Traffic flow prediction plays a crucial role in traffic management and urban planning. Accurate predictions can effectively alleviate traffic congestion and enhance the overall efficiency of the transportation system. In this paper, we propose a traffic flow prediction method based on EMD-BiLSTM. The method first uses Empirical Mode Decomposition (EMD) to process the raw traffic flow data, breaking it down into multiple Intrinsic Mode Functions (IMFs) and a residue. The advantage of EMD is its ability to precisely extract the inherent characteristics of the data, thereby effectively reducing the complexity of the subsequent prediction model. Subsequently, a Bi-Directional Long Short-Term Memory (BiLSTM) network is employed to predict each IMF and the residue. The unique structure of the BiLSTM network enables it to capture both the long-term trends and short-term fluctuations in the data, demonstrating a strong capability for modeling the spatiotemporal characteristics of traffic flow. The experimental results fully demonstrate that our proposed method has a significant advantage over other deep learning methods in terms of prediction accuracy and stability. Specifically, the Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) of our method are significantly lower than those of other comparative methods. Furthermore, a case study using an actual traffic flow dataset further verifies the effectiveness and feasibility of the proposed method.
Research on Traffic Flow Prediction Methods Based on EMD-BiLSTM
28.03.2025
694571 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Traffic flow prediction method based on singular spectrum decomposition and SSA-BiLSTM
Europäisches Patentamt | 2024
|BiLSTM- and GNN-Based Spatiotemporal Traffic Flow Forecasting with Correlated Weather Data
DOAJ | 2023
|Short-term traffic congestion prediction with Conv–BiLSTM considering spatio-temporal features
IET | 2021
|Short‐term traffic congestion prediction with Conv–BiLSTM considering spatio‐temporal features
Wiley | 2020
|