Implementation of neural networks for classification of moss and lichen samples on the basis of gamma-ray spectrometric analysis
Samo za registrovane korisnike
2007
Članak u časopisu (Objavljena verzija)
Metapodaci
Prikaz svih podataka o dokumentuApstrakt
Mosses and lichens have an important role in biomonitoring. The objective of this study is to develop a neural network model to classify these plants according to geographical origin. A three-layer feed-forward neural network was used. The activities of radionuclides (Ra-226, U-238, U-235, K-40, Th-232, Cs-134, Cs-137 and Be-7) detected in plant samples by gamma-ray spectrometry were used as inputs for neural network. Five different training algorithms with different number of samples in training sets were tested and compared, in order to find the one with the minimum root mean square error. The best predictive power for the classification of plants from 12 regions was achieved using a network with 5 hidden layer nodes and 3,000 training epochs, using the online back-propagation randomized training algorithm. Implementation of this model to experimental data resulted in satisfactory classification of moss and lichen samples in terms of their geographical origin. The average classificat...ion rate obtained in this study was (90.7 +/- 4.8)%.
Ključne reči:
biomonitoring / feed-forward neural network / geographical origin / lichens / mosses / radionuclidesIzvor:
Environmental Monitoring and Assessment, 2007, 130, 1-3, 245-253Izdavač:
- Springer, Dordrecht
Finansiranje / projekti:
- Nove metode i tehnike za separaciju i specijaciju hemijskih elemenata u tragovima, organskih supstanci i radionuklida i identifikaciju njihovih izvora (RS-MESTD-MPN2006-2010-142039)
DOI: 10.1007/s10661-006-9393-4
ISSN: 0167-6369
PubMed: 17057958
WoS: 000246732600022
Scopus: 2-s2.0-34249878734
Institucija/grupa
Tehnološko-metalurški fakultetTY - JOUR AU - Dragović, Snežana D. AU - Onjia, Antonije AU - Dragović, Ranko M. AU - Bacić, Goran PY - 2007 UR - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/1095 AB - Mosses and lichens have an important role in biomonitoring. The objective of this study is to develop a neural network model to classify these plants according to geographical origin. A three-layer feed-forward neural network was used. The activities of radionuclides (Ra-226, U-238, U-235, K-40, Th-232, Cs-134, Cs-137 and Be-7) detected in plant samples by gamma-ray spectrometry were used as inputs for neural network. Five different training algorithms with different number of samples in training sets were tested and compared, in order to find the one with the minimum root mean square error. The best predictive power for the classification of plants from 12 regions was achieved using a network with 5 hidden layer nodes and 3,000 training epochs, using the online back-propagation randomized training algorithm. Implementation of this model to experimental data resulted in satisfactory classification of moss and lichen samples in terms of their geographical origin. The average classification rate obtained in this study was (90.7 +/- 4.8)%. PB - Springer, Dordrecht T2 - Environmental Monitoring and Assessment T1 - Implementation of neural networks for classification of moss and lichen samples on the basis of gamma-ray spectrometric analysis EP - 253 IS - 1-3 SP - 245 VL - 130 DO - 10.1007/s10661-006-9393-4 ER -
@article{ author = "Dragović, Snežana D. and Onjia, Antonije and Dragović, Ranko M. and Bacić, Goran", year = "2007", abstract = "Mosses and lichens have an important role in biomonitoring. The objective of this study is to develop a neural network model to classify these plants according to geographical origin. A three-layer feed-forward neural network was used. The activities of radionuclides (Ra-226, U-238, U-235, K-40, Th-232, Cs-134, Cs-137 and Be-7) detected in plant samples by gamma-ray spectrometry were used as inputs for neural network. Five different training algorithms with different number of samples in training sets were tested and compared, in order to find the one with the minimum root mean square error. The best predictive power for the classification of plants from 12 regions was achieved using a network with 5 hidden layer nodes and 3,000 training epochs, using the online back-propagation randomized training algorithm. Implementation of this model to experimental data resulted in satisfactory classification of moss and lichen samples in terms of their geographical origin. The average classification rate obtained in this study was (90.7 +/- 4.8)%.", publisher = "Springer, Dordrecht", journal = "Environmental Monitoring and Assessment", title = "Implementation of neural networks for classification of moss and lichen samples on the basis of gamma-ray spectrometric analysis", pages = "253-245", number = "1-3", volume = "130", doi = "10.1007/s10661-006-9393-4" }
Dragović, S. D., Onjia, A., Dragović, R. M.,& Bacić, G.. (2007). Implementation of neural networks for classification of moss and lichen samples on the basis of gamma-ray spectrometric analysis. in Environmental Monitoring and Assessment Springer, Dordrecht., 130(1-3), 245-253. https://doi.org/10.1007/s10661-006-9393-4
Dragović SD, Onjia A, Dragović RM, Bacić G. Implementation of neural networks for classification of moss and lichen samples on the basis of gamma-ray spectrometric analysis. in Environmental Monitoring and Assessment. 2007;130(1-3):245-253. doi:10.1007/s10661-006-9393-4 .
Dragović, Snežana D., Onjia, Antonije, Dragović, Ranko M., Bacić, Goran, "Implementation of neural networks for classification of moss and lichen samples on the basis of gamma-ray spectrometric analysis" in Environmental Monitoring and Assessment, 130, no. 1-3 (2007):245-253, https://doi.org/10.1007/s10661-006-9393-4 . .