顾及路口转移偏好和当前移动模式的个体驾驶目的地预测方法

扫码查看

原文链接

NETL
NSTL
万方数据

中文摘要：个体驾驶目的地预测在个性化服务推荐、智慧交通等位置服务中具有重要的应用价值,但现有深度学习方法多以高密度采样轨迹点为单位构建出行特征,导致数据冗余、信息增益有限.路口序列可简化道路驾驶轨迹的表达形态,降低训练成本;同时,路口间的转移偏好与当前移动模式隐含路口与目的地间的时空关联关系,能够一定程度上表征个体出行意图,却鲜有研究将其用于目的地预测.为此,提出一种顾及路口转移偏好和当前移动模式的个体驾驶目的地预测方法:(1)以路口为单位构建输入特征,利用图注意力机制学习不同时间槽内路口间的转移系数,并结合长短期记忆模型捕获转移偏好长期依赖关系;(2)构建时间循环编码与驾驶状态特征,利用长短期记忆模型学习个体当前移动模式表征;(3)通过特征交叉与注意力机制实现特征融合,并利用残差网络输出预测.基于中国深圳市12名私家车司机2019年全年的轨迹数据开展实验,通过与隐马尔可夫、长短期记忆模型、远近距离依赖模型、融合地理语义与位置重要性的长短期记忆模型的精度进行对比并进行消融实验,验证了所提方法的有效性;可视化分析了转移偏好在捕获路口间空间关联关系中的作用,并探讨转移路口数量设置对预测精度的影响.

外文标题：Individual Driving Destination Prediction by Considering Intersection Transfer Preference and Current Movement Mode

外文摘要：Objectives:Individual driving destination prediction has important value in location-based services such as personalized services recommendation and intelligent transportation.However,most of the existing deep learning methods construct travel features on the basis of densely-sampled trajectory points,which generate data redundancy but only achieve limited information gain,and in turn introduce negative impacts on model training.Road intersection sequence can simplify the expression of driving trajectories restricted on the roads,and reduce the model training cost.Meanwhile,transfer preference between intersections and current movement mode imply the spatiotemporal correlation between road intersections and destinations,and are capable to represent individual travel intention to some extent,but few researches have applied them to destination prediction.Methods:This paper proposes a novel individual driving destination prediction method that takes intersection transfer preference(ITP)and current movement mode(CMM)into account,named ITP-CMM.First,it constructs input features in units of each intersection,and adopts graph attention network to learn the individual-level transfer coefficients between intersections in different time slots.Then,it uses long short-term memory(LSTM)to capture the long-term dependence of transfer preferences.Second,ITP-CMM constructs time cyclic encoding features and driving features to learn current move mode by using two-layered LSTM.Third,intersection transfer preferences and current move mode are fused and weighted through feature intersection and attention mechanisms respectively.And the stacked residual networks are introduced to output prediction results.Results and Conclusions:Based on the trajectory data of twelve private car drivers in Shenzhen City,China for the whole year of 2019,this paper has conducted a group of experiments to verify the feasibility of the proposed method ITP-CMM.We verify the effectiveness of the proposed method by carrying out ablation experiments and comparing the prediction accuracy and stability of ITP-CMM with four baselines,including hidden Markov model,LSTM,distance neighboring dependencies model and attention-aware LSTM for real-time driving destination prediction by considering location semantics and location im-portance trajectory points.Besides,we demonstrate the value of transfer preference in capturing the spatial correlation between intersections through visual analytics,and explore the impact of the number of transfer intersections on the prediction accuracy.

外文关键词：

trajectory predictiontraveling patternlocation-based servicesindividual drivingdestina-tionpredictionintersection transfer preferencemovement mode

作者：

桂志鹏、杨乐、丁劲宸、王锦添、孙云增、吴华意

展开 >

作者单位：

武汉大学遥感信息工程学院,湖北武汉,430079

武汉大学测绘遥感信息工程国家重点实验室,湖北武汉,430079

航天科工智能运筹与信息安全研究院(武汉)有限公司,湖北武汉,430040

关键词：

轨迹预测出行模式位置服务个体驾驶目的地预测路口转移偏好移动模式

基金：

国家重点研发计划国家重点研发计划国家自然科学基金国家自然科学基金

项目编号：

2018YFC08098062017YFB05037044197134942090010

出版年：

2024

DOI：

10.13203/j.whugis20210555

武汉大学学报(信息科学版)

武汉大学

武汉大学学报(信息科学版)

CSTPCD北大核心

影响因子：1.072

ISSN：1671-8860

年,卷(期)：2024.49(5)

参考文献量32