模糊广义决策信息系统的证据特征与信任约简

探究模糊广义决策信息系统的证据特征和信任约简.首先,给出模糊广义决策信息系统中的模糊上、下近似算子及其相关性质.然后,基于证据理论探讨模糊广义决策信息系统的数值特征,并在模糊广义决策信息系统中,利用证据理论中的模糊信任和模糊似然函数对模糊近似集进行刻画.最后,根据模糊信任函数定义的属性重要度,提出模糊广义决策信息系统信任约简的算法,并给出实例验证其有效性.     

采用局部粗糙集模型的决策规则提取

研究基于局部粗糙集模型下的决策规则提取.对经典粗糙集的决策规则提取进行改进,给出局部粗糙集模型下的决策规则公式,并研究相关性质.结合局部粗糙集模型给出的规则提取公式,引入参数值α,α∈(0,1］,使规则提取公式的泛化能力更强,适用性更广.通过3个实例对局部粗糙集模型决策规则提取的运用进行说明.     

LNG气瓶传热计算方法及实验验证

以液氮为工质,选取150 L、330 L和450 L等3种规格LNG气瓶进行传热计算.采用饱和均质模型,根据在饱和状态下的热力学关系,拟合出液氮物性参数与温度的关系并编制程序,计算得到了气瓶内介质压力随时间的变化规律.通过与有关文献的液氮升压实验数据对比,验证了该计算模型的有效性.     

基于马尔科夫决策过程的多目标跟踪算法

目前,多目标跟踪算法仍面临诸多挑战,例如遮挡、快速运动等所造成的影响难以完全规避.为了解决上述问题,提出一种基于马尔科夫决策过程的多目标跟踪算法.该算法将每个目标建模成一个马尔科夫决策过程,通过最大化奖励函数来驱动状态间的转移,并将强化学习训练用于数据关联相似度函数,有效地解决了目标遮挡问题.同时,为了解决物体快速运动...     

Generalization of the linguistic aggregation operator and its application in decision making

A generalization of the linguistic aggregation functions (or operators) is presented by using generalized and quasiarithmetic means.Firstly,the linguistic weighted generalized mean (LWGM) and the linguistic generalized ordered weighted averaging (LGOWA) operator are introduced.These aggregation functions use linguistic information and generalized means in the weighted average (WA) and in the ordered weighted averaging (OWA) function.They are very useful for uncertain situations where the available information cannot be assessed with numerical values but it is possible to use linguistic assessments.These aggregation operators generalize a wide range of aggregation operators that use linguistic information such as the linguistic generalized mean (LGM),the linguistic OWA (LOWA) operator and the linguistic ordered weighted quadratic averaging (LOWQA) operator.We also introduce a further generalization by using quasi-arithmetic means instead of generalized means obtaining the quasi-LWA and the quasi-LOWA operator.Finally,we develop an application of the new approach where we analyze a decision making problem regarding the selection of strategies.     

Ranking approach of cross-efficiency based on improved TOPSIS technique

The cross-efficiency evaluation method is reviewed which is developed as a date envelopment analysis (DEA) extensive tool.The cross-efficiency evaluation method is utilized to identify the decision making unit (DMU) with the best practice and to rank the DMUs by their respective cross-efficiency scores.The main drawbacks of the cross-efficiency evaluation method when the ultimate average cross-efficiency scores are used to evaluate and rank the DMUs are also pointed out.With the research gap,an improved technique for order preference by similarity to ideal solution (TOPSIS) is introduced to rank the cross-efficiency by eliminating the average assumption.Finally,an empirical example is illustrated to examine the validity of the proposed method.     

Decision tree support vector machine based on genetic algorithm for multi-class classification

To solve the multi-class fault diagnosis tasks, decision tree support vector machine (DTSVM), which combines SVM and decision tree using the concept of dichotomy, is proposed. Since the classification performance of DTSVM highly depends on its structure, to cluster the multi-classes with maximum distance between the clustering centers of the two sub-classes, genetic algorithm is introduced into the formation of decision tree, so that the most separable classes would be separated at each node of decisions tree. Numerical simulations conducted on three datasets compared with "one-against-all" and "one-against-one" demonstrate the proposed method has better performance and higher generalization ability than the two conventional methods.     

数据的动态挖掘与P-增广矩阵关系

P-增广矩阵是通过利用P-集合的结构与动态特征,改进普通增广矩阵A^*提出的。P-增广矩阵是由内P-增广矩阵A^(-overF)与外P-增广矩阵A^F构成的矩阵对,或者(A^(-overF),A^F)是P-增广矩阵。在一定条件下,P-增广矩阵(A^(-overF),A^F)被还原成普通增广矩阵A^*。利用P-增广矩阵的结构与动态特征,给出数据的动态挖掘研究及其与P-增广矩阵的关系。提出数据的动态挖掘的内P-增广矩阵判定定理,外P-增广矩阵判定定理与P-增广矩阵判定定理,给出数据的动态挖掘的P-增广矩阵准则,利用这些理论结果,给出一个简单应用。     

基于关联规则分析的产品销售推荐的应用

阐述了关联规则算法的基本原理,并利用事务数据库中的销售数据和SQL Server 2008 DataMining Add-Ins for Microsoft office 2007工具挖掘顾客购买的商品之间各种有趣联系,帮助商家制定营销策略,最终向每个顾客提供一组正确的推荐信息,从而改善客户的购物体验,增加总的销售额。     

基于G4ICCS系统的数据挖掘并行算法

针对传统决策树SPRINT（Scalable Parallelizable Induction of Decision Trees）算法不能处理海量地学数据挖掘的问题, 设计实现了基于G⁴ICCS(Geology Geography Geochemistry Geophysics Information Cloud Computing System）的决策树并行分类算法PSPRINT。该算法使用哈希表存储连续属性分割点两侧的数据记录, 为并行节点的分割提供依据, 在MapReduce架构下解决了海量地学数据挖掘问题。实验结果表明, 在模拟的云计算环境下, 决策树并行算法可以处理海量地学数据分类问题, 并获得较好的稳定性和较高的处理速度。