People and vehicle trajectories embody important information of transportation infrastructures, and trajectory similarity computation is functionality in many real-world applications involving trajectory data analysis. Recently, deep-learning based trajectory similarity techniques hold the potential to offer improved efficiency and adaptability over traditional similarity techniques. Nevertheless, the existing trajectory similarity learning proposals emphasize spatial similarity over temporal similarity, making them suboptimal for time-aware analyses. To this end, we propose ST2Vec, a trajectory-representation-learning based architecture that considers fine-grained spatial and temporal correlations between pairs of trajectories for spatio-temporal similarity learning in road networks. To the best of our knowledge, this is the first deep-learning proposal for spatio-temporal trajectory similarity analytics. Specifically, ST2Vec encompasses three phases: (i) training data preparation that selects representative training samples; (ii) spatial and temporal modeling that encode spatial and temporal characteristics of trajectories, where a generic temporal modeling module (TMM) is designed; and (iii) spatio-temporal co-attention fusion (STCF), where a unified fusion (UF) approach is developed to help generating unified spatio-temporal trajectory embeddings that capture the spatio-temporal similarity relations between trajectories. Further, inspired by curriculum concept, ST2Vec employs the curriculum learning for model optimization to improve both convergence and effectiveness. An experimental study offers evidence that ST2Vec outperforms all state-of-the-art competitors substantially in terms of effectiveness, efficiency, and scalability, while showing low parameter sensitivity and good model robustness.
翻译:人们和车辆轨迹体现了运输基础设施的重要信息,轨迹相似的计算是许多涉及轨迹数据分析的真实世界应用中的功能。最近,基于深层学习的轨迹相似技术有可能提高传统相似技术的效率和适应性。然而,现有的轨迹相似学习建议强调时间相似性的空间相似性,使其在时间相似性分析中不最优化。为此,我们提议ST2Vec(基于轨迹的代表制学习架构),考虑到空间与时间对齐的轨迹在空间与时间上的相关性,涉及轨迹数据对齐,涉及轨迹数据分析的轨迹分析。最近,基于深层学习的轨迹相似性技术相似性技术使我们最有可能提高与传统相似性技术相似性。具体来说,ST2Vec(i)包括三个阶段:(i) 培训数据准备工作,挑选具有代表性的培训样本;(ii) 空间和时间模型模型,将空间和时间上的轨迹特征编码,其中设计了一个通用的时空模型模块(TMM),用于空间-时际相似性相似的轨迹相似性学习模式;以及(iii) 空间-空间-空间-轨迹轨迹模型关系,用来显示同步-同步和空间-同步的轨迹系的轨迹系关系,同时生成的轨迹系的轨迹关系,通过生成的轨迹关系,通过生成的轨迹-轨迹系的轨迹迹迹迹迹系的轨迹系的轨迹系的轨迹迹迹迹迹迹迹迹关系,通过生成关系,通过生成的轨迹关系,通过生成关系,进一步生成的轨迹迹迹关系,通过生成的轨迹迹迹迹关系,通过生成的轨迹迹迹迹关系,通过生成的轨迹关系,通过生成的轨迹-轨迹-轨迹-感-轨迹-感-轨迹-轨迹-感-轨迹-感-感-轨迹-轨迹-轨迹-轨迹-轨关系形成-轨关系形成-感-轨迹-轨迹-轨迹-感-轨迹-轨迹-轨迹-轨迹-感-轨迹-轨迹-轨迹-轨迹-轨关系形成-轨迹-轨迹-轨迹-轨迹-轨迹-轨迹-轨迹-轨迹-轨迹-轨迹-轨迹-轨迹-轨迹-