Differentiation and classification of counterfeit and real coins by applying statistical methods

Download
2012
Tansel, İçten
In this study, forty coins which were obtained from Museum of Anatolian Civilizations (MAC) in Ankara were investigated. Some of those coins were real (twenty two coins) and the remaining ones (eighteen coins) were fake coins. Forty coins were Greek coins which were dated back to middle of the fifth century BCE and reign of Alexander the Great (323 – 336 BCE). The major aims of this study can be summarized as follow; • To analyze coins under study to determine elemental contents and to measure physical properties (weights and diameters) • To illustrate the use of cluster analysis technique for forgery analysis • Specifically, to carry out cluster analysis for Greek coins (dated back to middle of the fifth century BCE and reign of Alexander the Great (323 – 336 BCE)) that were obtained from MAC. In chemical analysis, portable X-Ray fluorescence (PXRF) spectrometry was used. By using portable XRF spectrometry chemical compositions of the coins were determined. Results obtained from XRF analysis were analysed statistically. In statistical analysis, cluster analysis was carried out. Before clustering, correlation - a technique that determines the relation between two or more variables - was used in order to determine the most related elements. The most related elements mean that elements contain high and negative correlation between them. In this study, the most related elements were determined by using Pearson’s correlation coeefficient. Pearson’s correlation coefficient which was equal or higher than -0.50 was assumed efficient. Variables of clustering was chosen from major elements of the coins ((Ag (silver), Cu (copper), Fe (iron) and Pb (lead)). Pairs were constructed from those four major elements such as Ag-Cu, Ag-Fe, Ag-Pb, Cu-Fe, Cu-Pb, Fe-Pb. In this study, hierarchical agglomerative clustering algorithm and complete linkage were prefered. Results of clustering was visualized by using the most common graphical form of clustering. At this point, dendrograms were constructed. Two dendograms were constructed for each element pair. In the construction of one dendogram ratio of the elements between them were used. On the otherhand, in the construction of other dendogram individual values of the elements were used. Differentiation of fake coins from their real ones realized in many relations. Lastly, independent samples t test was applied in order to determine the magnitude of the difference between groups of real and fake coins.
Citation Formats
İ. Tansel, “Differentiation and classification of counterfeit and real coins by applying statistical methods,” M.S. - Master of Science, Middle East Technical University, 2012.