基于模糊-粗糙集的移动对象k近邻预测  

Fuzzy-Rough Sets for Prediction of Moving Objects' K-Nearest Neighbor

作　　者：袁妍[1] 洪晓光[1] 

机构地区：[1]山东大学计算机科学与技术学院,济南250101

出　　处：《计算机科学》2008年第2期140-143,共4页Computer Science

基　　金：教育部重点科技计划项目(03102);国家自然科学基金(60673130);省重大科技专项项目(2004GG4201022);山东省中青年科学家奖励基金(2005BS01002)

摘　　要：已往移动对象k近邻预测的研究中,有各种不确定性的分析以及对象本身预测位置不确定性的处理,而预测位置模糊不确定性导致其k近邻查询边界的粗糙不确定性的相关处理仍是空白。本文应用模糊-粗糙集的理论,先分析了已有方法得出的预测位置的模糊性,再用传统方法求得基于预测位置的扩展k+m近邻集,最后借助模糊-粗糙隶属函数来最终确定所求k近邻集合中的各个点。实验数据表明,本方法明显提高了k近邻集合相对移动对象实际位置的精确度。There are many analyses on the diversified uncertainty and many disposals on the uncertainty of objects＇ predicted position in the previous study of the prediction of moving objects＇ k-nearest neighbor. But there have not been any measure to deal with the rough-uncertainty of moving objects＇ k-nearest neighbor set, which is caused by the fuzzyuncertainty of moving objects＇ predicted position. In this paper, the theory of fuzzy-rough sets is employed to analyze the fuzzy position of the moving objects and its extended k ＋ m nearest neighbor set. Also, the fuzzy-rough membership function is employed to obtain thefinal k-nearest neighbor set. A comparison between the processed result and the initial result is made by experiments. Compared to the actual position of the moving objects, the analysis based on the theory of fuzzy-rough sets can promote the precision of its k-nearest neighbor set distinctly.

关 键 词：移动对象 K近邻查询 模糊集 粗糙集 

分 类 号：TP75[自动化与计算机技术—检测技术与自动化装置] TP311.52[自动化与计算机技术—控制科学与工程]