Non-destructive characterisation and classification of ceramic artefacts using pEDXRF and statistical pattern recognition

2012
Authors
Gajić-Kvaščev, MajaMarić-Stojanović, Milica

Jančić-Heinemann, Radmila

Kvascev, Goran S.
Andrić, Velibor

Article (Published version)
Metadata
Show full item recordAbstract
Background: Portable energy dispersive X-ray fluorescence (pEDXRF) spectrometry analysis was applied for the characterisation of archaeological ceramic findings from three Neolithic sites in Serbia. Two dimension reduction techniques, principal component analysis (PCA) and scattering matrices-based dimension reduction were used to examine the possible classification of those findings, and to extract the most discriminant features. Results: A decision-making procedure is proposed, whose goal is to classify unknown ceramic findings based on their elemental compositions derived by pEDXRF spectrometry. As a major part of decision-making procedure, the possibilities of two dimension reduction methods were tested. Scattering matrices-based dimension reduction was found to be the more efficient method for the purpose. Linear classifiers designed based on the desired output allowed for 7 of 8 unknown samples from the test set to be correctly classified. Conclusions: Based on the results, the c...onclusion is that despite the constraints typical of the applied analytical technique, the elemental composition can be considered as viable information in provenience studies. With a fully-developed procedure, ceramic artefacts can be classified based on their elemental composition and well-known provenance.
Keywords:
pEDXRF spectrometry / Pattern recognition / Dimension reduction / Feature extraction / Classification / Cultural Heritage / Neolithic ceramicsSource:
Chemistry Central Journal, 2012, 6Publisher:
- Springeropen, London
Funding / projects:
- IAEA Regional Technical Cooperation Program [RER/0/034]
- Serbian Ministry of Culture [451-04-00792/2011-03]
- Research and verification of the multidisciplinary forensic methods in (RS-37021)
- Increasing the availability and energy efficiency in thermal power plants and energy distribution systems by developing new diagnosis and early fault detection methods (RS-32038)
- Predefined functional properties polymer composite materials processes and equipment development (RS-34011)
- Society, spiritual and material culture and communications in the prehistory and early history of the Balkans (RS-177012)
- System for Optimization of Thermal Power Plant Blocks Operation over 300 MW capacity (RS-42007)
- Synthesis, processing and characterization of nanostructured materials for application in the field of energy, mechanical engineering, environmental protection and biomedicine (RS-45012)
DOI: 10.1186/1752-153X-6-102
ISSN: 1752-153X
PubMed: 22978788
WoS: 000313130500001
Scopus: 2-s2.0-84866144647
Institution/Community
Tehnološko-metalurški fakultetTY - JOUR AU - Gajić-Kvaščev, Maja AU - Marić-Stojanović, Milica AU - Jančić-Heinemann, Radmila AU - Kvascev, Goran S. AU - Andrić, Velibor PY - 2012 UR - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/2153 AB - Background: Portable energy dispersive X-ray fluorescence (pEDXRF) spectrometry analysis was applied for the characterisation of archaeological ceramic findings from three Neolithic sites in Serbia. Two dimension reduction techniques, principal component analysis (PCA) and scattering matrices-based dimension reduction were used to examine the possible classification of those findings, and to extract the most discriminant features. Results: A decision-making procedure is proposed, whose goal is to classify unknown ceramic findings based on their elemental compositions derived by pEDXRF spectrometry. As a major part of decision-making procedure, the possibilities of two dimension reduction methods were tested. Scattering matrices-based dimension reduction was found to be the more efficient method for the purpose. Linear classifiers designed based on the desired output allowed for 7 of 8 unknown samples from the test set to be correctly classified. Conclusions: Based on the results, the conclusion is that despite the constraints typical of the applied analytical technique, the elemental composition can be considered as viable information in provenience studies. With a fully-developed procedure, ceramic artefacts can be classified based on their elemental composition and well-known provenance. PB - Springeropen, London T2 - Chemistry Central Journal T1 - Non-destructive characterisation and classification of ceramic artefacts using pEDXRF and statistical pattern recognition VL - 6 DO - 10.1186/1752-153X-6-102 ER -
@article{ author = "Gajić-Kvaščev, Maja and Marić-Stojanović, Milica and Jančić-Heinemann, Radmila and Kvascev, Goran S. and Andrić, Velibor", year = "2012", abstract = "Background: Portable energy dispersive X-ray fluorescence (pEDXRF) spectrometry analysis was applied for the characterisation of archaeological ceramic findings from three Neolithic sites in Serbia. Two dimension reduction techniques, principal component analysis (PCA) and scattering matrices-based dimension reduction were used to examine the possible classification of those findings, and to extract the most discriminant features. Results: A decision-making procedure is proposed, whose goal is to classify unknown ceramic findings based on their elemental compositions derived by pEDXRF spectrometry. As a major part of decision-making procedure, the possibilities of two dimension reduction methods were tested. Scattering matrices-based dimension reduction was found to be the more efficient method for the purpose. Linear classifiers designed based on the desired output allowed for 7 of 8 unknown samples from the test set to be correctly classified. Conclusions: Based on the results, the conclusion is that despite the constraints typical of the applied analytical technique, the elemental composition can be considered as viable information in provenience studies. With a fully-developed procedure, ceramic artefacts can be classified based on their elemental composition and well-known provenance.", publisher = "Springeropen, London", journal = "Chemistry Central Journal", title = "Non-destructive characterisation and classification of ceramic artefacts using pEDXRF and statistical pattern recognition", volume = "6", doi = "10.1186/1752-153X-6-102" }
Gajić-Kvaščev, M., Marić-Stojanović, M., Jančić-Heinemann, R., Kvascev, G. S.,& Andrić, V.. (2012). Non-destructive characterisation and classification of ceramic artefacts using pEDXRF and statistical pattern recognition. in Chemistry Central Journal Springeropen, London., 6. https://doi.org/10.1186/1752-153X-6-102
Gajić-Kvaščev M, Marić-Stojanović M, Jančić-Heinemann R, Kvascev GS, Andrić V. Non-destructive characterisation and classification of ceramic artefacts using pEDXRF and statistical pattern recognition. in Chemistry Central Journal. 2012;6. doi:10.1186/1752-153X-6-102 .
Gajić-Kvaščev, Maja, Marić-Stojanović, Milica, Jančić-Heinemann, Radmila, Kvascev, Goran S., Andrić, Velibor, "Non-destructive characterisation and classification of ceramic artefacts using pEDXRF and statistical pattern recognition" in Chemistry Central Journal, 6 (2012), https://doi.org/10.1186/1752-153X-6-102 . .