天津师范大学学报（自然科学版）2025，Vol.45Issue(3)：68-73,6.DOI:10.19638/j.issn1671-1114.20250310
基于语境特征注入的交通流速度预测模型
Traffic flow speed prediction based on context feature injection and fusion
摘要
Abstract
A traffic flow speed prediction model based on context feature injection is proposed.The time series features and context features of traffic flow speed data are learned and extracted through recurrent neural networks and deep belief networks,respectively.The vector fusion mechanism is used to inject the extracted context features into the time series features to generate new fusion features,which are used for traffic flow speed prediction.The experimental results show that the proposed model can reflect the real state of the traffic flow speed and accurately capture the stochastic changes of traffic speed,and has good predic-tive performance.On six time scales,such as 5 min and 10 min,the prediction error of the model is better than that of other comparison models.关键词
交通流预测/时间序列/语境特征/门控循环单元/深度置信网络Key words
traffic flow prediction/time series/context features/gated recurrent unit/deep belief networks分类
信息技术与安全科学引用本文复制引用
于强,康洪超,蔺大朋,高琳琦..基于语境特征注入的交通流速度预测模型[J].天津师范大学学报（自然科学版）,2025,45(3):68-73,6.基金项目
天津市教委社会科学重大项目(2020JWZD19) （2020JWZD19）
北京市教委科技计划资助项目(KM201810028021). （KM201810028021）
