欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
位置：立项数据库 > 立项详情页
中文摘要：
日益复杂和动态变化的海量数据处理是当前人们普遍关注的问题，其核心内容之一是研究如何利用已有的信息实现快速的知识更新。粒计算是信息处理中一种新的计算范式，已成功应用到知识发现等领域。本项目基于粒计算来研究动态更新知识的理论与高效算法。以邻域粗糙集、概率粗糙集、模糊粗糙集和多论域粗糙集为研究对象，研究内容分为两大部分1.研究粒度变化下基于这些粗糙集模型的高效知识更新机理，讨论这些粗糙集模型下不同粒层次之间转换的数学关系，分析不同粒度之间的变换规律，研究粒度变换中基于这些粗糙集模型的知识增量更新技术，以形成适合不同情况下大规模信息系统知识动态更新与维护的理论与方法，为建立基于粒计算的高效知识发现理论体系奠定基础；2.利用云计算中并行处理技术研究设计其中的动态更新知识的高效算法，提高应用粒计算和粗糙集解决不同情况下大规模信息系统学习问题时的知识发现效率，为复杂的海量数据处理提供理论、方法和算法。
英文摘要：
Knowledge discovery；Granular computing；Rough sets；Cloud computing；Big data
结论摘要：
如何利用已有信息实现快速知识更新是当前大数据处理中一个普遍关注问题。本项目以若干典型粗糙集扩展模型为研究对象，基于粒计算对动态知识更新的理论与高效算法进行研究，主要取得了以下成果(1)针对信息系统中对象、属性或属性值粒度变化的情形下，给出了不同粒层次之间转换的数学关系，刻画了不同粒度之间的变换规律，提出粒度变换中基于若干典型粗糙集模型的高效知识更新方法；(2)采用增量学习技术，设计了在不同粒度变化下基于若干典型粗糙集模型的高效动态更新知识算法，并进行了性能评测；(3)基于云计算技术，设计了动态更新知识算法的并行化处理方法，进一步提升了其效率。本项目共发表/录用论文107篇，其中国际期刊论文43篇，国际会议论文43篇，国内核心期刊论文19篇；论文已被SCI检索38篇、EI检索39篇；获国际会议优秀论文奖1次，国际会议、全国会议和IEEE成都分会优秀学生论文奖各1次；国际会议大会特邀报告5次、指南报告1次；主办国际研讨会和国内研讨会各1次，承办国际会议、国际研讨会和全国会议各1次；培养了多名研究生，1名博士论文获得ACM成都优秀博士论文奖。这些成果为建立基于粒计算的高效知识发现理论体系和处理复杂且动态的大数据提供了学术思想与技术路线。
成果综合统计
期刊论文
会议论文
专利
获奖
著作
期刊论文
Fast Algorithms for Computing Rough Approximations in Set-valued Decision Systems While Updating Cri
A rough-set-based incremental approach for updating approximations under dynamic maintenance environ
会议论文
The incremental updating method for core computing based on information entropy in set-valued ordere
The incremental updating method for core computing based on information entropy in set-valued ordere
A matrix-based incremental attribute reduction approach under knowledge granularity on the variation
A matrix-based incremental attribute reduction approach under knowledge granularity on the variation
An Incremenal Approach for Updating Approximation of Rough Fuzzy Sets under the Variation of the Obj
An Incremental Approach for Updating Approximations of Neighborhood Rough Fuzzy Sets under the Varia
An Incremenal Approach for Updating Approximation of Rough Fuzzy Sets under the Variation of the Obj
An Incremental Approach for Updating Approximations of Neighborhood Rough Fuzzy Sets under the Varia
An approach for incremental maintenance of approximations in set-valued ordered decision systems whi
An approach for incremental maintenance of approximations in set-valued ordered decision systems whi
An incremental approach for updating approximations of rough fuzzy set under the variation of attrib
An Incremenal Approach for Updating Approximation of Rough Fuzzy Sets under the Variation of the Obj
An Incremental Approach for Updating Approximations of Neighborhood Rough Fuzzy Sets under the Varia
An Incremenal Approach for Updating Approximation of Rough Fuzzy Sets under the Variation of the Obj
An Incremental Approach for Updating Approximations of Neighborhood Rough Fuzzy Sets under the Varia
An Approach for Attribute Reduction in Set-valued Ordered Information Systems based on Information E
An Incremental Method for Core Computing based on Information Entropy in Set-valued Ordered Informat
An approach for incremental maintenance of approximations in set-valued ordered decision systems whi
An approach for incremental maintenance of approximations in set-valued ordered decision systems whi
A parallel matrix-based approach for computing approximations in dominance-based rough sets approach
A parallel matrix-based approach for computing approximations in dominance-based rough sets approach
A matrix-based incremental attribute reduction approach under knowledge granularity on the variation
A matrix-based incremental attribute reduction approach under knowledge granularity on the variation
A parallel matrix-based approach for computing approximations in dominance-based rough sets approach
A parallel matrix-based approach for computing approximations in dominance-based rough sets approach
The incremental updating method for core computing based on information entropy in set-valued ordere
The incremental updating method for core computing based on information entropy in set-valued ordere
获奖
相关项目
李天瑞的项目