The invention provides a traffic flow time sequence data prediction method and system based on CEEMDAN-RF-LSTM, and the method comprises the steps: collecting and preprocessing time sequence data, and decomposing an original sequence into a plurality of IMFs with different frequencies through CEEMDAN in the traffic flow prediction aspect; then, a prediction model of the high-frequency IMF is established, an RF algorithm is used, and the performance of the model is optimized by adjusting and optimizing hyper-parameters; and then, establishing a low-frequency IMF prediction model by using an LSTM network, and adjusting network parameters to improve a prediction effect. And finally, through linear weighted fusion of the RF prediction result of the high-frequency IMF and the LSTM prediction result of the low-frequency IMF, final prediction output of the time sequence is obtained. The method can help a decision maker to better understand traffic demands and formulate an effective traffic management strategy so as to improve traffic planning and reduce congestion problems. In addition, the method can also be applied to high-frequency big data modeling and prediction of the number of passengers, the vehicle flow, the traffic delay and the like in public transportation, and has relatively high prediction accuracy and stability.
本发明提供了一种基于CEEMDAN‑RF‑LSTM的交通流量时间序列数据预测方法及系统,在交通流量预测方面,首先,采集和预处理时间序列数据,并利用CEEMDAN将原始序列分解为多个不同频率的IMF。然后,建立高频IMF的预测模型使用RF算法,并通过调优超参数来优化模型性能。接下来,利用LSTM网络建立低频IMF的预测模型,并调整网络参数以提高预测效果。最后,通过线性加权融合高频IMF的RF预测结果和低频IMF的LSTM预测结果,得到时间序列的最终预测输出。该方法可以帮助决策者更好地了解交通需求,制定有效的交通管理策略,以改善交通规划并减少拥堵问题。此外,该方法还可应用于公共交通乘客数量、车辆流量、交通延迟等高频大数据建模和预测,具有较高的预测准确率和稳定性。
CEEMDAN-RF-LSTM-based traffic flow time sequence data prediction method and system
基于CEEMDAN-RF-LSTM的交通流量时间序列数据预测方法及系统
2024-02-20
Patent
Electronic Resource
Chinese
IPC: | G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung / 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 |
Prediction of Bus Passenger Flow Based on CEEMDAN-BP Model
SAE Technical Papers | 2020
|Flutter boundary prediction method based on CEEMDAN
British Library Conference Proceedings | 2022
|