Model-based evaluation of clustering validation measures

A cluster operator takes a set of data points and partitions the points into clusters (subsets). As with any scientific model, the scientific content of a cluster operator lies in its ability to predict results. This ability is measured by its error rate relative to cluster formation. To estimate the error of a cluster operator, a sample of point sets is generated, the algorithm is applied to each point set and the clusters evaluated relative to the known partition according to the distributions, and then the errors are averaged over the point sets composing the sample. Many validity measures have been proposed for evaluating clustering results based on a single realization of the random-point-set process. In this paper we consider a number of proposed validity measures and we examine how well they correlate with error rates across a number of clustering algorithms and random-point-set models. Validity measures fall broadly into three classes: internal validation is based on calculating properties of the resulting clusters; relative validation is based on comparisons of partitions generated by the same algorithm with different parameters or different subsets of the data; and external validation compares the partition generated by the clustering algorithm and a given partition of the data. To quantify the degree of similarity between the validation indices and the clustering errors, we use Kendall's rank correlation between their values. Our results indicate that, overall, the performance of validity indices is highly variable. For complex models or when a clustering algorithm yields complex clusters, both the internal and relative indices fail to predict the error of the algorithm. Some external indices appear to perform well, whereas others do not. We conclude that one should not put much faith in a validity score unless there is evidence, either in terms of sufficient data for model estimation or prior model knowledge, that a validity measure is well-correlated to the error rate of the clustering algorithm.     

降低铁矿石烧结烟气中二氧化硫的实验研究

在实验室条件下，通过在原料混合时添加脱硫剂的方法来脱除烧结烟气中二氧化硫有害气体。分析了烧结烟气中有害气体的危害；介绍了添加脱硫剂的方法；并考察了添加脱硫剂后对烧结技术经济指标的影响。     

河南省宿鸭湖水库水污染现状及防治对策

该文依据宿鸭湖水库水质的实际监测资料,采用指数法对水库的水环境进行地表水环境质量评价和水库富营养化评价,采用秩相关系数法对近5年水库水质变化趋势进行分析和评价,提出污染防治对策.结果表明,宿鸭湖水库水质基本满足地表水水域环境功能,水库富营养化程度为轻度富营养化,近5年来水质变化趋势稳定;通过提出针对性的对策和建议,可以进一步降低污染物水平,保障水库综合效益的发挥.     

脂肪烃类化合物气相色谱保留指数的预测

为了能更好地揭示脂肪烃的气相色谱保留指数与结构的关系,通过对412个脂肪烃类化合物在不同固定相、不同柱温下的1742个样本集的气相色谱保留指数值(RI)与其部分参数相关性的研究,发现RI与拓扑指数(mQ)、分子杂化状态指数(MHSI)、碳原子数(N)、固定液极性(CP)及柱温(T)的关系可表示为:RI=46．6537 15．83520Q 6．02101Q 49．9215MHSI- 62．4378N 2．2836CP 0．6159T(R=0．9954)此式不仅在一定程度上阐明了脂肪烃类化合物RI与其分子结构信息、固定液极性及柱温之间的关系,同时也提供了一种预测脂肪烃类化合物在各种色谱分离条件(不同固定相、不同温度)下RI的新方法。继以留一法(leave-one-out,LOO)进行交互检验,相关系数RLOO=0．9953,说明所建模型具有良好的稳定性和预测能力,较好地揭示了脂肪烃类化合物在不同固定相、不同柱温下气相色谱保留指数的变化规律。     

基于Web的产品装配评价建模研究

从产品装配结构和装配过程协同设计的角度出发,提出产品装配效率和产品装配复杂度等评价指标,建立产品装配性综合评定体系,采用知识库和网络技术实现网络环境下的产品装配结构分析和再设计。在实现产品装配的相关设计知识及网络环境共享的前提下,支持设计者在网络环境下针对装配结构问题进行协同分析改进,能够有效克服面向装配的产品结构设计和装配过程设计的孤岛化问题,实现产品设计和过程设计的协调与并行。     

A Coordinated Framework of DG Allocation and Operating Strategy in Distribution System for Configuration Management under Varying Loading Patterns

Abstract

The distributed generation (DG) planning with the varying pattern of the practical load is difficult as it calls for the frequent changes in DG size and system configuration, which is neither feasible nor permissible. Rather such a DG size and a configuration, which can be utilized over a wider load pattern, are more acceptable. This work presents a coordinated approach for DG planning and system reconfiguration. While to operate a particular DG size and the system configuration over a wide range of loading pattern, the configurations are ranked under different probabilistic loading patterns. Based upon the ranking of the new configuration, the energy performance of the coordinated planning is evaluated. Further, the observations from coordinated planning are imposed on coordinated operation using harmony search algorithm (HSA). The proposed approach is tested for single as well as multi-objectives on a 33-node system. A significant improvement in the computational efforts and energy performance of the resulting configuration have been observed where losses have reduced to 81.11 and 53.77?kW with single DG and multi-DG allocation respectively.     

Differentiable structure of realizable Markov parameters

The geometry of the finite sequences of p×m$p\times m$ matrices that are realizable by systems of minimal order d$d$ is investigated. They can be stratified according to their partial row and column Kronecker indices. The case when the sum of the number of non-zero row and column indices is smaller than the number of elements in the sequence of parameters is considered. It is shown that, in this case, the whole set of Markov parameters and each stratum can be endowed with structures of differentiable manifolds, and their dimensions are computed.     

辽宁省种植冬麦的农业气候指标研究

本文通过对可能影响冬麦生育过程的若干因子的分析，筛选出４个主要气候因子，作为辽宁省种植冬麦的农业气候指标。这４个农业气候指标是：越冬前活动积温为４２０～５４０℃，越冬前降水１２０～１７０ｍｍ，抽穗到成熟期降水 １１０～ １５０ｍｍ，越冬期可耐一 ８００ ℃负积温及一２４～一２６℃的极端最低气温。由此，以农业气候相似论为依据，可以实现以沈阳为中心的辽宁省部分地区冬麦北移种植的构想。     

绿色印染助剂的开发与原料选用

指出了印染助剂中被禁用的非环保助剂的致癌、天才畸、生物降解性差等危害性，同时详细介绍了无毒性、生物降解性好的替代产品及原材料的选用，以予科技人员进一步开发符合环保要求和生态指标的绿色印染助剂。     

Process capability indices—an overview of theory and practice

A range of process capability indices is widely used to measure process performance. The simplicity of the formulae for these capability indices is both a strength and a weakness. The underlying assumptions behind capability indices are frequently overlooked. Capability studies usually result in single point estimates which may result in misleading assessments of process performance. Point estimates ignore sampling error, and safer estimates can be obtained by constructing confidence intervals. The construction of confidence intervals is considered in some detail. Testing or measurement variability give rise to additional uncertainty in process capability assessments. Inaccurate assessments of process performance can result if the basic assumptions and sources of uncertainty are overlooked.