Principal Component-Discrimination Model and Its Application

Having researched for many years, seismologists in China presented about 80 earthquake prediction factors which reflected omen information of earthquake. How to concentrate the information that the 80 earthquake prediction factors have and how to choose the main factors to predict earthquakes precisely have become one of the topics in seismology. The model of principal component-discrimination consists of principal component analysis, correlation analysis, weighted method of principal factor coefficients and Mahalanobis distance discrimination analysis. This model combines the method of maximization earthquake prediction factor information with the weighted method of principal factor coefficients and correlation analysis to choose earthquake prediction variables, applying Mahalanobis distance discrimination to establishing earthquake prediction discrimination model. This model was applied to analyzing the earthquake data of Northern China area and obtained good prediction results.

Water Quality Evaluation of Chapurson Valley in Hunza Nagar, Gilgit Baltistan, Pakistan, Based on Statistical Analysis and Water Quality Index

Water borne ailments are of serious public health concern in Gilgit Baltistan’s (GB) region of Pakistan. The pollution load on the glacio-fluvial streams and surface water resources of the Chapurson Valley in the Hunza Nagar area of the GB is increasing as a result of anthropogenic activities and tourism. The present study focuses on the public health quality of drinking water of Chapurson valley. The study addressed the fundamental drinking water quality criteria in order to understand the state of the public health in the valley. To ascertain the current status of physico-chemical, metals, and bacteriological parameters, 25 water samples were collected through deterministic sampling strategy and examined accordingly. The physico-chemical parameters of the water samples collected from the valley were found to meet the World Health Organization (WHO) guidelines of drinking water. The water samples showed a pattern of mean metal concentrations in order of Arsenic (As) > Lead (Pb) > Iron (Fe) > Zinc (Zn) > Copper (Cu) > Magnesium (Mg) > Calcium (Ca). As, Cu, Zn, Ca and Mg concentration were under the WHO guidelines range. However, results showed that Pb and Fe are present at much higher concentrations than recommended WHO guidelines. Similarly, the results of the bacteriological analysis indicate that the water samples are heavily contaminated with the organisms of public health importance (including total coliforms (TCC), total faecal coliforms (TFC) and total fecal streptococci (TFS) are more than 3 MPN/100mL). Three principal components, accounting for 48.44% of the total variance, were revealed using principal component analysis (PCA). Bacteriological parameters were shown to be the main determinants of the water quality as depicted by the PCA analysis. The dendrogram of Cluster analysis using the Ward’s method validated the same traits of the sampling locations that were found to be contaminated during geospatial analysis using the Inverse Distance Weight (IDW) method. Based on these findings, it is most likely that those anthropogenic activities and essentially the tourism results in pollution load from upstream channels. Metals may be released into surface and groundwater from a few underlying sources as a result of weathering and erosion. This study suggests that the valley water resources are more susceptible to bacteriological contamination and as such no water treatment facilities or protective measure have been taken to encounter the pollution load. People are drinking the contaminated water without questioning about the quality. It is recommended that the water resources of the valley should be monitored using standard protocol so as to protect not only the public health but to safe guard sustainable tourism in the valley.

Estimation of crop water requirement based on principal component analysis and geographically weighted regression

In this study the principal component analysis (PCA) and geographically weighted regression (GWR) are combined to estimate the spatial distribution of water requirement of the winter wheat in North China while the effect of the macroand micro-topographic as well as the meteorological factors on the crop water requirement is taking into account. The spatial distribution characteristic of the water requirement of the winter wheat in North China and its formation are analyzed based on the spatial variation of the main affecting factors and the regression coefficients. The findings reveal that the collinearity can be effectively removed when PCA is applied to process all of the affecting factors. The regression coefficients of GWR displayed a strong variability in space, which can better explain the spatial differences of the effect of the affecting factors on the crop water requirement. The evaluation index of the proposed method in this study is more efficient than the widely used Kriging method. Besides, it could clearly show the effect of those affecting factors in different spatial locations on the crop water requirement and provide more detailed information on the region where those factors suddenly change. To sum up, it is of great reference significance for the estimation of the regional crop water requirement.

