基于高斯混合-贝叶斯模型的轨迹预测
|
摘要
如今,在交通管理系统、军事机械化战场、安全行驶系统中,对实时、准确、可靠的移动对象轨迹预测具有很重要的作用,在市场上的应用越来越广,简称智能化预测。智能化预测可以提供精准的基于位置的服务,还可以根据预判,给车主推荐最优路线,这成为移动对象数据库研究的热点。针对现有方法的不足,提出基于高斯混合-贝叶斯模型的轨迹预测模型。实验表明,GM-BM模型在路段车流量正常情况下,通过调整混合模型中子模型的权重,可预测出最可能的轨迹,经计算与相同参数设置下的单模型相比,预测准确性至少提高10. 00%。
Nowadays,real-time,accurate and reliable track prediction of moving objects plays a very important role in traffic management system,military mechanized battlefield and safe driving system,which has been applied more and more widely in the market,namely intelligent prediction. Intelligent prediction can provide accurate location-based services,and it can also recommend optimal routes to car owners based on pre-judgment,which has become a hot spot of research on mobile object database.Aiming at the shortcomings of the existing methods,a Gaussian mixture-Bayesian trajectory prediction model is proposed. The experimental results show that the GM-BM model can predict the most likely trajectory by adjusting the weight of the neutron model of the mixed model under the normal traffic flow of road section. After calculation,the prediction accuracy is improved by at least10. 00% compared with the single model under the same parameter setting.
Nowadays,real-time,accurate and reliable track prediction of moving objects plays a very important role in traffic management system,military mechanized battlefield and safe driving system,which has been applied more and more widely in the market,namely intelligent prediction. Intelligent prediction can provide accurate location-based services,and it can also recommend optimal routes to car owners based on pre-judgment,which has become a hot spot of research on mobile object database.Aiming at the shortcomings of the existing methods,a Gaussian mixture-Bayesian trajectory prediction model is proposed. The experimental results show that the GM-BM model can predict the most likely trajectory by adjusting the weight of the neutron model of the mixed model under the normal traffic flow of road section. After calculation,the prediction accuracy is improved by at least10. 00% compared with the single model under the same parameter setting.
引文
[1]李万高,赵雪梅,孙德厂.基于改进贝叶斯方法的轨迹预测算法研究[J].计算机应用,2013,33(7):1960-1963.
[2] LI Z B,LIU P,WANG W,et al. Using support vector machine models for crash injury severity analysis[J]. Accident Analysis&Prevention,2012,45:478-486.
[3]张迎亚.基于隐马尔可夫模型的车辆轨迹预测算法的研究[D].南京:南京邮电大学,2017.
[4]陈思静,张可. VANETs中的车辆移动规律性及轨迹预测研究[J].计算机工程与应用,2016,52(18):139-143.
[5]卓鹏宇.基于时间序列分析的股票趋势预测模型研究[D].杭州:浙江工业大学,2016.
[6]王俊华,左万利,闫昭.基于朴素贝叶斯模型的单词语义相似度度量[J].计算机研究与发展,2015,52(7):1499-1509.
[7]刘章君,郭生练,李天元,等.贝叶斯概率洪水预报模型及其比较应用研究[J].水利学报,2014,45(9):1019-1028.
[8] BABU N,SUJATHA S,NARAYANAN S,et al. New approach for prediction of influence of vehicle dynamics parameters on instability of unmanned track vehicle using robotic approach[J]. Journal of Mechanical Science and Technology,2018,32(3):1357-1365.
[9] YU B,YIN H T,ZHU Z X. Spatio-Temporal Graph Convolutional Networks:A Deep Learning Framework for Traffic Forecasting[DB/OL].(2017-09-14). https://arxiv. org/pdf/1709. 04875v1. pdf.
[10]陈英.高斯混合模型聚类及其优化算法研究[D].南昌:华东交通大学,2015.
[11]刘平. ANSYS网格划分精度与计算精度[C]//2016年中国水产学会学术年会论文摘要集. 2016:298.
[12]詹盛,徐远新,石涌泉,等.基于模糊着色Petri网的车辆运动轨迹预测[J].计算机工程与应用,2014,50(3):227-231.
[13]高磊,刘乐平,卢志义.大数据背景下贝叶斯模型平均的理论突破与应用前景[J].统计与信息论坛,2016,31(6):14-22.
[14] COELHO I M,COELHO V N,LUZ E J D S,et al. A GPU deep learning metaheuristic based model for time se-ries forecasting[J]. Applied Energy,2017,201:412-418.
[15]张永华,杜煜,潘峰,等.基于三次B样条曲线拟合的智能车轨迹跟踪算法[J].计算机应用,2018,38(6):1562-1567.
[16] AL-MILLI S,SENEVIRATNE L D,ALTHOEFER K.Track-terrain modelling and traversability prediction for tracked vehicles on soft terrain[J]. Journal of Terramechanics,2010,47(3):151-160.
