基于粗糙集和模糊C均值聚类的空战效能评估  

Aerial Warfare Efficiency Evaluation for Fighter-plane Based on Rough Set and Fuzzy C-Means Clustering Algorithm

作　　者：龚胜科[1,2] 徐浩军[1] 贾联慧 晏波 

机构地区：[1]空军工程大学工程学院 [2]空军95737部队

出　　处：《数学的实践与认识》2013年第19期118-122,共5页Mathematics in Practice and Theory

基　　金：国家自然科学基金(70671106)

摘　　要：针对评估指标的重要性不一,且存在冗余问题,基于粗集可辨识矩阵,提出了一种计算指标属性重要度和约简的有效、简便算法,对样本信息进行约简,并计算约简后各指标的权重.其中,针对连续属性值离散化过程可能造成信息损失问题,采用了模糊C均值聚类算法离散化连续属性值.最后,建立了基于粗糙集和模糊C均值聚类的空战效能评估模型,并通过实例验证了该模型的可行性和有效性.In view of the different significance and redundancies of index system, a valid and simple algorithm of determining the significance of each index and attribute relative reduction is proposed, based on the discernibility matrix of rough set method, and this algorithm is used to reduce the sample information and ascertain weights. Aiming at the loss of information in the discretization of continuous attributes, fuzzy c-means clustering（FCM） algorithm is introduced to discretize the continuous attributes. Finally, the evaluation model of aerial warfare efficiency is established based on the Rough Set and FCM algorithm. The feasibility and validity of the model is verified with a case study.

关 键 词：可辨识矩阵 约简 模糊C均值聚类 空战效能评估 

分 类 号：E91[军事] TP18[自动化与计算机技术—控制理论与控制工程]