一个有效的稀疏轨迹数据相似性度量

An Effective Measure for Calculating the Similarity of Sparse Trajectory Data

随着GPS设备和无线通信等技术的快速发展,移动对象的轨迹数据的多样性和复杂性与日递增,对于这些数据的挖掘和分析越显重要。在观察时间内,轨迹是稀疏的—移动对象的轨迹点在时间维度上分布是不均匀,即轨迹点之间的时间间隔不是相等的,而且,移动对象的轨迹的时间跨度占整个观察时间的比例很小。传统的轨迹相似性方法不适用于分析稀疏轨迹的相似性。针对移动对象的稀疏轨迹进行研究,提出了一种基于关键点和时间分段的稀疏轨迹相似性度量,并在此基础上给出了一个相似性计算算法STS(Sparse Trajectory Similarity Computation),在真实数据集上的实验表明STS算法较现有算法具有更好的运行效率和准确度。

With the rapid expansion of GPS equipment and wireless communication,diversity and complexity of moving objects＇ trajectory data increase,so it＇s important to analyze these trajectory data.In observation time,the trajectory is sparse：moving objects＇ trajectory points distribute unevenly in time dimension,that is time intervals between trajectory points are not equal and time span of moving objects＇ trajectory is a small fraction of the total observation time.Conventional trajectory similarity methods are not suitable for analyzing the sparse trajectory similarity.This paper focuses on moving objects＇ sparsity issue in trajectory similarity and proposes a sparse trajectory similarity measurement based on key point and time slicing,and proposes a similarity computation algorithm （Sparse Trajectory Similarity Computation）.Experimental results based on real datasets confirm the effectiveness and efficiency of the proposed algorithm.