Support vector machines for classification of soils according to geographic origin based on their radionuclide content
Апстракт
The paper introduces support vector machines
(SVM), a recent method in statistical learning theory, used to recognize
and classify soils according to their geographic origin. The classification
was performed based on activities of seven radionuclides determined by
gamma-ray spectrometry. The radionuclides of uranium and thorium
series (226Ra, 232Th, 235U, 238U) and 40K were used to differentiate
investigated areas based on geology, while cosmogenic beryllium (
7
Be)
and anthropogenic 137Cs were used to differentiate areas according to
their susceptibility to fallout. The performances of the proposed method
was compared to those of principal component analysis (PCA), linear
discriminant analysis (LDA), k-nearest neighbours (kNN), soft
independent modelling of class analogy (SIMCA) and artificial neural
networks (ANN) applied to the same dataset.
Кључне речи:
Chemometrics / Lithology / Fallout / Prediction abilityИзвор:
Serbian Journal of Geosciences, 2018, 4, 1, 15-26Издавач:
- Department of Geography, Faculty of Sciences, University of Niš
Финансирање / пројекти:
- Нове технологије за мониторинг и заштиту животног окружења од штетних хемијских супстанци и радијационог оптерећења (RS-MESTD-Integrated and Interdisciplinary Research (IIR or III)-43009)
Институција/група
Tehnološko-metalurški fakultetTY - JOUR AU - Dragović, Snežana AU - Kovačević, Miloš AU - Bajat, Branislav AU - Onjia, Antonije PY - 2018 UR - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/7109 AB - The paper introduces support vector machines (SVM), a recent method in statistical learning theory, used to recognize and classify soils according to their geographic origin. The classification was performed based on activities of seven radionuclides determined by gamma-ray spectrometry. The radionuclides of uranium and thorium series (226Ra, 232Th, 235U, 238U) and 40K were used to differentiate investigated areas based on geology, while cosmogenic beryllium ( 7 Be) and anthropogenic 137Cs were used to differentiate areas according to their susceptibility to fallout. The performances of the proposed method was compared to those of principal component analysis (PCA), linear discriminant analysis (LDA), k-nearest neighbours (kNN), soft independent modelling of class analogy (SIMCA) and artificial neural networks (ANN) applied to the same dataset. PB - Department of Geography, Faculty of Sciences, University of Niš T2 - Serbian Journal of Geosciences T1 - Support vector machines for classification of soils according to geographic origin based on their radionuclide content EP - 26 IS - 1 SP - 15 VL - 4 UR - https://hdl.handle.net/21.15107/rcub_technorep_7109 ER -
@article{ author = "Dragović, Snežana and Kovačević, Miloš and Bajat, Branislav and Onjia, Antonije", year = "2018", abstract = "The paper introduces support vector machines (SVM), a recent method in statistical learning theory, used to recognize and classify soils according to their geographic origin. The classification was performed based on activities of seven radionuclides determined by gamma-ray spectrometry. The radionuclides of uranium and thorium series (226Ra, 232Th, 235U, 238U) and 40K were used to differentiate investigated areas based on geology, while cosmogenic beryllium ( 7 Be) and anthropogenic 137Cs were used to differentiate areas according to their susceptibility to fallout. The performances of the proposed method was compared to those of principal component analysis (PCA), linear discriminant analysis (LDA), k-nearest neighbours (kNN), soft independent modelling of class analogy (SIMCA) and artificial neural networks (ANN) applied to the same dataset.", publisher = "Department of Geography, Faculty of Sciences, University of Niš", journal = "Serbian Journal of Geosciences", title = "Support vector machines for classification of soils according to geographic origin based on their radionuclide content", pages = "26-15", number = "1", volume = "4", url = "https://hdl.handle.net/21.15107/rcub_technorep_7109" }
Dragović, S., Kovačević, M., Bajat, B.,& Onjia, A.. (2018). Support vector machines for classification of soils according to geographic origin based on their radionuclide content. in Serbian Journal of Geosciences Department of Geography, Faculty of Sciences, University of Niš., 4(1), 15-26. https://hdl.handle.net/21.15107/rcub_technorep_7109
Dragović S, Kovačević M, Bajat B, Onjia A. Support vector machines for classification of soils according to geographic origin based on their radionuclide content. in Serbian Journal of Geosciences. 2018;4(1):15-26. https://hdl.handle.net/21.15107/rcub_technorep_7109 .
Dragović, Snežana, Kovačević, Miloš, Bajat, Branislav, Onjia, Antonije, "Support vector machines for classification of soils according to geographic origin based on their radionuclide content" in Serbian Journal of Geosciences, 4, no. 1 (2018):15-26, https://hdl.handle.net/21.15107/rcub_technorep_7109 .