Scholarlink

With the growth of intelligent transportation systems, enhancing the accuracy of short-term traffic flow predictions is crucial for effective real-time traffic management. This paper introduces a method for short-term traffic flow forecasting that utilizes Empirical Mode Decomposition (EMD) for data processing, combined with a LightGBM model optimized through Bayesian optimization. EMD first decomposes the traffic flow data. Then, Bayesian optimization fine-tunes the LightGBM model parameters, creating a prediction model. The method’s effectiveness is assessed using publicly available traffic flow data and compared to existing algorithms. Results show that this approach better captures traffic flow trends, offering improved prediction accuracy for short-term forecasting.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Boosting Short-Term Traffic Flow Prediction with EMD and Bayesian Optimization

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Zhuang Ma,
  • Chuan’gang Zhao,
  • Tao Du,
  • Tao Shen

摘要

With the growth of intelligent transportation systems, enhancing the accuracy of short-term traffic flow predictions is crucial for effective real-time traffic management. This paper introduces a method for short-term traffic flow forecasting that utilizes Empirical Mode Decomposition (EMD) for data processing, combined with a LightGBM model optimized through Bayesian optimization. EMD first decomposes the traffic flow data. Then, Bayesian optimization fine-tunes the LightGBM model parameters, creating a prediction model. The method’s effectiveness is assessed using publicly available traffic flow data and compared to existing algorithms. Results show that this approach better captures traffic flow trends, offering improved prediction accuracy for short-term forecasting.