The invention provides a traffic flow prediction method based on singular spectrum decomposition and SSA-BiLSTM, and the method is characterized in that the method comprises the following steps: S1, carrying out the data cleaning of historical traffic flow data, and obtaining the cleaned data; s2, performing singular spectrum analysis on the cleaned data to obtain a non-principal component sequence and a principal component sequence; s3, inputting the non-principal component sequence into the first SSA-BiLSTM network to obtain a noise prediction result; s4, inputting the principal component sequence into a second SSA-BiLSTM network to obtain a period prediction result; and S5, reconstructing the noise prediction result and the period prediction result to obtain a traffic flow prediction result. In a word, the method can obtain a more accurate traffic flow prediction result.
本发明提供了一种基于奇异谱分解与SSA‑BiLSTM的交通流量预测方法,具有这样的特征,包括以下步骤:步骤S1,对历史交通流量数据进行数据清洗,得到清洗数据;步骤S2,将清洗数据进行奇异谱分析,得到非主成分序列和主成分序列;步骤S3,将非主成分序列输入第一SSA‑BiLSTM网络,得到噪声预测结果;步骤S4,将主成分序列输入第二SSA‑BiLSTM网络,得到周期预测结果;步骤S5,将噪声预测结果和周期预测结果进行重构,得到交通流量预测结果。总之,本方法能够得到更准确的交通流量预测结果。
Traffic flow prediction method based on singular spectrum decomposition and SSA-BiLSTM
基于奇异谱分解与SSA-BiLSTM的交通流量预测方法
2024-10-22
Patent
Electronic Resource
Chinese
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 / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung |
BiLSTM- and GNN-Based Spatiotemporal Traffic Flow Forecasting with Correlated Weather Data
DOAJ | 2023
|