Analysis of 7 Be behaviour in the air by using a multilayer perceptron neural network

Samolov, Aleksandra; Dragović, S.; Daković, Marko; Bačić, Goran

doi:10.1016/j.jenvrad.2014.07.016

Cited by 6 publications

(5 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The over all cor re la tion co ef fi cient be tween exper i men tally ob tained spe cific ac tiv i ties and cal culated (pre dicted) val ues was low (0.20) in di cat ing that our model can not cor rectly fore cast 137 Cs ac tiv ity. This is a very dif fer ent sit u a tion than for cosmogenic 7 Be where a rather good cor re la tion of r = 0.91 has been ob tained us ing the same meth od ol ogy [20]. This is prob a bly due to the fact that val ues of all in di vid ual cor re la tion co ef fi cients are rather low (tab.…”

Section: Discussionmentioning

confidence: 88%

“…Ben e fits of us ing PCA/ANN meth ods in forecast ing can not be seen when cor re la tion co ef fi cients for in di vid ual me te o ro log i cal pa ram e ters and spe cific ac tiv i ties of 137 Cs are low. How ever, this method has been found to be use ful in cases of fore cast ing con centra tion lev els of other air borne radionuclides such as 7 Be and 3 H and air pol lut ants [20,37,38] and us ing PCA/ANN seems to be the only way ana lyse mul ti ple pa ram e ters and un known an a lyt i cal re la tion ships.…”

Section: Discussionmentioning

confidence: 99%

“…In this study we mea sured spe cific ac tiv i ties of 137 Cs in near-ground air and cor re lated them with lo cal me te o ro log i cal con di tions since those have the greatest in flu ence on the sta bil ity of the ground layer of atmo sphere. Sim i lar to our pre vi ous study on 7 Be [20], we tested the abil ity of ANN to pre dict spe cific ac tiv ities of 137 Cs in near-ground air by us ing me te o ro log ical pa ram e ters as in put.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Neural networks in analysing 137Cs behaviour in the air in the Belgrade area

Samolov

Dragović²,

Daković

et al. 2014

NUCL TECH RAD PROT

View full text Add to dashboard Cite

The application of the principal component analysis and artificial neural network method in forecasting 137Cs behaviour in the air as the function of meteorological parameters is presented. The model was optimized and tested using 137Cs specific activities obtained by standard gamma-ray spectrometric analysis of air samples collected in Belgrade (Serbia) during 2009-2011 and meteorological data for the same period. Low correlation (r = 0.20) between experimental values of 137Cs specific activities and those predicted by artificial neural network was obtained. This suggests that artificial neural network in the case of prediction of 137Cs specific activity, using temperature, insolation, and global Sun warming does not perform well, which can be explained by the relative independence of 137Cs specific activity of particular meteorological parameters and not by the ineffectiveness of artificial neural network in relating these parameters in general. [Projekat Ministarstva nauke Republike Srbije, br. TR34034]

show abstract

Section: Discussionmentioning

confidence: 88%

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Neural networks in analysing 137Cs behaviour in the air in the Belgrade area

Samolov

Dragović²,

Daković

et al. 2014

NUCL TECH RAD PROT

View full text Add to dashboard Cite

show abstract

“…The risk assessment program was a type of deep neural network (DNN) model developed using the multilayer perceptron (MLP) method [ 9 ], and built with the R Language ( https://www.r-project.org/ ). The response variable of the model was in binary form (outbreak/non-outbreak).…”

Section: Methodsmentioning

confidence: 99%

Risk Assessment Program of Highly Pathogenic Avian Influenza with Deep Learning Algorithm

Yoon

Jang

Jung

et al. 2020

Osong Public Health Res Perspect

View full text Add to dashboard Cite

This study presents the development and validation of a risk assessment program of highly pathogenic avian influenza (HPAI). This program was developed by the Korean government (Animal and Plant Quarantine Agency) and a private corporation (Korea Telecom, KT), using a national database (Korean animal health integrated system, KAHIS). Methods: Our risk assessment program was developed using the multilayer perceptron method using R Language. HPAI outbreaks on 544 poultry farms (307 with H5N6, and 237 with H5N8) that had available visit records of livestock-related vehicles amongst the 812 HPAI outbreaks that were confirmed between January 2014 and June 2017 were involved in this study. Results: After 140,000 iterations without drop-out, a model with 3 hidden layers and 10 nodes per layer, were selected. The activation function of the model was hyperbolic tangent. Precision and recall of the test gave F1 measures of 0.41, 0.68 and 0.51, respectively, at validation. The predicted risk values were higher for the "outbreak" (average ± SD, 0.20 ± 0.31) than "non-outbreak" (0.18 ± 0.30) farms (p < 0.001). Conclusion: The risk assessment model developed was employed during the epidemics of 2016/2017 (pilot version) and 2017/2018 (complementary version). This risk assessment model enhanced risk management activities by enabling preemptive control measures to prevent the spread of diseases.

show abstract

“…[24][25][26] A multilayer perceptron (MLP) is a feedforward articial neural network model that maps sets of input data onto a set of appropriate outputs. 27 An MLP consists of three parts, which are the input layer, hidden layer and output layer. Fig.…”

Section: Ensemble Learning Prediction Modelmentioning

confidence: 99%