中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 先进控制与自动化团队
Accurate and Interpretable Bayesian MARS for Traffic Flow Prediction

文献类型：期刊论文

作者Xu, Yanyan1,2; Kong, Qing-Jie3; Klette, Reinhard4; Liu, Yuncai1,2
刊名IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
出版日期2014-12-01
卷号15期号:6页码:2457-2469
关键词Bayesian inference interpretable model Markov chain Monte Carlo (MCMC) multivariate adaptive-regression splines (MARS) spatiotemporal relationship analysis traffic flow prediction
英文摘要Current research on traffic flow prediction mainly concentrates on generating accurate prediction results based on intelligent or combined algorithms but ignores the interpretability of the prediction model. In practice, however, the interpretability of the model is equally important for traffic managers to realize which road segment in the road network will affect the future traffic state of the target segment in a specific time interval and when such an influence is expected to happen. In this paper, an interpretable and adaptable spatiotemporal Bayesian multivariate adaptive-regression splines (ST-BMARS) model is developed to predict short-term freeway traffic flow accurately. The parameters in the model are estimated in the way of Bayesian inference, and the optimal models are obtained using a Markov chain Monte Carlo (MCMC) simulation. In order to investigate the spatial relationship of the freeway traffic flow, all of the road segments on the freeway are taken into account for the traffic prediction of the target road segment. In our experiments, actual traffic data collected from a series of observation stations along freeway Interstate 205 in Portland, OR, USA, are used to evaluate the performance of the model. Experimental results indicate that the proposed interpretable ST-BMARS model is robust and can generate superior prediction accuracy in contrast with the temporal MARS model, the parametric model autoregressive integrated moving averaging (ARIMA), the state-of-the-art seasonal ARIMA model, and the kernel method support vector regression.
WOS标题词Science & Technology ; Technology
类目[WOS]Engineering, Civil ; Engineering, Electrical & Electronic ; Transportation Science & Technology
研究领域[WOS]Engineering ; Transportation
关键词[WOS]REGRESSION ; SPLINES ; MODELS ; VOLUME
收录类别SCI
语种英语
WOS记录号WOS:000345572900009
源URL[http://ir.ia.ac.cn/handle/173211/3628]  
专题自动化研究所_复杂系统管理与控制国家重点实验室_先进控制与自动化团队
作者单位1.Shanghai Jiao Tong Univ, Dept Automat, Shanghai 200240, Peoples R China
2.Shanghai Jiao Tong Univ, China Key Lab Syst Control & Informat Proc, Minist Educ, Shanghai 200240, Peoples R China
3.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
4.Univ Auckland, Dept Comp Sci, Auckland 1020, New Zealand
推荐引用方式
GB/T 7714		 Xu, Yanyan,Kong, Qing-Jie,Klette, Reinhard,et al. Accurate and Interpretable Bayesian MARS for Traffic Flow Prediction[J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,2014,15(6):2457-2469.
APA Xu, Yanyan,Kong, Qing-Jie,Klette, Reinhard,&Liu, Yuncai.(2014).Accurate and Interpretable Bayesian MARS for Traffic Flow Prediction.IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,15(6),2457-2469.
MLA Xu, Yanyan,et al."Accurate and Interpretable Bayesian MARS for Traffic Flow Prediction".IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 15.6(2014):2457-2469.

入库方式： OAI收割

来源：自动化研究所

浏览0
下载0
收藏0
其他版本

除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。