轨迹模式挖掘是轨迹数据知识发现的一个重要课题.由于定位设备的局限性,采集到的轨迹数据具有不确定性.着眼于不确定轨迹数据模式挖掘,通过引入模糊集方法,提出不确定轨迹数据模式挖掘方法.首先用均匀网格划分对象的运动平面,基于对象实际位置的概率分布计算轨迹点相对于每个网格的隶属度,通过不确定轨迹兴趣区域发现算法,得到所有的不确定兴趣区域,然后在此基础上进行轨迹模式挖掘.实验展示了所提出的不确定轨迹数据模式挖掘方法进行模式挖掘的效果.
Trajectory pattern mining is an important topic of knowledge discovery.Due to the limitations of location device,the trajectory data are not certain.The paper focuses on mining uncertain trajectory patterns.With the introduction of fuzzy set,a novel method is proposed to deal with uncertain trajectory data pattern mining.Firstly,the work space is divided by a grid whose cells are size uniform.The degree of membership of uncertain points relative to cells is calculated based on the probability distribution of moving object′s real position.Then obtain the regions through the uncertain regions of interest extracting method.Uncertain trajectory pattern mining is done based on regions of interest.Finally,the experiments show the effects of uncertain trajectory pattern mining using fuzzy theory.