Multivariate Cluster and Principle Component Analyses of Selected Yield Traits in Uzbek Bread Wheat Cultivars

Investigation of genetic diversity of geographically distant wheat genotypes is a useful approach in wheat breeding providing efficient crop varieties. This article presents multivariate cluster and principal component analyses (PCA) of some yield traits of wheat, such as thousand-kernel weight (TKW), grain number, grain yield and plant height. Based on the results, an evaluation of economically valuable attributes by eigenvalues made it possible to determine the components that significantly contribute to the yield of common wheat genotypes. Twenty-five genotypes were grouped into four clusters on the basis of average linkage. The PCA showed four principal components (PC) with eigenvalues > 1, explaining approximately 90.8% of the total variability. According to PC analysis, the variance in the eigenvalues was the greatest (4.33) for PC-1, PC-2 (1.86) and PC-3 (1.01). The cluster analysis revealed the classification of 25 accessions into four diverse groups. Averages, standard deviations and variances for clusters based on morpho-physiological traits showed that the maximum average values for grain yield (742.2), biomass (1756.7), grains square meter (18,373.7), and grains per spike (45.3) were higher in cluster C compared to other clusters. Cluster D exhibited the maximum thousand-kernel weight (TKW) (46.6).

Comparison of Principal Components Analysis,Independent Components Analysis and Common Components Analysis

The aim of this work is to describe and compare three exploratory chemometrical tools,principal components analysis,independent components analysis and common components analysis,the last one being a modification of the multi-block statistical method known as common components and specific weights analysis.The three methods were applied to a set of data to show the differences and similarities of the results obtained,highlighting their complementarity.

Unsupervised Functional Data Clustering Based on Adaptive Weights

In recent years, functional data has been widely used in finance, medicine, biology and other fields. The current clustering analysis can solve the problems in finite-dimensional space, but it is difficult to be directly used for the clustering of functional data. In this paper, we propose a new unsupervised clustering algorithm based on adaptive weights. In the absence of initialization parameter, we use entropy-type penalty terms and fuzzy partition matrix to find the optimal number of clusters. At the same time, we introduce a measure based on adaptive weights to reflect the difference in information content between different clustering metrics. Simulation experiments show that the proposed algorithm has higher purity than some algorithms.

不同软枣猕猴桃资源果实抗氧化活性比较分析

为评价不同软枣猕猴桃资源果实抗氧化活性,该研究以32份软枣猕猴桃资源果实为材料,测定其总酚、总黄酮、维生素C、花青素含量、DPPH自由基、羟基自由基、超氧阴离子自由基清除率、总抗氧化能力和总还原力,并对其进行差异性分析、加权综合评价、相关性分析与主成分分析。结果表明:各资源果实的总酚、总黄酮、维生素C和花青素含量存在差异。综合评价抗氧化能力,排名在前5位的资源为B080401、A180902、A100703、B020802、A100101。总酚和维生素C含量对软枣猕猴桃抗氧化活性贡献较大。DPPH自由基清除率、超氧阴离子自由基清除率、总抗氧化能力和总还原力4种测定方法适用于软枣猕猴桃资源果实抗氧化能力测定。总酚含量、总黄酮含量、维生素C含量、DPPH自由基清除率、羟基自由基清除率、超氧阴离子自由基清除率、总抗氧化能力和总还原力为软枣猕猴桃抗氧化能力的主要测定项目。

