APPROACH FOR FUZZY MULTI-ATTRIBUTE DECISION-MAKING WITH FUZZY COMPLEMENTARY PREFERENCE RELATION ON ALTERNATIVES

In presented fuzzy multi-attribute decision-making （FMADM） problems, the information about attribute weights is interval numbers and the decision maker （DM） has fuzzy complementary preference relation on alternatives. Firstly, the decision-making information based on the subjective preference information in the form of the fuzzy complementary judgment matrix is uniform by using a translation function. Then an objective programming model is established. Attribute weights are obtained by solving the model, thus the fuzzy overall values of alternatives are derived by using the additive weighting method. Secondly, the ranking approach of alternatives is proposed based on the degree of similarity between the fuzzy positive ideal solution of alternatives （FPISA） and the fuzzy overall values. The method can sufficiently utilize the objective information of alternatives and meet the subjective requirements of the DM as much as possible. It is easy to be operated and implemented on a computer. Finally, the proposed method is applied to the project evaluation in the venture investment.

模糊复合抽检贮存数据的Bayes融合评估方法

目的 针对包含模糊样本的复合抽检型产品开展贮存寿命评估。方法 针对批次产品中的出厂失效数据和贮存失效数据,开展批次数据的相容性检验。通过出厂失效样本数随机化处理,量化贮存过程中模糊样本的不确定性。将出厂试验数据作为先验信息,贮存过程中的出厂试验数据作为观测信息,基于Bayes融合方法,更新出厂失效概率。通过更新后的出厂失效概率,确定模糊样本的组成,筛选出贮存失效概率样本。针对筛选后的样本,基于样本量加权最小二乘方法,开展贮存寿命评估。结果 将所提方法应用于某弹箭产品案例,有效评估了批次出厂失效概率及其估计方差,并给出了可靠寿命评估结果。结论 所提Bayes评估方法融合了出厂抽检数据和贮存抽检数据,有效解决了含模糊样本的失效概率估计问题,提高了估计的精确性,基于样本量权重的加权最小二乘法,考虑了样本的可信程度,提升了方法的科学性。

Multi-attribute decision making method for air target threat evaluation based on intuitionistic fuzzy sets

The function of the air target threat evaluation （TE） is the foundation for weapons allocation and senor resources management within the surface air defense. The multi-attribute evaluation methodology is utilized to address the issue of the TE in which the tactic features of the detected target are treated as evaluation attributes. Meanwhile, the intuitionistic fuzzy set （IFS） is employed to deal with information uncertainty in the TE process. Furthermore, on the basis of the entropy weight and inclusion-comparison probability, a hybrid TE method is developed. In order to accommodate the demands of naturalistic decision making, the proposed method allows air defense commanders to express their intuitive opinions besides incorporating into the threat features of the detected target. An illustrative example is provided to indicate the feasibility and advantage of the proposed method.

基于模糊Bayes-Gauss判别法的遥感影像的聚类

针对Fisher线性判别法和传统的Bayes判别方法在遥感影像聚类问题研究中存在的不足,提出一种以隶属度代替先验概率的模糊Bayes-Gauss聚类算法,并将此算法应用于真彩色(RGB)图像中的草地、道路、裸土地和建筑物的聚类.实验结果表明,本算法在聚类中与Fisher线性判别法和传统Bayes判别法相比,具有精确度较高、误识率和拒识率较低、适用性较强的特点.

基于改进朴素贝叶斯算法的文本分类研究

朴素贝叶斯算法在给定输出类别的情况下,需假设属性之间相互独立,然而现实中这个假设一般不成立,导致在属性个数较多或者属性之间相关性较大时,分类效果不是很理想。为了解决这个问题,本文采用优化的模糊C均值聚类及权重计算方法改进朴素贝叶斯算法。首先,基于JS散度构造类别个数的自适应函数优化模糊聚类算法,利用优化后的算法将文本分类整理。然后,采用词频因子优化的TF-IDF算法计算分类后各样本的特征权重,结合样本权重与贝叶斯公式,进行分类计算。最后,为了体现改进的朴素贝叶斯算法的有效性和优越性,将其与原始朴素贝叶斯算法以及其他改进算法进行对比实验。实验结果表明,改进后的算法有效地降低了朴素贝叶斯模型对特征项独立性的要求,提高了分类决策的准确率,且在分类性能和效率上具有一定的优越性。

基于Choquet模糊积分的水电机组振动故障诊断

为提高水电机组故障诊断的准确性,提出了基于Choquet模糊积分融合的多分类器组合故障诊断方法,对朴素贝叶斯分类器进行了基于属性相似度的加权改进,得到基于属性相似度的加权朴素贝叶斯分类器(Attribute Similarity Weighted Naive Bayes Classifier,简称SWNBC),并应用基于Mahalanobis距离的分类器(Mahalanobis Distance Classifier,简称MDC)与BP神经网络(BP neural network)组合成为SWNBC+MDC+BP的多分类器组合模型,以小波包提取的相关频带能量作为输入特征向量,应用组合模型对水电机组故障进行诊断,采用模糊积分法来决定最终的故障类型。实验结果表明该模型相对于单一的分类器,能有效提高识别故障的精度。

多属性加权模糊贝叶斯的复杂网络故障自修复技术

为了提高对复杂网络进行故障诊断时的准确率,以及实现故障节点的有效自修复,提出一种多属性加权模糊贝叶斯的复杂网络故障自修复机制。建立贝叶斯网络结构模型,针对故障网络和故障节点进行条件概率估计,实现故障类别诊断。在该模型的基础上引入了多属性值和模糊集合理论进行扩展,提出了一种多属性加权模糊贝叶斯,提升模型对节点进行故障诊断时的灵敏度和准确度。对网络和节点进行故障诊断后,采用网络故障自修复机制,在查找出节点故障类型,采取有效的能量分配方法来修复节点。实验仿真及对比表明,该方法相比基于神经网络的故障诊断方法、基于半监督聚类的故障诊断方法以及基于隐马尔可夫模型的故障诊断方法具有更好的故障诊断和修复性能。