[17]朱军,胡文波.贝叶斯机器学习前沿进展综述[J].计算机研究与发展,2015,52(1):16-26.
[18]丁军,张佐,陈洪昕,等.车辆轨迹数据的若干处理方法研究[J].交通信息与安全,2011,29(5):10-14.
[19]夏卓群,胡珍珍,罗君鹏. EAVTP:一种环境自适应车辆轨迹预测方法[J].小型微型计算机系统,2016,37(10):2375-2379.
[20]唐克双,杨博文,许凯,等.基于车辆轨迹数据的交叉口危险驾驶行为预测[J].同济大学学报(自然科学版),2017,45(10):1454-1461.
[21]董学仁.基于立体视觉的球状飞行物体的轨迹预测的研究[D].厦门:厦门大学,2014.
[22]彭曲,丁治明,郭黎敏.基于马尔可夫链的轨迹预测[J].计算机科学,2010,37(8):189-193.
[23] LIANG Y X,KE S Y,ZHANG J B,et al. Geo MAN:Multi-level attention networks for geo-sensory time series prediction[C]//Proceedings of the 27th International Joint Conference on Artificial Intelligence. 2018:3428-3434.
[2] LI Z B,LIU P,WANG W,et al. Using support vector machine models for crash injury severity analysis[J]. Accident Analysis&Prevention,2012,45:478-486.
[3]张迎亚.基于隐马尔可夫模型的车辆轨迹预测算法的研究[D].南京:南京邮电大学,2017.
[4]陈思静,张可. VANETs中的车辆移动规律性及轨迹预测研究[J].计算机工程与应用,2016,52(18):139-143.
[5]卓鹏宇.基于时间序列分析的股票趋势预测模型研究[D].杭州:浙江工业大学,2016.
[6]王俊华,左万利,闫昭.基于朴素贝叶斯模型的单词语义相似度度量[J].计算机研究与发展,2015,52(7):1499-1509.
[7]刘章君,郭生练,李天元,等.贝叶斯概率洪水预报模型及其比较应用研究[J].水利学报,2014,45(9):1019-1028.
[8] BABU N,SUJATHA S,NARAYANAN S,et al. New approach for prediction of influence of vehicle dynamics parameters on instability of unmanned track vehicle using robotic approach[J]. Journal of Mechanical Science and Technology,2018,32(3):1357-1365.
[9] YU B,YIN H T,ZHU Z X. Spatio-Temporal Graph Convolutional Networks:A Deep Learning Framework for Traffic Forecasting[DB/OL].(2017-09-14). https://arxiv. org/pdf/1709. 04875v1. pdf.
[10]陈英.高斯混合模型聚类及其优化算法研究[D].南昌:华东交通大学,2015.
[11]刘平. ANSYS网格划分精度与计算精度[C]//2016年中国水产学会学术年会论文摘要集. 2016:298.
[12]詹盛,徐远新,石涌泉,等.基于模糊着色Petri网的车辆运动轨迹预测[J].计算机工程与应用,2014,50(3):227-231.
[13]高磊,刘乐平,卢志义.大数据背景下贝叶斯模型平均的理论突破与应用前景[J].统计与信息论坛,2016,31(6):14-22.
[14] COELHO I M,COELHO V N,LUZ E J D S,et al. A GPU deep learning metaheuristic based model for time se-ries forecasting[J]. Applied Energy,2017,201:412-418.
[15]张永华,杜煜,潘峰,等.基于三次B样条曲线拟合的智能车轨迹跟踪算法[J].计算机应用,2018,38(6):1562-1567.
[16] AL-MILLI S,SENEVIRATNE L D,ALTHOEFER K.Track-terrain modelling and traversability prediction for tracked vehicles on soft terrain[J]. Journal of Terramechanics,2010,47(3):151-160.
[17]朱军,胡文波.贝叶斯机器学习前沿进展综述[J].计算机研究与发展,2015,52(1):16-26.
[18]丁军,张佐,陈洪昕,等.车辆轨迹数据的若干处理方法研究[J].交通信息与安全,2011,29(5):10-14.
[19]夏卓群,胡珍珍,罗君鹏. EAVTP:一种环境自适应车辆轨迹预测方法[J].小型微型计算机系统,2016,37(10):2375-2379.
[20]唐克双,杨博文,许凯,等.基于车辆轨迹数据的交叉口危险驾驶行为预测[J].同济大学学报(自然科学版),2017,45(10):1454-1461.
[21]董学仁.基于立体视觉的球状飞行物体的轨迹预测的研究[D].厦门:厦门大学,2014.
[22]彭曲,丁治明,郭黎敏.基于马尔可夫链的轨迹预测[J].计算机科学,2010,37(8):189-193.
[23] LIANG Y X,KE S Y,ZHANG J B,et al. Geo MAN:Multi-level attention networks for geo-sensory time series prediction[C]//Proceedings of the 27th International Joint Conference on Artificial Intelligence. 2018:3428-3434.