基于PCA-ShapeDTW-QWGRU的分布式光伏集群短期功率预测

针对分布式光伏短期功率预测建立基于主成分分析、改进的动态时间规整算法与量子加权门控循环单元(PCAShapeDTW-QWGRU)的集群功率预测模型。针对集群划分不够精细、光伏电站数据蕴含的信息难以捕捉的问题,提出基于主成分分析结合密度聚类算法(PCA-OPTICS)的集群划分方法;针对目前选取代表电站与集群相似性较低的问题,提出基于改进的动态时间规整算法(ShapeDTW)的代表电站的选取方法,利用ShapeDTW度量相似性距离,选取最小值作为代表电站,并利用基于均方根传播梯度下降法优化的量子加权门控循环单元(RMSprop-QWGRU)模型进行预测;为了解决代表电站与集群功率的变换系数转换差异较大的问题,采用实时变换系数对代表电站进行集群功率值预测计算。实验结果表明,所提方法能有效提升光伏集群功率预测的精度。

“五位一体”总体布局下陕西省城市宜居性评价及关键驱动力研究

以陕西省为例,基于“五位一体”总体布局,使用熵权TOPSIS法对10个地级市的城市宜居性进行评价与分析,并运用主成分析法对区域内城市宜居性提升的关键驱动力进行研究。结果表明,陕西省西安市的城市宜居性较高,且与其他城市存在较大的差异,但总体上各城市宜居性仍有较大的提升空间;商洛、安康和铜川的城市宜居性一直处于较低水平。陕西省城市宜居性提升的驱动力在不同时段存在一定的差异。2011—2015年的关键驱动力为政治、经济和社会因素,关键驱动因子为公共服务水平、经济发展水平、基层政治服务水平、资源供给水平和产业结构优化水平。2016—2020年的关键驱动力转变为经济、文化、社会和生态文明因素,关键驱动因子为通信文化交流环境、公共服务水平、水土流失治理水平、共同富裕水平、污水治理效率和对外开放水平。公共服务水平驱动因子在两个不同的时期对城市宜居性的提升均发挥着重要的促进作用。

基于加权主元分析(WPCA)的人脸识别

将特征加权和主元分析相结合,提出了一种新的加权主元分析方法;这种方法先根据加权重建误差最小化,计算出各类训练样本的加权子空间,然后计算测试样本点到各加权子空间的距离,并根据该距离进行分类识别。最后,通过对剑桥ORL数据库进行的试验证明,该方法与传统的主元分析相比可以在不增加运算量的情况下大大提高识别率。

腌制剂及冲洗工艺对宣威火腿滋味的影响

以宣威火腿为研究对象,探讨3种腌制剂及2种冲洗工艺对其滋味特征的影响。通过钠离子含量、水分含量、水分活度、氨基酸、核苷酸、肽分子质量分布和电子舌分析不同宣威火腿滋味化合物和滋味属性的差异。结果表明,海藻碘盐腌制且高压水枪冲洗的火腿钠离子含量最高,为6.61 g/100 g;氯化钠腌制且清水浸泡冲洗的火腿中氨基酸含量最高,为961.96 mg/100 g;海藻碘盐腌制且高压水枪冲洗的火腿中核苷酸含量最高,为493.38 mg/100 g;分子质量分布分析表明,清水浸泡冲洗的火腿中小分子肽(<1000 Da)含量最多;电子舌分析发现高压水枪冲洗的火腿鲜味和咸味显著高于清水浸泡处理的火腿;主成分分析发现,高压水枪冲洗的条件下海藻碘盐和氯化钠腌制的宣威火腿在鲜味、咸味和丰富度上更加接近,该研究在阐明不同腌制剂及冲洗工艺对宣威火腿滋味影响的前提下,为提升宣威火腿的品质及其工业化提供了理论依据及技术支撑。

