-
摘要: 对于超熵较大情况下的正态云模型,说明了云模型雾化过程.通过统计分析云滴离散的整体趋势,说明超熵增大过程中,云滴整体趋于离散.通过分析各论域区间内云滴离散趋势,说明靠近概念核心的云滴的离散速度相对缓慢.归纳云模型雾化性质:在超熵取值持续增大的过程中(He>En/3),正态云表示的概念的论域范围持续增大,呈雾化状态,但靠近概念核心的论域区间内的云滴不失数量优势.雾化性质适用于建模偏离正态分布、缺乏共识的定量数据,期望表示概念语义值核心,熵描述概念语义的离散程度,超熵表示各种语义的共识程度,扩展了云模型知识表示的应用范围.Abstract: The cloud model atomization process was related to a larger hyper enctropy. Through statistical analysis of the overall trend of the cloud drops, the cloud drops dispersed over the course of hyper entropy increase. By analyzing the dispersion trend of cloud drops in each semantic ranges, it is indicated that the drops represent the core concept dispersed in a low speed. The atomization feature of the cloud model was summarized. The semantic range of the concept represented by the cloud model extended while the hyper entropy increased step by step. The cloud drops spread but the drops nearby the core semantic keep a high density. The atomization feature of the cloud model was used to model the data deviates from the normal distribution. A cloud with a large hyper entropy value represented the concept lack of consensus. For each parameter, the expectation stands for the core semantic value, the entropy represents the semantic range and the hyper entropy shows the degree of consensus of the different semantics ranges. The cloud model knowledge representation application range was extended.
-
Key words:
- knowledge representation /
- uncertainty /
- statistics /
- cloud model
-
[1] 李德毅,刘常昱,杜鹢,等.不确定性人工智能[J].软件学报,2004,15(11):1-13 Li Deyi,Liu Changyu,Du Yi,et al.Artificial intelligence with uncertainty[J].Journal of Software,2004,15(11):1-13 (in Chinese) [2] Wang Shuliang,Li Deren,Shi Wenzhong,et al.Cloud model-based spatial data mining[J].Geographical Information Science,2003,9(2):67-78 [3] 吕辉军,王晔,李德毅.逆向云在定性评价中的应用[J].计算机学报,2003,26(8):1009-1014 Lü Huijun,Wang Ye,Li Deyi.The application of backward cloud in qualitative evaluation[J].Chinese Journal of Computers,2003,26(8):1009-1014 (in Chinese) [4] 李德毅,杜鹢.不确定性人工智能[M].北京:国防工业出版社,2004 Li Deyi,Du Yi.Artificial intelligence with uncertainty[M].Beijing:National Defence Industry Press,2004(in Chinese) [5] 张光卫,李德毅,刘禹.基于正态云模型的进化算法[J].计算机学报,2008,7(7):1082-1091 Zhang Guangwei,Li Deyi,Liu Yu.An evolutionary algorithm based on cloud model[J].Chinese Journal of Computers,2008,7(7):1082-1091(in Chinese) [6] 张光卫,康建初,李鹤松,等.基于云模型的全局最优化算法[J].北京航空航天大学学报,2007,33(4):486-490 Zhang Guangwei,Kang Jianchu,Li Hesong,et al.Cloud model based algorithm for global optimization of functions[J].Journal of Beijing University of Aeronautics and Astronautics,2007,33(4):486-490(in Chinese) [7] Liu Yu,Chen Guisheng.Cloud model based classifier // Luo Qi,Tan Honghua.2009 Internal Conference on Test and Measurement.Hong Kong:IEEE,2009:427-430 [8] Blake C L,Merz C J.UCI repository of machine learning databases .Irvine,CA:University of California,1998.http://www.ics.uci.edu/~mlearn/MLRepository.html
点击查看大图
计量
- 文章访问数: 3653
- HTML全文浏览量: 273
- PDF下载量: 1877
- 被引次数: 0