Artificial Neural Network Approach to Modelling of Metal Contents in Different Types of Chocolates
Nema prikaza
Autori
Podunavac-Kuzmanović, SanjaJevrić, Lidija
Svarc-Gajić, Jaroslava
Kovacević, Strahinja
Vasiljević, Ivana
Kecojević, Isidora
Ivanović, Evica
Članak u časopisu (Objavljena verzija)
Metapodaci
Prikaz svih podataka o dokumentuApstrakt
The relationships between the contents of various metals (Cu, Ni, Pb and Al) in different types of chocolates were studied using chemometric approach. Chemometric analysis was based on the application of artificial neural networks (ANN). ANN was performed in order to select the significant models for predicting the metal contents. ANN equations that represent the content of one metal as a function of the contents of other metals were established. The statistical quality of the generated mathematical models was determined by standard statistical measures and cross-validation parameters. High agreement between experimental and predicted values, obtained in the validation procedure, indicated the good quality of the models. The obtained results indicate the possibility of predicting the metal contents in different types of chocolate and define the strong non-linear relationship between metal contents.
Ključne reči:
Chocolate / chemometric analysis / artificial neural networks / metal contentIzvor:
Acta Chimica Slovenica, 2015, 62, 1, 190-195Izdavač:
- Slovensko Kemijsko Drustvo, Ljubljana
Finansiranje / projekti:
- Provincial Secretariat for Science and Technological Development of Vojvodina [114-451-3593/2013-04]
- Pristupi održivosti i zelene hemije u razvoju ekološki pogodnih analitičkih metoda i skladištenju energije (RS-MESTD-Basic Research (BR or ON)-172012)
- Dizajniranje, sinteza, karakterizacija i procena praktične primene koordinacionih i organometalnih jedinjenja (RS-MESTD-Basic Research (BR or ON)-172014)
Institucija/grupa
Poljoprivredni fakultetTY - JOUR AU - Podunavac-Kuzmanović, Sanja AU - Jevrić, Lidija AU - Svarc-Gajić, Jaroslava AU - Kovacević, Strahinja AU - Vasiljević, Ivana AU - Kecojević, Isidora AU - Ivanović, Evica PY - 2015 UR - http://aspace.agrif.bg.ac.rs/handle/123456789/3795 AB - The relationships between the contents of various metals (Cu, Ni, Pb and Al) in different types of chocolates were studied using chemometric approach. Chemometric analysis was based on the application of artificial neural networks (ANN). ANN was performed in order to select the significant models for predicting the metal contents. ANN equations that represent the content of one metal as a function of the contents of other metals were established. The statistical quality of the generated mathematical models was determined by standard statistical measures and cross-validation parameters. High agreement between experimental and predicted values, obtained in the validation procedure, indicated the good quality of the models. The obtained results indicate the possibility of predicting the metal contents in different types of chocolate and define the strong non-linear relationship between metal contents. PB - Slovensko Kemijsko Drustvo, Ljubljana T2 - Acta Chimica Slovenica T1 - Artificial Neural Network Approach to Modelling of Metal Contents in Different Types of Chocolates EP - 195 IS - 1 SP - 190 VL - 62 UR - https://hdl.handle.net/21.15107/rcub_agrospace_3795 ER -
@article{ author = "Podunavac-Kuzmanović, Sanja and Jevrić, Lidija and Svarc-Gajić, Jaroslava and Kovacević, Strahinja and Vasiljević, Ivana and Kecojević, Isidora and Ivanović, Evica", year = "2015", abstract = "The relationships between the contents of various metals (Cu, Ni, Pb and Al) in different types of chocolates were studied using chemometric approach. Chemometric analysis was based on the application of artificial neural networks (ANN). ANN was performed in order to select the significant models for predicting the metal contents. ANN equations that represent the content of one metal as a function of the contents of other metals were established. The statistical quality of the generated mathematical models was determined by standard statistical measures and cross-validation parameters. High agreement between experimental and predicted values, obtained in the validation procedure, indicated the good quality of the models. The obtained results indicate the possibility of predicting the metal contents in different types of chocolate and define the strong non-linear relationship between metal contents.", publisher = "Slovensko Kemijsko Drustvo, Ljubljana", journal = "Acta Chimica Slovenica", title = "Artificial Neural Network Approach to Modelling of Metal Contents in Different Types of Chocolates", pages = "195-190", number = "1", volume = "62", url = "https://hdl.handle.net/21.15107/rcub_agrospace_3795" }
Podunavac-Kuzmanović, S., Jevrić, L., Svarc-Gajić, J., Kovacević, S., Vasiljević, I., Kecojević, I.,& Ivanović, E.. (2015). Artificial Neural Network Approach to Modelling of Metal Contents in Different Types of Chocolates. in Acta Chimica Slovenica Slovensko Kemijsko Drustvo, Ljubljana., 62(1), 190-195. https://hdl.handle.net/21.15107/rcub_agrospace_3795
Podunavac-Kuzmanović S, Jevrić L, Svarc-Gajić J, Kovacević S, Vasiljević I, Kecojević I, Ivanović E. Artificial Neural Network Approach to Modelling of Metal Contents in Different Types of Chocolates. in Acta Chimica Slovenica. 2015;62(1):190-195. https://hdl.handle.net/21.15107/rcub_agrospace_3795 .
Podunavac-Kuzmanović, Sanja, Jevrić, Lidija, Svarc-Gajić, Jaroslava, Kovacević, Strahinja, Vasiljević, Ivana, Kecojević, Isidora, Ivanović, Evica, "Artificial Neural Network Approach to Modelling of Metal Contents in Different Types of Chocolates" in Acta Chimica Slovenica, 62, no. 1 (2015):190-195, https://hdl.handle.net/21.15107/rcub_agrospace_3795 .