Multivariate data analysis methods were used to recognize and classify soils of unknown geographic origin. A total of 103 soil samples were differentiated into classes, according to regions in Serbia and Montenegro from which they were collected. Their radionuclide (Ra-226, U-238, U-235, K-40, Cs-134, Cs-137, Th-232 and Be-7) activities detected by gamma-ray spectrometry were then used as the inputs in different pattern recognition methods. For the classification of soil samples using eight selected radionuclides, the prediction ability of linear discriminant analysis (LDA), k-nearest neighbours (kNN), soft independent modelling of class analogy (SIMCA) and artificial neural network (ANN) were 82.8%, 88.6%, 60.0% and 92.1%, respectively.
TY - JOUR
AU - Dragović, Snežana
AU - Onjia, Antonije
PY - 2007
UR - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/1121
AB - Multivariate data analysis methods were used to recognize and classify soils of unknown geographic origin. A total of 103 soil samples were differentiated into classes, according to regions in Serbia and Montenegro from which they were collected. Their radionuclide (Ra-226, U-238, U-235, K-40, Cs-134, Cs-137, Th-232 and Be-7) activities detected by gamma-ray spectrometry were then used as the inputs in different pattern recognition methods. For the classification of soil samples using eight selected radionuclides, the prediction ability of linear discriminant analysis (LDA), k-nearest neighbours (kNN), soft independent modelling of class analogy (SIMCA) and artificial neural network (ANN) were 82.8%, 88.6%, 60.0% and 92.1%, respectively.
PB - Pergamon-Elsevier Science Ltd, Oxford
T2 - Applied Radiation and Isotopes
T1 - Classification of soil samples according to geographic origin using gamma-ray spectrometry and pattern recognition methods
EP - 224
IS - 2
SP - 218
VL - 65
DO - 10.1016/j.apradiso.2006.07.005
ER -
@article{
author = "Dragović, Snežana and Onjia, Antonije",
year = "2007",
abstract = "Multivariate data analysis methods were used to recognize and classify soils of unknown geographic origin. A total of 103 soil samples were differentiated into classes, according to regions in Serbia and Montenegro from which they were collected. Their radionuclide (Ra-226, U-238, U-235, K-40, Cs-134, Cs-137, Th-232 and Be-7) activities detected by gamma-ray spectrometry were then used as the inputs in different pattern recognition methods. For the classification of soil samples using eight selected radionuclides, the prediction ability of linear discriminant analysis (LDA), k-nearest neighbours (kNN), soft independent modelling of class analogy (SIMCA) and artificial neural network (ANN) were 82.8%, 88.6%, 60.0% and 92.1%, respectively.",
publisher = "Pergamon-Elsevier Science Ltd, Oxford",
journal = "Applied Radiation and Isotopes",
title = "Classification of soil samples according to geographic origin using gamma-ray spectrometry and pattern recognition methods",
pages = "224-218",
number = "2",
volume = "65",
doi = "10.1016/j.apradiso.2006.07.005"
}
Dragović, S.,& Onjia, A.. (2007). Classification of soil samples according to geographic origin using gamma-ray spectrometry and pattern recognition methods. in Applied Radiation and Isotopes
Pergamon-Elsevier Science Ltd, Oxford., 65(2), 218-224.
https://doi.org/10.1016/j.apradiso.2006.07.005
Dragović S, Onjia A. Classification of soil samples according to geographic origin using gamma-ray spectrometry and pattern recognition methods. in Applied Radiation and Isotopes. 2007;65(2):218-224.
doi:10.1016/j.apradiso.2006.07.005 .
Dragović, Snežana, Onjia, Antonije, "Classification of soil samples according to geographic origin using gamma-ray spectrometry and pattern recognition methods" in Applied Radiation and Isotopes, 65, no. 2 (2007):218-224,
https://doi.org/10.1016/j.apradiso.2006.07.005 . .
