基于改进云粒子群优化的模糊神经网络在甲醇合成转化率软测量中的应用

针对基本PSO算法早熟、搜索精度不高与易陷入局部最优的缺点,结合云滴的随机性、稳定倾向性,提出了一种改进粒子群优化算法(ICPSO)。将改进算法用于模糊神经网络的参数优化,并应用于甲醇单程转化率建模中。仿真实验结果表明：该模型具有较高的精度和较好的泛化能力,能够实现甲醇转化率的实时监测。     

对脾虚大鼠模型建立模糊数学评价体系的研究

应用模糊数学模式识别方法对脾虚证动物模型进行综合评估。通过计算出每个评价对象的造模程度隶属度值,对评价结果进行初步分析,进而评判模型是否达到要求。     

不同军兵种官兵对初级军官胜任特征的评价

目的: 本研究在回顾优秀领导者心理特点研究文献基础上,通过工作分析,探讨不同军兵种官兵对初级军官胜任特征评价的差异和特点.方法: 各军兵种官兵6263名,完成<优秀初级军官心理素质调查表>9004份,有效率86.02%;采用多级重要度语义量词模糊集评估法对40项指标逐条评价.结果: ①根据模糊集语意量词MFS分值将37项指标分为3个等级: "最重要"10项,"很重要"13项, "较重要"14项;②陆海空3个军种在最重要的10项胜任特征指标中,有7项的评价均存在显著性差异(P<0.05);③ 7个兵种在10项最重要指标评价上总趋势一致性比较好,二炮和航空兵被试分别在4项指标上与其他兵种的评价存在显著性差异(P<0.05).结论: 不同军兵种官兵在初级军官胜任特征的评价上有各自的特点和结构.     

基于模糊隶属度与支持向量机心律失常分类模型

目的:基于心电信号波形特点,运用模糊隶属度与支持向量机技术,探索实现心律失常自动分类的方法.方法:对MIT-BIH心律失常标准数据库的心电信号预处理,识别并定位QRS波;以QRS波为核心,利用心电信号波形相似性进行心电信号聚类;心电信号提取特征参数并模糊化,构建心律失常特征参数集;利用支持向量机技术建立心律失常分类器.结果:通过MIT-BIH心律失常标准数据库检验分类效果,总体准确率达到97.2%.结论:对MIT-BIH心律失常标准数据库的心电信号具有较高的分类准确率和较好的实用性.     

一种适用于多模态过程监控的集成统计指标

具有多模态特性的工业过程的数据分布呈现出与单模态过程不同的特性。在构造监控指标时,不仅要能够概括每个模态内部的数据统计特征,还要充分考虑到不同模态之间的信息。传统的T2和SPE统计量在多模态过程中可能无法实现这一目标。提出了一种融合多模态统计信息的全局监控统计量,在贝叶斯推论的框架下,通过对每个模态的局部马氏距离赋予相应权重来实现对多模态数据的描述。通过多模态的连续反应搅拌釜(CSTH)仿真实验,验证了全局监控指标的有效性和灵敏性。     

新疆4所综合性医院医疗服务质量满意度的分析与评价

目的：分析与评价新疆4所综合性医院医疗服务质量满意度。方法对4所医院28项指标进行调查,参考美国顾客满意度指数模型（ACSI）,构建医疗服务质量满意度评价模型,用层次分析法和模糊综合评价法,计算医疗服务质量满意度分值。结果4所综合性医院患者的总体满意度分别为95．08、86．02、77．06、82．64。在一级指标中,医疗技术水平权重分值最高,分别为97．56、90．50、78．94、86．62;而医疗费用权重分值最低,分别为89．18、76．48、67．10、78．62。结论患者对4所医院的医疗服务质量总体上是满意的,特别是对医疗技术水平给予了高度肯定,但一级指标中的医疗费用指标分值最低,我区医院在降低医疗费用和节约时间成本方面还有许多工作要做。     

基于贝叶斯网络高斯混合模型医学图像检索的研究

结合医学影像诊断的实际情况,提出一种基于贝叶斯网络高斯混合模型的医学图像检索方法。算法首先引入条件高斯模型,将连续变量模糊离散化,再利用贝叶斯网络对医学图像进行语义建模,并最终完成基于内容的图像检索。实验采用医学图像库中的CT和MRI影像样本进行仿真,仿真结果显示,这种方法是有效的,可以满足医生的一般需要。     

Suggestions for a Web based universal exchange and inference language for medicine

Mining biomedical and pharmaceutical data generates huge numbers of interacting probabilistic statements for inference, which can be supported by mining Web text sources. This latter can also be probabilistic, in a sense described in this report. However, the diversity of tools for probabilistic inference is troublesome, suggesting a need for a unifying best practice. Physicists often claim that quantum mechanics is the universal best practice for probabilistic reasoning. We discuss how the Dirac notation and algebra suggest the form and algebraic and semantic meaning of XML-like Web tags for a clinical and biomedical universal exchange language formulated to make sense directly to the eye of the physician and biomedical researcher.     

Social cognition in individuals with agenesis of the corpus callosum

Past research has revealed that individuals with agenesis of the corpus callosum (ACC) have deficits in interhemispheric transfer, complex novel problem-solving, and the comprehension of paralinguistic aspects of language. Case studies and family reports also suggest problems in social cognition. The performance of 11 individuals with complete ACC and with normal intelligence was compared to that of 13 IQ- and age-matched controls on three measures of social cognition. Individuals with ACC were indistinguishable from controls on the Happé Theory of Mind Stories and the Adult Faux Pas Test, but performed significantly worse on various portions of the Thames Awareness of Social Inference Test (TASIT) involving interpretations of videotaped social vignettes. Further analysis of the TASIT indicated that individuals with ACC showed deficiency in the recognition of emotion, weakness in understanding paradoxical sarcasm, and particular difficulty interpreting textual versus visual social cues. These results suggest that the tendency for deficient social cognition in individuals with ACC stems from a combination of difficulty integrating information from multiple sources, using paralinguistic cues for emotion, and understanding nonliteral speech. Together, these deficits would contribute to a less robust theory of mind.     

Nonparametric Procedures for Simultaneous Identification of the Minimum Effective Dose in Each of Several Groups

Abstract

This paper considers the extension of the dose finding problem in a one-way layout setting to the case of several groups, in which the main goal is to identify the minimum effective dose (MED) of each group simultaneously. We propose two nonparametric procedures using the respective pairwise- and Helmert-type two-sample Mann–Whitney statistics, which are applied in a step-down testing scheme for identifying the MED simultaneously. The computation for the associated p-value of the identified MED vector is discussed. One numerical example is given to illustrate the proposed procedures.