计算机应用 ›› 2013, Vol. 33 ›› Issue (07): 1960-1963.DOI: 10.11772/j.issn.1001-9081.2013.07.1960

• 人工智能 • 上一篇    下一篇

基于改进贝叶斯方法的轨迹预测算法研究

李万高1,赵雪梅2,孙德厂3   

  1. 1. 河南工程学院 计算机学院,郑州 451191
    2. 郑州升达经贸管理学院,郑州 451191
    3. 中国科学院 沈阳自动化研究所,沈阳 110016
  • 收稿日期:2013-01-30 修回日期:2013-02-27 出版日期:2013-07-01 发布日期:2013-07-06
  • 通讯作者: 李万高
  • 作者简介:李万高(1973-),男,河南兰考人,讲师,硕士,主要研究方向:智能数据管理;赵雪梅(1966-),女,河南濮阳人,副教授,硕士,主要研究方向:智能控制;孙德厂(1976-),男,河南兰考人,博士研究生,主要研究方向:生产计划与控制、先进制造。
  • 基金资助:

    国家重大科技专项(2011ZX02507-006)

Prediction of trajectory based on modified Bayesian inference

LI Wangao1,ZHAO Xuemei2,SUN Dechang3   

  1. 1. School of Computer, Henan Institute of Engineering, Zhengzhou Henan 451191, China
    2. Shengda Trade Economics and Management College of Zhengzhou, Zhengzhou Henan 451191, China
    3. Shenyang Institute of Automation, Chinese Academic of Science, Shenyang Liaoning 110016, China
  • Received:2013-01-30 Revised:2013-02-27 Online:2013-07-06 Published:2013-07-01
  • Contact: LI Wangao

摘要: 针对传统轨迹预测方法在历史轨迹数目有限时,预测准确度较低的问题,提出一种改进的贝叶斯推理(MBI)方法,MBI构建了马尔可夫模型来量化相邻位置的相关性,并通过对历史轨迹进行分解来获得更准确的马尔可夫模型,最后得到改进的贝叶斯推理公式。实验结果表明,MBI方法比现有方法的预测速度快2到3倍,并且有较高的准确度和稳定性。MBI方法充分利用现有轨迹信息,不仅提高了查询效率,还保证了较高的预测精度。

关键词: 轨迹预测, 马尔可夫模型, 贝叶斯推理

Abstract: The existing algorithms for trajectory prediction have very low prediction accuracy when there are a limited number of available trajectories. To address this problem, the Modified Bayesian Inference (MBI) approach was proposed, which constructed the Markov model to quantify the correlation between adjacent locations. MBI decomposed historical trajectories into sub-trajectories to get more precise Markov model and the probability formula of Bayesian inference was obtained. The experimental results based on real datasets show that MBI approach is two to three times faster than the existing algorithm, and it has higher prediction accuracy and stability. MBI makes full use of the available trajectories and improves the efficiency and accuracy for the prediction of trajectory.

Key words: trajectory prediction, Markov model, Bayesian inference

中图分类号: