A Variational Bayesian Inference-Based En-Decoder Framework for Traffic Flow Prediction

文献类型： 外文期刊

第一作者： Kong, Jianlei

作者： Kong, Jianlei;Fan, Xiaomeng;Jin, Xuebo;Lin, Sen;Zuo, Min

作者机构：

关键词： Traffic flow prediction; time-series data prediction; variational Bayesian inference; multi-head attention; deep learning; encoder-decoder

期刊名称：IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS （ 影响因子：8.5； 五年影响因子：9.0 ）

ISSN： 1524-9050

年卷期： 2023 年

页码：

收录情况： SCI

摘要： Accurate traffic flow prediction, a hotspot for intelligent transportation research, is the prerequisite for traffic flow prediction for making travel plans. The speed of traffic flow can be affected by roads condition, weather, holidays, etc. Moreover, sensors to catch the information about traffic flow will be interfered with by environmental factors such as illumination, collection time, occlusion, etc. Therefore, the traffic flow in the practical transportation system is complicated, uncertain, and challenging to predict accurately. Motivated from the aforementioned issues and challenges, in this paper, we propose a deep encoder-decoder prediction framework based on variational Bayesian inference. A Bayesian neural network is designed by combining variational inference with Gated Recurrent Units (GRU) which is used as the deep neural network unit of the encoder-decoder framework to mine the intrinsic dynamics of traffic flow. Then, the variational inference is introduced into the multi-head attention mechanism to avoid noise-induced deterioration of prediction accuracy. The proposed model achieves superior prediction performance on the Guangzhou urban traffic flow dataset over the benchmarks, particularly when the long-term prediction.

分类号：

  • 相关文献
作者其他论文 更多>>

微信小程序