The invention discloses a short-term traffic flow prediction method in combination with data decomposition and deep learning, which is a short-term traffic flow prediction method based on complementary ensemble empirical mode decomposition (CEEMD) and in combination with a convolutional neural network (CNN) and a long short-term memory network (LSTM). According to the traffic flow prediction model, the influence of noise on traffic flow data prediction is reduced through CEEMD signal decomposition, and spatial-temporal characteristics of data are fully mined by adopting CNN and LSTM, so that the model makes more accurate judgment, and the learning efficiency of the neural network is improved. The invention combines the advantages of data decomposition and deep learning, and provides a short-term traffic flow prediction method, thereby achieving a more scientific means and improving the accuracy of short-term traffic flow prediction.
本发明公开了一种结合数据分解和深度学习的短时交通流预测方法,基于互补集成经验模态分解(CEEMD),并结合卷积神经网络(CNN)和长短期记忆网络(LSTM)的短时交通流预测方法。交通流预测模型通过CEEMD信号分解减少噪声对交通流数据预测的影响,采用CNN、LSTM充分挖掘数据的时空特征,使得模型做出更加准确的判断,从而提高神经网络的学习效率。本发明结合数据分解和深度学习的优点,给出一种短时交通流预测方法,从而达到更科学的手段,提高短时交通流预测准确率的目的。
Short-term traffic flow prediction method combining data decomposition and deep learning
一种结合数据分解和深度学习的短时交通流预测方法
2022-08-30
Patent
Electronic Resource
Chinese
Deep Learning for Short-Term Traffic Flow Prediction
Online Contents | 2016
|Short-term traffic flow prediction using deep learning
SLUB | 2023
|Short-term traffic flow prediction method based on deep learning
European Patent Office | 2025
|Short-term traffic flow prediction method based on deep learning
European Patent Office | 2020
|