基于熵权法、灰色关联度法和低场核磁共振检测的苹果品质评价

研究不同品种苹果的品质特性,建立苹果品质综合评价模型。以5个品种的苹果(天水花牛、阿克苏糖心、黄元帅、奶油富士、洛川红富士)作为研究对象,对其硬度、黏着性、咀嚼性、内聚性等4项质构特性和含水量、可滴定酸(Titratable acid,TA)、可溶性糖含量(Soluble sugar,SS)、可溶性固体含量(Soluble solid content,SSC)等4项理化指标进行检测,结合低场核磁共振检测技术,探究苹果水分分布与理化及质构特性间的关联性,通过主成分分析法确立可评价苹果品质的主要指标。基于熵权法对各核心指标赋予权重,并建立灰色关联度评价模型。结果表明,不同品种苹果的各指标存在显著性差异(P<0.05),其水分分布与质构特性和理化指标存在高度的相关性,确立了自旋-自旋弛豫时间T_(22)(不易流动水)、T_(21)(结合水)及TA、SS、SSC为核心指标。熵权法计算权重结果得出T_(22)、T_(21)之和为35.31%,占比最大,表明水分分布对苹果品质影响最大,由灰色关联度分析得出天水花牛和阿克苏糖心的品质较好。本研究所采用的方法,能够快速准确地建立苹果的品质评价模型,为包括苹果在内的果蔬品质评价提供新方法。

一种融合WPCA与WLDA的人脸识别方法

提出了一种融合加权PCA与加权LDA的人脸识别方法。该方法将主成分分析(PCA)的优点和线性鉴别分析(LDA)的优点充分地融合在一起,以欧式距离为参数的权函数w1使得PCA降维时加入类别差异从而得到最优投影矩阵,解决了PCA过程中使用最小距离方法时识别精度相对低的缺点;以马氏距离为参数的权函数w2使得LDA分类时,进一步扩大类间离散度,减小类内离散度。另外该方法在识别精度上比WPCA+LDA、PCA+WLDA、PCA+LDA算法都有很大的提高,通过在ORL、AR、FERET人脸库上的实验验证了算法的有效性。

矩阵数据基于鲁棒主成分分析的距离加权判别分析

距离加权判别(DWD)是一种已被广泛应用的矩阵数据分类模型,当数据中存在严重的噪声污染时,该模型的性能会明显下降。鲁棒主成分分析(RPCA)因具备分离数据矩阵低秩结构和稀疏部分的特性已成为解决该问题的有效手段之一。因此,提出一种矩阵数据鲁棒距离加权判别(RDWD-2D)模型。特别地,该模型以有监督的方式对数据矩阵进行鲁棒主成分分析,并同步实现干净数据的恢复与分类。在MNIST和COIL20数据集上的实验结果表明,针对有噪声污染或数据缺失的矩阵数据,与DWD-2D、RPCA+DWD等模型相比,RDWD-2D模型有最好的数据恢复能力和最高的分类准确率;同时RDWD-2D模型对于数据污染度也有较好的鲁棒性。

基于WPCA和修正的最大间距准则的人脸识别

针对Fisher准则遇到的高维小样本问题和最大间距准则遇到的"次优化问题",提出一种基于加权PCA(WPCA)和修正的最大间距准则(MMMC)的线性判别分析方法。首先对PCA空间进行加权,对最大间距准则的散布矩阵进行修正,然后结合WPCA和MMMC进行特征提取。该方法为有效地解决上述两个问题提供了途径。在ORL和FERET人脸库上的实验结果验证了该方法的有效性。

基于MIWOA优化SCN的变压器故障诊断研究

针对变压器故障诊断精确度低的问题,本文提出了一种多策略改进的鲸鱼优化算法(MIWOA)优化随机配置网络(SCN)的变压器故障诊断模型。首先,对变压器冗杂繁多的原始故障数据进行核主成分分析(KPCA)降维处理,降低无效特征的影响;其次,利用Tent混沌映射、动态自适应权重和初级知识获取共享算法对鲸鱼算法(WOA)进行改进,提高其优化能力;然后,在SCN中引入L2范数惩罚项进行正则化处理,并使用改进后的MIWOA算法对SCN惩罚项系数C进行寻优求解,提高SCN分类精度和泛化能力;最后,将降维的数据输入到MIWOA-SCN故障诊断模型中,提高模型收敛速度。结果表明,本文所提出的模型诊断精度为93.1%,与WOA-SCN、GWO-SCN和PSO-SCN诊断模型相比,分别提高了6.89%、9.48%、14.65%,证明MIWOA-SCN诊断模型在变压器故障诊断上具有良好的诊断效果。

