Thirty-three archaeological ceramic fragment samples from Damascus Castle archaeological site, Damascus city, Syria, were analyzed using instrumental neutron activation analysis (INAA). 36 elements were determined. These elemental concentrations have been processed using two multivariate statistical methods, cluster and factor analysis in order to determine similarities and correlation between the various samples. Factor analysis confirms that 84.8% of the ceramics samples classified by cluster analysis are correctly classified by cluster analysis. The results provided persuasive evidence that Castle pottery used at least four different clay sources. Moreover, by means of systematic local analysis it will be clear whether these sources are local or not.
Authors:Cairong Luo, Jie Liu, Yan Liang, Xiangchun Shen, Xiaoyan Zhang, and Wei Zhou
were statistically processed by multivariate statistical analysis including bivariate analysis, hierarchical clusteringanalysis (HCA) and principal component analysis (PCA). Multivariate statistical analysis was used to evaluate the intrinsic quality
A method of measuring the communication in a network of research institutions i presented. The method is based on the determination of the subject similarity of research reports. The requests of the users are taken into account. The hierarchic cluster analysis of communication in the network is fulfilled on the base of the fuzzy binary relations of similarity between objects.
Authors:Jean-Charles Lamirel, Claire Francois, Shadi Al Shehabi, and Martial Hoffmann
The information analysis process includes a cluster analysis or classification step associated with an expert validation of the results. In this paper, we propose new measures of Recall/Precision for estimating the quality of cluster analysis. These measures derive both from the Galois lattice theory and from the Information Retrieval (IR) domain. As opposed to classical measures of inertia, they present the main advantages to be both independent of the classification method and of the difference between the intrinsic dimension of the data and those of the clusters. We present two experiments on the basis of the MultiSOM model, which is an extension of Kohonen's SOM model, as a cluster analysis method. Our first experiment on patent data shows how our measures can be used to compare viewpoint-oriented classification methods, such as MultiSOM, with global cluster analysis method, such as WebSOM. Our second experiment, which takes part in the EICSTES EEC project, is an original Webometrics experiment that combines content and links classification starting from a large non-homogeneous set of web pages. This experiment highlights the fact that break-even points between our different measures of Recall/Precision can be used to determine an optimal number of clusters for web data classification. The content of the clusters obtained when using different break-even points are compared for determining the quality of the resulting maps.
Descriptive capacities of a new bibliometric method, namely co-heading analysis, are investigated. The method uses the appearance and co-appearance of classification subdivisions (headings) in the document records of 1988 INSPEC database to display correspondingly the main topics of Australian geophysics and their links. The findings, in the form of inclusion maps (resulting from multidimensional scaling and cluster analysis) provide new insights into geophysics national activity and into its structure.
Analysis of scientific production is made in the domains of vaccines for the period 1990–1995, including eight Iberian-American
countries. To attain the results, different indicators were applied such as: collaboration rate, activity index and representation
techniques, using a cluster analysis and multidimensional scaling. Similarities between countries are represented according
to their activity index in the subject field. Results show a discontinuity in the scientific production over the years, where
each country has a peculiar behavior.
Authors:E. Mello, S. Lusuardi, S. Meloni, and M. Oddone
Recently excavated roman amphorae were submitted to instrumental neutron activation analysis for the determination of Ca,
Sc, Cr, Fe, Co, Sb, Ba, La, Ce, Eu, Yb, Lu, Hf and Th. Data reduction was carried out by identifying first the elements useful
for discrimination purposes and then by submitting the data to cluster analysis. Amphorae are parted in two groups which are
related to different provenance areas.
Authors:M. Peisach, L. Jacobson, G. Boulle, D. Gihwala, and L. Underhill
Data on the concentrations of K, Ca, Ti, Fe, Cu, Zn, Ga, Rb, Sr and Zr obtained by PIXE and of B, F, Na, Mg, Al, Si and Cu
obtained by proton-induced prompt gamma-ray spectrometry were used to characterize archaeological artefacts and source materials
by multivariate analysis. The mathematical approaches employed were cluster analysis using nearest-neighbour data, multidimensional
scaling and correspondence analysis.
Authors:M. Bacchi, E. De Nadai Fernandes, S. Tsai, and L. Santos
The elemental composition of potato tubers from four varieties growing in an experimental field under conventional and organic
conditions was investigated. Br, Co, K, Na, Rb and Zn, determined by k0-instrumental neutron activation analysis, were used to distinguish the tubers according to the cultivation system. The difference
between organic and conventional potatoes was evidenced by cluster analysis, specially using Br, Co, K and Rb.
Authors:X.-J. Chen, W. Miao, Y. Liu, Y.-F. Shen, W.-S. Feng, T. Yu, and Y.-H. Yu
Using isothermal microcalorimetry, the growth power-time
curves of three strains of Tetrahymena
were determined at 28C. Their Euclidean distances and cluster analysis
diagram were obtained by using two thermokinetic parameters (r
and Qlog), which
showed that T. thermophila BF1
and T. thermophila BF5
had a closer relationship. Compared with the single molecular biomarker (ITS1)
method, microcalorimetry wasmaybe a simpler, more sensitive andmore economic
technique in the phylogenetic studies of Tetrahymena