Background considerations in the analysis of PIXE spectra by Artificial Neural Systems.

19th Chilean Physics Symposium 2014

Correa, R.^1 ; Morales, J.R.^2 ; Requena, I.^3 ; Miranda, J.^4 ; Barrera, V.A.^4

Universidad Tecnológica Metropolitana, Departamento de Física, Av. José Pedro Alessandri, Ñuñoa Santiago

1242, Chile^1

Universidad de Chile, Facultad de Ciencias, Departamento de Física, Las Palmeras 3425, Ñuñoa Santiago, Chile^2

Universidad de Granada, Departamento de Ciencias de la Computación e Inteligencia Artificial, Daniel Saucedo Aranda s/n, Granada

18071, Spain^3

Universidad Nacional Autónoma de México, Instituto de Física, Ap. Postal 20-364, Mexico. D. F.

010000, Mexico^4

关键词: Elemental concentrations;    Intrinsic characteristics;    Mexico City;    Neural systems;    Normalized values;    Number of samples;    Reduce time;    Santiago , Chile;   

Others  :  https://iopscience.iop.org/article/10.1088/1742-6596/720/1/012053/pdf
DOI  :  10.1088/1742-6596/720/1/012053

来源: IOP

【 摘 要 】

In order to study the importance of background in PIXE spectra to determine elemental concentrations in atmospheric aerosols using artificial neural systems ANS, two independently trained ANS were constructed, one which considered as input the net number of counts in the peak, and another which included the background. In the training and validation phases thirty eight spectra of aerosols collected in Santiago, Chile, were used. In both cases the elemental concentration values were similar. This fact was due to the intrinsic characteristic of ANS operating with normalized values of the net and total number of counts under the peaks, something that was verified in the analysis of 172 spectra obtained from aerosols collected in Mexico city. Therefore, networks operating under the mode which include background can reduce time and cost when dealing with large number of samples.