天水地区花牛苹果主栽品种香气成分研究

香气成分是苹果品质和地理标志性产品的重要指标,分析天水地区主栽花牛苹果的香气成分构成,对科学鉴别花牛苹果品种和保护种质资源具有重要意义。本研究使用气相色谱质谱联用技术对天水地区4个花牛苹果主栽品种的挥发性化合物进行鉴定,用CRITIC权重法确定最适谱库匹配度,用主成分分析方法(PCA)进行特征香气成分分析。结果表明,标准谱库匹配度≥50%可作为香气化合物判定的依据,4个品种共鉴别出22种香气成分,其中酯类物质占比均在99%以上;主成分分析表明,‘俄矮二号’‘天汪一号’‘首红’和‘栽培二号’的特征香气成分分别有4、2、3、1种。

雷州山羊体尺与体重指标的主成分分析

目的:选育工作中以主成分为单位首先进行集团选择,再根据对主成分贡献率较大的单一性状进行筛选,以提高选育效率。根据雷州山羊体重和体尺性状之间的相关性进行主成分分析,可以为雷州山羊的选种提供重要参考依据。方法:该试验选取体重相近且健康状况良好的雷州山羊公羔60只,采用放牧+补饲方式饲养至60日龄断奶,并进行体重、体高、体斜长等11个体尺指的测定及主成分分析。结果:雷州山羊公羔的腰角宽变异系数最大,有较大的选择潜力;体重与管围的相关系数为0.484,达到显著正相关的水平(P<0.05)。体重与体尺性状可区分为相对独立的4个主成分:躯体因子、匀称因子、特征类因子以及宽度因子。第一主成分的贡献率为31.727%,其中胸深、额宽、体斜长以及肢高的特征向量系数较大,分别为0.432、0.413、0.384以及0.361。结论:胸深、额宽、体斜长以及肢高是雷州山羊公羔的主要性状指标。

HPLC多指标成分定量、化学计量学及熵权-TOPSIS分析在龙葵综合质量评价中的应用

目的建立不同产地龙葵中11个成分含量同步检测方法,并采用化学计量学和熵权-TOPSIS法对其质量进行评价。方法收集8省17个批次龙葵样品,采用HPLC法同时检测龙葵中梣皮树脂醇、松脂素、槲皮素、芦丁、澳洲茄碱、澳洲茄边碱、客西茄碱、澳洲茄胺、去半乳糖替告皂苷、薯蓣皂苷元和β-谷甾醇的含量,建立龙葵多组分定量控制模式;采用化学识别模式和熵权-TOPSIS法建立龙葵质量优劣评价模型,对其整体质量进行综合评价。结果11个成分分别在0.78~39.00,0.55~27.50,0.34~17.00,0.21~10.50,41.87~2093.50,60.95~3047.50,2.58~129.00,1.02~51.00,0.46~23.00,1.05~52.50,0.42~21.00μg/mL(r>0.9990)范围内线性关系良好,平均加样回收率在96.81%~100.28%范围内(RSD<2.0%,n=9);17批样品聚为3类;澳洲茄边碱、澳洲茄碱、去半乳糖替告皂苷和梣皮树醇可能是影响龙葵产品质量主要潜在标志物;熵权-TOPSIS法分析结果显示17批龙葵质量评价贴近度分别为0.4336、0.4168、0.6242、0.5008、0.4791、0.6361、0.5683、0.2500、0.1909、0.2221、0.1707、0.7200、0.6983、0.7447、0.7179、0.7209、0.7183,辽宁、吉林和黑龙江产地龙葵整体质量较好,其次为江苏、河南和安徽产地。结论建立的同时测定龙葵中11种成分含量的HPLC法,操作便捷,结果准确;化学计量学及熵权-TOPSIS法客观全面,可用于龙葵的整体质量评价。