A road traffic flow prediction system for predicting a road traffic flow from data received from a plurality of sensors, each sensor of the plurality of sensors for acquiring road traffic data at a respective traffic location, where the system is configured to: receive data from the sensors; implementing a machine learning algorithm to learn a model of a relationship between traffic flow at a first location and traffic flow at other locations where the sensor is located from a time series of the received data; the model is implemented to predict a time series of traffic flow at the first location from other data received from the sensors.
一种用于根据从多个传感器接收的数据预测道路交通流的道路交通流预测系统,所述多个传感器中的每个传感器用于在相应交通位置获取道路交通数据,其中,所述系统用于:从所述传感器接收数据;实现机器学习算法,以根据所述接收的数据的时间序列学习第一位置处的交通流与所述传感器所在的其它位置处的交通流之间的关系的模型;实现所述模型,以根据从所述传感器接收的其它数据预测所述第一位置处的交通流的时间序列。
Multi-step traffic prediction
多步交通预测
2022-04-05
Patent
Electronic Resource
Chinese
IPC: | G08G Anlagen zur Steuerung, Regelung oder Überwachung des Verkehrs , TRAFFIC CONTROL SYSTEMS |
Conv1D + LSTM-based multi-step traffic flow prediction method
European Patent Office | 2021
|