社会化商务中消费者感知推荐信任的聚类方法研究

新兴社会化商务社会中人与人之间的高交互性及推荐信息的海量化和高动态性,对平台分析消费者感知信任提出了新的挑战。然而,对推荐信息进行聚类难以体现消费者主观性及主体间关系。本文将感知推荐信任聚类问题转化为复合网络划分问题,将主观逻辑方法与基于Normal矩阵的谱平分方法相结合构建社会化商务中消费者感知推荐信任的聚类方法。首先,将推荐信息转化为感知推荐信任,然后,从社交网络中抽取感知推荐信任相似度与关系亲密度网络,并构建Normal矩阵用谱平分方法进行划分。最后,通过多组仿真实验证明了该方法的实用性和有效性。该方法能够为社会化商务中消费者信任的分析提供新视角,为平台制定精准化营销策略提供支持。     

Polypeptide folding on a conformational‐space network: Dependence of network topology on the structural discretization procedure

Mapping the conformational space of a polypeptide onto a network of conformational states involves a number of subjective choices, mostly in relation to the definition of conformation and its discrete nature in a network framework. Here, we evaluate the robustness of the topology of conformational‐space networks derived from Molecular Dynamics (MD) simulations with respect to the use of different discretization (clustering) methods, variation of their parameters, simulation length and analysis time‐step, and removing high‐frequency motions from the coordinate trajectories. In addition, we investigate the extent to which polypeptide dynamics can be reproduced on the resulting networks when assuming Markovian behavior. The analysis is based on eight 500 ns and eight 400 ns MD simulations in explicit water of two 10‐residue peptides. Three clustering algorithms were used, two of them based on the pair‐wise root‐mean‐square difference between structures and one on dihedral‐angle patterns. A short characteristic path length and a power‐law behavior of the probability distribution of the node degree are obtained irrespective of the clustering method or the value of any of the tested parameters. The average cliquishness is consistently one or two orders of magnitude larger than that of a random realization of a network of corresponding size and connectivity. The cliquishness as function of node degree and the kinetic properties of the networks are found to be most dependent on clustering method and/or parameters. Although Markovian simulations on the networks reproduce cluster populations accurately, their kinetic properties most often differ from those observed in the MD simulations. © 2010 Wiley Periodicals, Inc. J Comput Chem, 2010     

基于加权相似性的BIRCH聚类算法

BIRCH方法是一个集成的层次聚类方法.它克服了凝聚层次聚类方法所面临的两个难点:可伸缩性和不能撤销前一步工作的问题.基于BIRCH聚类的多阶段聚类算法思想,结合基于权重的欧式距离度量和基于划分的K-means算法,提出了一种基于加权相似性的BIRCH聚类方法,并将方法应用在时间序列的气象数据分析中.     

基于FA-DEA聚类的模式分析方法及在我国软件园研究中的应用

模式分析方法日益成为现代经济管理研究的主流方法之一,但是目前关于模式分析的结构化方法的研究还不多见.本文提出了基于FA-DEA聚类的模式研究结构化方法,这个方法区别于以往文献的是采用了混合聚类方法,综合运用关键因素的绝对量信息和效率的相对量信息.基于上述方法,本文确定了我国软件园发展的三种发展模式.并对三个模式的条件、特征以及它们之间的分界与演进做了详细的描述.最后,给出了若干建议.     

主成分方法用于聚类分析

本文提出一种新的聚类分析方法，它通过主成分分析简化数据，将原样品转化成单指标有序样品，然后利用有序样品的系统聚类法加以分类．其特点是计算量小，节省计算机内存．文中附有一个实例对算法进行说明．     

X-射线小角光散射(SAXS)研究全氟磺酸树脂中空纤维膜中的离子簇结构

本文用SAXS(Small Angle X-ray Scattering)方法对全氟磺酸树脂中空纤维膜中的离子簇结构进行了研究.在散射角2θ=2°左右,出现由离子簇产生的散射峰;并就离子交换容量、不同阳离子形式、含水量及不同拉伸等对离子簇散射峰位的影响进行了研究讨论.并计算了有关离子簇半径和每个离子簇中的离子数目.     

Space-Time Point-Process Models for Earthquake Occurrences

Several space-time statistical models are constructed based on both classical empirical studies of clustering and some more speculative hypotheses. Then we discuss the discrimination between models incorporating contrasting assumptions concerning the form of the space-time clusters. We also examine further practical extensions of the model to situations where the background seismicity is spatially non-homogeneous, and the clusters are non-isotropic. The goodness-of-fit of the models, as measured by AIC values, is discussed for two high quality data sets, in different tectonic regions. AIC also allows the details of the clustering structure in space to be clarified. A simulation algorithm for the models is provided, and used to confirm the numerical accuracy of the likelihood calculations. The simulated data sets show the similar spatial distributions to the real ones, but differ from them in some features of space-time clustering. These differences may provide useful indicators of directions for further study.     

Clustering Rules: A Comparison of Partitioning and Hierarchical Clustering Algorithms

Previous research has resulted in a number of different algorithms for rule discovery. Two approaches discussed here, the ‘all-rules’ algorithm and multi-objective metaheuristics, both result in the production of a large number of partial classification rules, or ‘nuggets’, for describing different subsets of the records in the class of interest. This paper describes the application of a number of different clustering algorithms to these rules, in order to identify similar rules and to better understand the data.     

Identifying Mixtures of Mixtures Using Bayesian Estimation

The use of a finite mixture of normal distributions in model-based clustering allows us to capture non-Gaussian data clusters. However, identifying the clusters from the normal components is challenging and in general either achieved by imposing constraints on the model or by using post-processing procedures. Within the Bayesian framework, we propose a different approach based on sparse finite mixtures to achieve identifiability. We specify a hierarchical prior, where the hyperparameters are carefully selected such that they are reflective of the cluster structure aimed at. In addition, this prior allows us to estimate the model using standard MCMC sampling methods. In combination with a post-processing approach which resolves the label switching issue and results in an identified model, our approach allows us to simultaneously (1) determine the number of clusters, (2) flexibly approximate the cluster distributions in a semiparametric way using finite mixtures of normals and (3) identify cluster-specific parameters and classify observations. The proposed approach is illustrated in two simulation studies and on benchmark datasets. Supplementary materials for this article are available online.     

Flexible and powerful strategy for qualitative and quantitative analysis of valepotriates in Valeriana jatamansi Jones using high‐performance liquid chromatography with linear ion trap Orbitrap mass spectrometry

Valeriana jatamansi Jones is an important medicinal plant and its quality is closely related to its region of origin. In the current study, we utilized a flexible and powerful strategy for comprehensive evaluation of the quality diversity for 15 regions in China. The method was based on a hybrid linear ion trap‐Orbitrap mass spectrometry platform. For structure characterization, fragmentation patterns were detected by analyzing a series of standard compounds using data dependent multistage mass spectrometry acquisition. A fragment ion database for valepotriates was established, and the acquired data were high throughput filtered by fragment ion search for compound identification. For quantitative purposes, we normalized the mass spectrometry data of 15 samples using SIEVE 2.0 and the differences in composition were analyzed using principal component analysis combined with hierarchical clustering analysis. The results identified a total of 92 compounds from Valeriana jatamansi Jones. Samples from Dali, Kunming, and Baoshan have better qualities and concentrations of the main active constituents. To verify our strategy, we compared the valtrate, acevaltrate, and baldrinal contents using high‐performance liquid chromatography with diode array detector. We developed and validated a comprehensive qualitative and quantitative analytical method to achieve quality control of Valeriana jatamansi Jones.