Review of the article „A Bayesian Regularized Artificial Neural Network for Simultaneous Determination of Loratadine, Naproxen And Diclofenac in wastewaters“, verified by Publons, Web of Science
Članak u časopisu (Recenzirana verzija)
Metapodaci
Prikaz svih podataka o dokumentuApstrakt
Simultaneous determination of medication components in pharmaceutical samples using
ordinary methods have some difficulties. Chemometric methods are effective ways to
analyses several components simultaneously. In this paper a novel approach based on
Bayesian regularized artificial neural network (BRANN) is developed for determination of
Loratadine, Naproxen and Diclofenac in water using UV-Vis spectroscopy. A dataset is
collected by performing several chemical experiments and recording the UV-Vis spectra and
actual constituent values. The effect of different number of neuron in hidden layer was
analyzed based on final mean square error, and the optimum number was selected. Principle
Component Analysis (PCA) was also applied on the data. Other back-propagation methods,
such as Levenberg-Marquardt, scaled conjugate gradient and resilient backpropagation are
tested. The results showed that bayesian regularization algorithm has the best performance
among other methods. In order... to see the proposed network performance, it was performed
on two cross-validation methods, namely partitioning data into train and test parts, and leaveone-
out technique. Mean square errors between expected results and predicted ones implied
that the proposed method has a strong ability in predicting the expected values.
Izvor:
Current Pharmaceutical Analysis, 2019, 1/BMS-CPA-2019-24-20Kolekcije
Institucija/grupa
Mašinski fakultetTY - JOUR AU - Jovanović, Tamara PY - 2019 UR - https://machinery.mas.bg.ac.rs/handle/123456789/5927 AB - Simultaneous determination of medication components in pharmaceutical samples using ordinary methods have some difficulties. Chemometric methods are effective ways to analyses several components simultaneously. In this paper a novel approach based on Bayesian regularized artificial neural network (BRANN) is developed for determination of Loratadine, Naproxen and Diclofenac in water using UV-Vis spectroscopy. A dataset is collected by performing several chemical experiments and recording the UV-Vis spectra and actual constituent values. The effect of different number of neuron in hidden layer was analyzed based on final mean square error, and the optimum number was selected. Principle Component Analysis (PCA) was also applied on the data. Other back-propagation methods, such as Levenberg-Marquardt, scaled conjugate gradient and resilient backpropagation are tested. The results showed that bayesian regularization algorithm has the best performance among other methods. In order to see the proposed network performance, it was performed on two cross-validation methods, namely partitioning data into train and test parts, and leaveone- out technique. Mean square errors between expected results and predicted ones implied that the proposed method has a strong ability in predicting the expected values. T2 - Current Pharmaceutical Analysis T1 - Review of the article „A Bayesian Regularized Artificial Neural Network for Simultaneous Determination of Loratadine, Naproxen And Diclofenac in wastewaters“, verified by Publons, Web of Science EP - 20 SP - 1/BMS-CPA-2019-24 UR - https://hdl.handle.net/21.15107/rcub_machinery_5927 ER -
@article{ author = "Jovanović, Tamara", year = "2019", abstract = "Simultaneous determination of medication components in pharmaceutical samples using ordinary methods have some difficulties. Chemometric methods are effective ways to analyses several components simultaneously. In this paper a novel approach based on Bayesian regularized artificial neural network (BRANN) is developed for determination of Loratadine, Naproxen and Diclofenac in water using UV-Vis spectroscopy. A dataset is collected by performing several chemical experiments and recording the UV-Vis spectra and actual constituent values. The effect of different number of neuron in hidden layer was analyzed based on final mean square error, and the optimum number was selected. Principle Component Analysis (PCA) was also applied on the data. Other back-propagation methods, such as Levenberg-Marquardt, scaled conjugate gradient and resilient backpropagation are tested. The results showed that bayesian regularization algorithm has the best performance among other methods. In order to see the proposed network performance, it was performed on two cross-validation methods, namely partitioning data into train and test parts, and leaveone- out technique. Mean square errors between expected results and predicted ones implied that the proposed method has a strong ability in predicting the expected values.", journal = "Current Pharmaceutical Analysis", title = "Review of the article „A Bayesian Regularized Artificial Neural Network for Simultaneous Determination of Loratadine, Naproxen And Diclofenac in wastewaters“, verified by Publons, Web of Science", pages = "20-1/BMS-CPA-2019-24", url = "https://hdl.handle.net/21.15107/rcub_machinery_5927" }
Jovanović, T.. (2019). Review of the article „A Bayesian Regularized Artificial Neural Network for Simultaneous Determination of Loratadine, Naproxen And Diclofenac in wastewaters“, verified by Publons, Web of Science. in Current Pharmaceutical Analysis, 1/BMS-CPA-2019-24-20. https://hdl.handle.net/21.15107/rcub_machinery_5927
Jovanović T. Review of the article „A Bayesian Regularized Artificial Neural Network for Simultaneous Determination of Loratadine, Naproxen And Diclofenac in wastewaters“, verified by Publons, Web of Science. in Current Pharmaceutical Analysis. 2019;:1/BMS-CPA-2019-24-20. https://hdl.handle.net/21.15107/rcub_machinery_5927 .
Jovanović, Tamara, "Review of the article „A Bayesian Regularized Artificial Neural Network for Simultaneous Determination of Loratadine, Naproxen And Diclofenac in wastewaters“, verified by Publons, Web of Science" in Current Pharmaceutical Analysis (2019):1/BMS-CPA-2019-24-20, https://hdl.handle.net/21.15107/rcub_machinery_5927 .