高维稳健主成分聚类方法及其应用研究

随着信息技术的高速发展,每条数据所包含的信息越来越丰富,使得数据不可避免地含有异常值,且随着维数的增加,异常值出现的可能性更大。传统的主成分聚类分析对异常值特別敏感,基于MCD估计的主成分聚类方法虽然对异常值具有防御作用,但是在高维数据下MCD估计的偏差过大,其稳健性显著降低,而且当维数大于观测值个数时MCD估计失效。为此本文提出了基于MRCD估计的稳健主成分聚类方法,数值模拟和实证分析表明,基于MRCD估计的主成分聚类分析的效果优于传统的主成分聚类分析和基于MCD估计的主成分聚类分析,尤其是在维数大于样本观测值的情况下,MRCD估计更为有效。     

Orientation-reversing involutions on handlebodies

The observation that the quotient orbifold of an orientation- reversing involution on a 3-dimensional handlebody has the structure of a compression body leads to a strong classification theorem, and general structure theorems. The structure theorems decompose the action along invariant discs into actions on handlebodies which preserve the -fibers of some -bundle structure. As applications, various results of R. Nelson are proved without restrictive hypotheses.

     

pH滴定-主成分回归法同时测定酚类同系物

本文利用pH滴定－主成分回归法同时测定了苯酚、邻苯二酚、邻苯三酚的混合物，结果良好。通过交差验证法，本文还对采样区间和采样间隔作了详细讨论。     

Simultaneous kinetic determination of thiocyanate and sulfide using eigenvalue ranking and correlation ranking in principal component-wavelet neural network

In this work, two toxic compound, sulfide and thiocyanate were determined simultaneously using kinetic spectrophotometry. These anions have shown the catalytic effects on the reaction between iodine and azide. Since the system was nonlinear, a nonlinear model, principal component-wavelet neural network (PC-WNN) was used as the multivariate calibration method. The principal component analysis was used to decrease the dimension of the original matrix. In other words, the scores of the PCs, 5, instead of the original variables, 301, were used as the input for the model. Two methods were used to select the most relevant principal components: eigenvalue ranking and correlation ranking. In this work, eigenvalue and correlation ranking methods have shown better results for thiocyanate and sulfide, respectively, and it can be concluded that these methods are complementary. The WNN has several advantages relative to other types of neural network such as better convergence ability. The data set was divided to calibration, prediction and validation sets. Each set was selected so that the concentrations of the analytes were approximately covered the entire ranges of the analytes. Mean relative error for thiocyanate and sulfide in validation set were 8.5 and 10.6, respectively. Thiocyanate and sulfide can be determined in the range of 60–700 ng ml⁻¹ and 20–400 ng ml⁻¹, respectively. The proposed method was applied for the determination of sulfide and thiocyanate in real samples such as tap, waste and river waters with satisfactory results.     

超细碳氮化钛的分析和评估

采用多种技术对超细碳氮化钛进行组成分析。可分别测定吸附和化合状态的氧。晶格常数与(原子比)具有线性关系,表明碳与氮可以相互无限置换,分子式为Ti C_xN_(1-x),每一样品只有一种C/N比.固溶体是均质的。气相合成的碳氮化钛含微量杂质,包括游离碳和氯根等,主相量显著地受吸附氧量影响,可控制达97％以上。介绍了拟定的分析方法。     

Implementation and efficiency of an automatic peak-purity-control procedure in HPLC-UV-VIS-coupling based on principal component analysis

Summary Based on a thorough knowledge of the actual system precision significance testing of the primary eigen values, resulting from principal component analysis of the two-dimensional data array of HPLC with photodiode-array detection, is a powerful means to uncover unresolved chromatographic peaks. The implementation of this chemometric technique for assuring peak homogeneity and results showing the efficiency for two-component peaks in regard to spectral characteristics, chromatographic resolution and absorbance ratio of the investigated compounds are presented.     

高分子效应

用许多杰出的实例,从高分子骨架的机械支架作用、邻基效应、协同效应、模板聚合等诸方面探论了高分子效应。     

Structural Features of Solid Phases and Topology of Phase Diagrams

The paper considers model phase diagrams of binary and ternary systems involving transformations (transitions) of phase equilibria. The relationship between the type of structural solidstate transformation and the type of phase diagram is shown. Topological series of phase diagrams of systems with continuous and limited types of solid solutions are considered, including phase diagrams with polymorphic transitions between intermediate solid phases of variable composition.     

主成份分析-偏最小二乘法分光光度法同时测定钴、镍、铜、锌四组份体系

用 PCA 及 PLS 分步处理分光光度数据,有效降低了计算的维数。以该法对不同酸度体系的5-Br-PADAP-钴、镍、铜、锌分光光度数据进行了处理,定量分析结果良好。     

Interaction of cubosomes with plasma components resulting in the destabilization of cubosomes in plasma

Cubosomes are novel dispersed nanoparticles with bicontinuous cubic phases of monoolein in their interior. We investigated their disintegration process in plasma by in vitro and in vivo studies. Cubosomes were incubated with whole plasma or plasma components such as HDL, LDL, and albumin. The lypolysis study indicated lipolytic activity of whole plasma towards cubosomes. Gel filtration chromatography revealed that HDL, LDL and albumin interacted with cubosomes. HDL affected cubosomes’ integrity and gave rise to smaller particles which contained the components of both cubosomes and HDL. Upon incubation with LDL, cubosomes fused with LDL. Albumin was shown to take up monoolein out of the particles. Cubosomes were disintegrated by whole plasma as a result of the interaction with plasma components. It was concluded that in vivo observation of a long circulation time of a hydrophobic substance in cubosomes was due to the sustained behavior of cubosome remnant particles.