The invention discloses a trajectory data mining method based on a deep semi-supervised neural network in the technical field of traffic data information mining. The method aims to solve the technicalproblem that in the prior art, when the driving style of a driver is mined from vehicle trajectory data, due to the fact that the marked data size is small and the marked data cost is high, the robustness of a model established through a data mining algorithm is low. The method comprises the following steps: carrying out segmentation processing on target vehicle trajectory data; and the processedtarget vehicle trajectory data is inputted to a pre-trained deep semi-supervised neural network, a driving style corresponding to the target vehicle trajectory data is acquired, and the deep semi-supervised neural network is constructed based on a CNN classifier and a convolutional deconvolution automatic encoder.

    本发明公开了交通数据信息挖掘技术领域的一种基于深半监督神经网络的轨迹数据挖掘方法,旨在解决现有技术中从车辆轨迹数据中挖掘驾驶员的驾驶风格时,由于标记的数据量少、标记数据成本高昂的缘故,使得数据挖掘算法建立的模型鲁棒性偏低的技术问题。所述方法包括如下步骤:对目标车辆轨迹数据进行分段处理;将处理后的目标车辆轨迹数据输入预先训练好的深半监督神经网络,获取目标车辆轨迹数据所对应的驾驶风格,所述深半监督神经网络基于CNN分类器和卷积反卷积自动编码器构建而成。


    Access

    Download


    Export, share and cite



    Title :

    Trajectory data mining method based on deep semi-supervised neural network


    Additional title:

    一种基于深半监督神经网络的轨迹数据挖掘方法


    Contributors:
    ZHANG DENGYIN (author) / YANG XIAORUN (author) / DING FEI (author) / ZHANG MIN (author)

    Publication date :

    2020-07-03


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Chinese


    Classification :

    IPC:    G06K Erkennen von Daten , RECOGNITION OF DATA / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / 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 / G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS




    Vehicle multi-modal trajectory prediction method based on semi-supervised model

    TIAN WEI / WANG SONGTAO | European Patent Office | 2023

    Free access

    Trajectory Generation using Deep Neural Network

    Watanabe, Toshinobu / Johnson, Eric N. | AIAA | 2018



    Semi-supervised Data Mining Tool Design with Self-tuning Optimization Techniques

    Akhmedova, Shakhnaz / Semenkina, Maria / Stanovov, Vladimir et al. | Springer Verlag | 2019