The present invention relates to a method for predicting traffic congestion based on LSTM, and more specifically, to a method and apparatus for predicting traffic congestion based on LSTM which conducts missing value imputation and predicts traffic congestion based on LSTM by extracting space-time characteristics from traffic flow data. According to an embodiment of the present invention, the apparatus for predicting traffic congestion based on LSTM can learn time series characteristics of traffic data by considering aspects of orders or time. According to another embodiment of the present invention, the apparatus for predicting traffic congestion based on LSTM can provide a prediction with high accuracy because external disturbance affecting traffic is smaller in an outskirt area than in an urban area, such that factors serving as variables are reduced when predicted. The apparatus comprises a data collection unit, a data correction unit, a preprocessing unit and a prediction unit.

    본 발명은 LSTM 기반 교통 혼잡도 예측 방법에 관한 것으로, 더욱 상세하게는 교통 흐름 데이터에서 시공간 특징을 추출을 활용한 결측 대치 및 LSTM 기반 교통 혼잡도를 예측하는 LSTM 기반 교통 혼잡도 예측 방법 및 장치에 관한 것이다. 본 발명의 실시예에 따르면, LSTM 기반 교통 혼잡도 예측 장치는 순서 또는 시간이라는 측면을 고려하여 교통 데이터의 시계열적인 특성을 학습할 수 있다. 본 발명의 다른 실시예에 따르면, LSTM 기반 교통 혼잡도 예측 장치는 도심 외곽지역이 도심지보다 외부의 방해로 인한 교통 흐름에 영향이 작기 때문에 예측 시 변수 작용을 하는 요인이 줄어들어 정확도가 높은 예측을 제공할 수 있다.


    Access

    Download


    Export, share and cite



    Title :

    LSTM METHOD AND APPARATUS FOR PREDICTION OF TRAFFIC CONGESTION BASED ON LSTM


    Additional title:

    LSTM 기반 교통 혼잡도 예측 방법 및 장치


    Contributors:

    Publication date :

    2022-12-23


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    Korean


    Classification :

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




    LSTM LSTM-based future threat prediction method and apparatus

    PARK YOUNG TACK / JEON MYUNG JOONG / KIM MIN SUNG et al. | European Patent Office | 2021

    Free access

    Traffic flow prediction method based on LSTM-Attention

    QIN XIAOLIN / LIU JIACHEN / SONG LIXIANG et al. | European Patent Office | 2021

    Free access

    Traffic situation prediction method based on LSTM model

    HU WEN / LUO MAN / PENG BO | European Patent Office | 2024

    Free access

    Intelligent Traffic Prediction Using LSTM Network

    Vidya, G. S. / Hari, V. S. / Shivasagaran, Suryakumar | Springer Verlag | 2021