To accurately detect an abnormal condition in traffic.SOLUTION: A traffic condition determination device comprises: a learning model that generates, from input data indicating a traffic condition in an abnormality detection region, output data indicating the traffic condition in the abnormality detection region; and a condition determination unit that determines whether or not a traffic abnormality condition is occurring on the basis of the input data and the output data. The learning model is an automatic encoder including a long short-term memory encoder, a repeat vector, and a long short-term memory decorder.SELECTED DRAWING: Figure 5

    【課題】交通における異常状態を正確に検出する。【解決手段】交通状態判定装置は、異常検知区域における交通状態を示す入力データから、前記異常検知区域における交通状態を示す出力データを生成する学習モデルと、前記入力データ及び前記出力データに基づいて、交通異常状態が発生しているか否かを判定する状態判定部と、を備え、前記学習モデルは、長・短期記憶エンコーダと、リピートベクタと、長・短期記憶デコーダと、を含むオートエンコーダである。【選択図】図5


    Access

    Download


    Export, share and cite



    Title :

    TRAFFIC CONDITION DETERMINATION DEVICE, TRAFFIC CONDITION DETERMINATION METHOD, COMPUTER PROGRAM, LEARNING MODEL, AND MACHINE LEARNING METHOD


    Additional title:

    交通状態判定装置、交通状態判定方法、コンピュータプログラム、学習モデル、及び機械学習方法


    Contributors:

    Publication date :

    2023-11-24


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Japanese


    Classification :

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



    TRAFFIC CONDITION DETERMINATION SYSTEM AND TRAFFIC CONDITION DETERMINATION DEVICE

    HIRATE MORIHIRO / TAKAHARA MASATOSHI / MIYAJI YUSUKE et al. | European Patent Office | 2020

    Free access

    Traffic condition determination method and device

    JIANG HAN / CHEN JIEYU / YU HAIFENG et al. | European Patent Office | 2022

    Free access


    TRAFFIC SITUATION DETERMINATION SYSTEM, TRAFFIC SITUATION DETERMINATION METHOD, COMPUTER PROGRAM, AND LEARNING MODEL

    CHIGA MAKOTO / NAKAO HIROSHI / KITAHARA TOSHIYA et al. | European Patent Office | 2022

    Free access