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).

Water Quality Evaluation Model Based on Principal Component Analysis and Information Entropy:Application in Jinshui River

水质评价对决策者决定水的使用功效尤为重要。水质综合评价系统中涉及到大量因子与指标,因子之间相互作用,致使水质的评价工作相对困难。主成分分析法可以消除因子间的相关性,因而被广泛应用于水质评价,但其忽略了数据离散程度的问题。熵值法则考虑了数据的离散特点。为更好地进行水质的综合评价,本文提出把主成分分析法和熵值法结合起来确定指标权重的方法,建立了水质评价模型,并采用该模型对郑州市金水河再生水2009年的水质情况进行评价,将评价结果与单独采用主成分分析或熵值法的结果进行了比较。结果表明了该方法的可行性与实用性,能够为非常规水资源利用提供理论依据和决策参考。

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。

数字零工劳动权益影响因素研究

互联网平台企业的发展催生了数字零工这一新兴工作群体,清晰识别数字零工劳动权益的核心影响因素对保护其劳动权益至关重要。运用扎根理论构建了包含国家政策法规、平台管理、工会支持能力和顾客四个维度的数字零工劳动权益影响因素模型。采用加权主成分分析法对模型赋权并进行评价,认为平台管理、国家政策法规的相关影响力较大,工会支持能力和顾客的影响力也不容忽视。要维护数字零工劳动权益,应持续规范和优化互联网平台企业管理、加快数字零工劳动权益保护的法治进程、提升数字零工工会的支持能力、强化顾客对数字零工的情感认同。

“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。

时间特征与空间特征融合的轻量网络故障诊断方法

为了解决多传感器数据间存在信息交叉、特征重复,导致模型训练精度低的问题,对滚动轴承在声辐射信号下的故障诊断进行了研究,提出了一种时间特征与空间特征融合的轻量网络故障诊断(SF-TFNet)方法。首先,利用卷积神经网络提取了原始轴承声阵列信号的空间特征(SFs),使用长短时记忆网络(LSTM)提取了声阵列信号中的时域特征(TFs),并对提取的SFs和TFs进行了特征融合,生成了新的特征矩阵;然后,为了消除融合特征带来的重叠特征和信息冗余问题,引入了基于核的主成分分析(KPCA)方法对新生成的特征矩阵进行了非线性降维,去除了特征中的冗余成分,构建了滚动轴承新的时空特征数据集;最后,采用AdaBoost算法对新生成的数据集进行了故障分类,并得到了滚动轴承的最终故障诊断结果。研究结果表明:在半消声室滚动轴承故障实验台测试中,SF-TFNet方法的故障分类精度可以达到99.75%,其分类精度较高、聚类效果明显。在强背景噪声环境下与ResNet、ICNN和AlexNet三种方法进行比较,SF-TFNet方法不仅收敛速度快,而且故障识别精度高,诊断精度最高可达99.25%。为基于多通道的滚动轴承声辐射信号故障诊断提供了理论依据。

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。

腾冲雪鸡体重与体尺性状的主成分和聚类分析

试验旨在研究腾冲雪鸡体重与体尺性状的关联性以及体型特征。试验采用相关分析、主成分分析和聚类分析等方法研究30只300日龄健康的公鸡和母鸡的体重及8个体尺指标。结果显示:腾冲雪鸡公鸡和母鸡体重平均值分别为(2689.33±308.49)g和(2016.67±351.44)g,公鸡体重显著高于母鸡(P<0.05)。除胸角外,公鸡其余体尺指标均显著高于母鸡(P<0.05)。主成分分析显示,腾冲雪鸡9个指标可简化为3个主成分,它们在公、母鸡中的累计贡献率分别为73.962%和74.900%;公、母鸡简化的主成分中,以体重、体斜长、胫围、龙骨长、胫长、髋骨宽和胸宽对主成分的贡献最大。聚类分析将测定的公、母鸡指标分别聚为4类。研究表明,腾冲雪鸡体型指数在云南主要地方鸡中处于中等水平,骨骼较大,产肉性能较好,属于体型较大品种,研究结果可为进一步选育腾冲雪鸡提供参考。

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。

矿区生态监测的地理加权遥感生态指数构建及评价

矿区生态是陆地生态系统的重要组成部分,准确监测矿区生态对保护生态环境、维持生态平衡具有重要意义。遥感技术为矿区生态监测提供了有效手段,针对遥感生态指数(remote sensing ecological index,RSEI)在矿区生态监测中存在监测精度低、针对性弱和指标权重空间上均一化问题,该研究对RSEI进行了改进。首先,考虑矿区特殊的生态成因,在绿度、热度、湿度、干度的基础上加入煤尘污染因子构成矿区遥感生态指数;然后,利用地理加权主成分分析法确定各指标的空间权重,构建了地理加权遥感生态指数(geographically weighted-remote sensing ecological index,GWRSEI);最后,以山西省大同煤田为例,基于多期遥感影像对GW-RSEI在矿区生态监测中的有效性、适用性进行了验证。结果表明:GW-RSEI能准确捕捉矿区大气中的煤尘污染,从整体和局部尺度实现了矿区生态的精准监测,有效提高了矿区生态监测的精度;地理加权主成分分析法能够明确表征矿区生态的空间异质性和生态环境变化的空间连续性;2000—2020年大同煤田的GW-RSEI均值分别为0.51、0.48、0.46、0.59、0.56,整体生态环境经历了先恶化后改善的过程,其东南部生态环境变化趋势与整体一致,而西北部生态环境呈现先改善后恶化的变化趋势。研究成果为准确监测矿区生态提供了一种更加科学、有效的方法。

基于逆方差加权的光谱反射率重建算法研究

为了能较大程度的满足图像复制的需求,避免同色异谱现象,研究光谱重建算法对光谱反射率重建精度和色度的影响。通过改进传统的主成分分析法,提出逆方差加权回归的光谱反射率重建算法。首先,引入逆方差加权模型,调整因子权重;其次,对光谱反射率训练样本集归一化处理,计算新的协方差矩阵;最后,对加权后的光谱反射率样本集奇异值分解,重建光谱反射率。实验表明,基于逆方差加权的光谱反射率重建算法的CIE DE2000颜色精度提高了3.3%,光谱重建精度提高了2%,能够实现良好的颜色再现效果。加权算法可以应用于光谱反射率重建过程,有助于提高光谱重建精度和色度。