期刊文献+

一种面向不确定对象的可见k近邻查询算法 被引量:11

Visible k Nearest Neighbor Queries over Uncertain Data
在线阅读 下载PDF
导出
摘要 真实世界中,常存在很多障碍物,影响空间对象到查询点的可见性及距离,可见k近邻查询查找距查询点最近的k个可见对象,是时空查询领域的一类重要算法.由于度量设备误差以及通信开销的限制等因素,空间对象位置不确定因素广泛存在.文中拟对不确定对象执行可见k近邻查询,提出了概率可见k近邻(PVkNN)查询,即查找前k个成为查询点最近邻居概率最大的节点.为了高效地执行这一查询,文中提出了k-界限剪枝方法,基于可见质心的紧缩过滤以及对不可见对象的剪枝策略,从空间角度过滤掉不符合条件的对象.为避免对候选集合中每个对象的概率都进行精确计算,从概率角度提出了根据概率上下限来对候选集合进行进一步的求精方法,采用近似采样技术来获取可见区域的比例,实现了对PVkNN的高效计算.采用真实和模拟数据集设计实验,充分验证了算法的效率和精度. In many spatial applications, there are physical obstacles which affect the distance and the visibility between two objects. The visible k nearest neighbor(VkNN) query is one of signifi- cant queries to search the space with obstacles. Due to the measurement errors, the limitation of communications and so on, uncertainty of object location is inherent in spatial database. This pa- per proposes a variant of the VkNN query which evaluates on uncertain data, namely probabilistic visible k nearest neighbor (PVkNN) query. A PVkNN query retrieves k objects visible to q with the maximum probability to be the nearest neighbor of the query point q. In order to improve the processing efficiency, this paper further proposes three spatial pruning methods and a probabilis- tic refinement method, proposes the k-bound pruning, visible center based pruning and the invisi- ble objects pruning methods. This paper also proposes a probabilistic refinement mechanism to avoid the integral computation for each object in the candidate set. Extensive experiments demonstrate the efficiency and the effectiveness of the proposed algorithms.
出处 《计算机学报》 EI CSCD 北大核心 2010年第10期1943-1952,共10页 Chinese Journal of Computers
基金 国家自然科学基金(60773220 61003058) 国家"八六三"高技术研究发展计划项目基金(2009AA01Z131)资助~~
关键词 概率可见k近邻查询 不确定对象 空间剪枝 概率上下限求精 probabilistic visible κ nearest neighbor uncertain object spatial pruning probabilis tic refinement
作者简介 王艳秋,女,1986年生,博士研究生,主要研究方向为不确定数据管理、时空数据库.E-mail:wangyanqiu@ise.neu.edu.cn. 徐传飞,男,1984年生,博士研究生,主要研究方向为不确定数据库、模糊数据管理等. 于戈,男,1962年生,教授,博士生导师,主要研究领域为数据库理论与技术. 谷峪,男,1981年生,副教授,主要研究方向为时空数据管理、不确定数据管理. 陈默,女,1983年生,博士研究生,主要研究方向为时空数据管理.
  • 相关文献

参考文献11

  • 1Netanong S, Tanin E, Zhang R. Visible nearest neighbor queries//Proceedings of the Database Systems for Advanced Applications. Bangkok, 2007:876- 883.
  • 2Nutanong S, Tanin E, Zhang R. Incremental evaluation of visible nearest neighbor queries. IEEE Transactions on Knowledge and Data Engineering (TKDE), 2010, 22 (5) 665-681.
  • 3Gao Y J, Zheng B H, Lee W C, Chen G C. Continuous visible nearest neighbor queries//Proeeedings of the Internation al Conference on Extending Database Technology. Saint Petersburg, 2009:144-155.
  • 4Cheng R, Kalashnikov D V, Prabhakar S. Querying imprecise data in moving object environments. IEEE Transactions on Knowledge and Data Engineering(TKDE), 2004, 16(9): 1112-1127.
  • 5Kriegel H P, Kunath P, Renz M. Probabilistic nearest neighbor query on uncertain objects//Proceedings of the Da tabase Systems for Advanced Applications. Bangkok, 2007 337-348.
  • 6Cheng R, Chen J C, Mokbel M F, Chow C Y. Probabilistic verifiers: Evaluating constrained nearest neighbor queries over uncertain data//Proceedings of the International Conference on Data Engineering. Cancfin, 2008 973-982.
  • 7Beskales G, Soliman M A, Ilyas I F. Efficient search for the top k probable nearest neighbors in uncertain databases// Proceedings of the VLDB Endowment. 2008, 1(1) 326-339.
  • 8Tao Y F, Xiao X K, Cheng R. Range search on multidimensional uncertain data. ACM Transactions on Database Systems, 2007, 32(3)15.
  • 9Zhang Y, Lin X M, Zhu G P, Zhang W J, Lin Q L Efficient rank based KNN query processing over uncertain data//Pro ceedings of the International Conference on Data Engineering. California, 2010:28-39.
  • 10Asano T, Cuibas L J, Hershberger J, Imai H. Visibility polygon search and euclidean shortest paths//Proceedings of the Annual Symposium Foundations of Computer Science. Portland, 1985, 155-164.

同被引文献95

  • 1刘刚,尹一涵,郑智源,李云涵,梁树乐,靳晨.基于三维点云的群体樱桃树冠层去噪和配准方法[J].农业机械学报,2022,53(S02):188-196. 被引量:4
  • 2张继超,刘宁,宋伟东,李建飞.一种特征选择的全极化雷达影像分类方法[J].测绘科学,2022,47(6):127-134. 被引量:3
  • 3孙圣力,林硕.一个高效的连续k近邻查询改进算法[J].计算机研究与发展,2013,50(S1):80-89. 被引量:2
  • 4FLIP K, MUTHUKRISHNAN S. Influence sets based on reverse nearest neighbor queries//Proc. of the 2000 ACM SIGMOD International Conference on Management of Data. Dallas: Association for Computing Machinery, 2000: 201-212.
  • 5YANG C, LINK I. An index structure for efficient reverse nearest neighbor queries//Proc. of the IEEE International Conference on Data Engineering. Heidelberg:Institute of Electrical and Electronics Engineers Computer Society, 2001: 485-492.
  • 6STANOI I, AGRAWAL D, ABBADI A. Reverse nearest neighbor queries for dynamic databases//ACM SIGMOD Workshop on Research Issues in Data Mining and Knowledge Discovery. Dallas: Association for Computing Machinery, 2000: 44-53.
  • 7TAO Y, PAPADIAS D, LIAN X. Reverse kNN search in arbitrary dimensionality//Proc. of the 30th Very Large Data Bases Conference.Toronto:VLDB Endowment, 2004: 744-755.
  • 8SINGH A, FERHATOSMANOGLU H, TOSUN A. High dimensional reverse nearest neighbor queries//Proc. of ACM CIKM International Conference on Information and Knowledge Management. New Orleans: Association for Computing Machinery, 2003: 91-98.
  • 9TAO Y, YIU M L, MAMOULIS N. Reverse nearest neighbor search in metric spaces[J]. IEEE Transactions on Knowledge and Data Engineering, 2006, 18(9): 1239-1252.
  • 10BENETIS R, JENSEN C S, KARCIAUSKAS G, et al. Nearest and reverse nearest neighbor queries for moving objects[J]. The VLDB Journal, 2006, 15(3): 229-249.

引证文献11

二级引证文献38

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部