm data; according to the obtained alarm data, black spot identification is carried out by using a clustering algorithm; wherein hyper-parameters in the clustering algorithm are adjusted and optimized by adopting a Bayesian optimization algorithm, and specifically, an objective function is subjected to regression fitting by using a Gaussian process, so that an optimal hyper-parameter combination of the clustering algorithm is obtained; according to the method, the Bayesian optimization algorithm is adopted to realize the automatic tuning of the hyper-parameters in the clustering algorithm, so that the optimal hyper-parameter combination is obtained, the black spot recognition accuracy is ensured, the globally optimal solution can be found through fewer iterations, and the calculation efficiency is ensured.

    本发明属于车辆安全驾驶技术领域,提供了一种基于贝叶斯和聚类的黑点识别方法、系统及地图生成方法,获取车辆告警数据;根据获取的告警数据,利用聚类算法,进行黑点识别;其中,采用贝叶斯优化算法对聚类算法中的超参数进行调优,具体的,使用高斯过程回归拟合目标函数,得到聚类算法的最佳超参数组合;本发明采用贝叶斯优化算法实现聚类算法中超参数的自动调优,从而得到最佳超参数组合,保证了黑点识别准确率,并且通过较少的迭代次数能够找到全局最优解,保证了计算效率。


    Access

    Download


    Export, share and cite



    Title :

    Bayesian and clustering-based black spot identification method and system and map generation method


    Additional title:

    基于贝叶斯和聚类的黑点识别方法、系统及地图生成方法


    Contributors:
    QI HONGLEI (author) / WANG BO (author) / CHEN ZHENGUO (author) / XUE RONGRONG (author) / ZHANG GANG (author) / XU NING (author) / FENG XILIANG (author) / YANG CHUNXIAO (author) / LI PENGPENG (author)

    Publication date :

    2024-04-02


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen




    Fully Bayesian Approach to Investigate and Evaluate Ranking Criteria for Black Spot Identification

    Lan, Bo / Persaud, Bhagwant | Transportation Research Record | 2011


    Multivariate Full Bayesian Hot Spot Identification and Ranking

    Sacchi, Emanuele / Sayed, Tarek / El-Basyouny, Karim | Transportation Research Record | 2015