TY  - JOUR
AU  - Antanasijević, Davor
AU  - Pocajt, Viktor
AU  - Perić-Grujić, Aleksandra
AU  - Ristić, Mirjana
PY  - 2020
UR  - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/4574
AB  - In this study, a self-organizing network-based monitoring location similarity index (LSI) was coupled with Ward neural networks (WNNs) with the aim to create a more accurate, but less complex, multiple sites model for the prediction of dissolved oxygen (DO) content. This multilevel splitting approach comprises the LSI-based grouping of monitoring locations according to their similarity, and virtual splitting of processed data based on their features using WNN. The values of 18 water quality parameters monitored for 12 years at 17 sites on the Danube River flow thought Serbia were used. The optimal input combinations were selected using partial mutual information algorithm with termination based on the Akaike information criterion. LSI-based splitting has yielded two groups of monitoring sites that were modeled with separate WNN models. The number and types of selected inputs differed between those two groups of sites, which was in agreement with possible pollution sources. Multiple performance metrics have revealed that the WNN models perform similar or better than multisite DO prediction models published in the literature, while using two to four times less inputs and data patterns.
PB  - Springer London Ltd, London
T2  - Neural Computing & Applications
T1  - Multilevel split of high-dimensional water quality data using artificial neural networks for the prediction of dissolved oxygen in the Danube River
EP  - 3966
IS  - 8
SP  - 3957
VL  - 32
DO  - 10.1007/s00521-019-04079-y
ER  - 

@article{
author = "Antanasijević, Davor and Pocajt, Viktor and Perić-Grujić, Aleksandra and Ristić, Mirjana",
year = "2020",
abstract = "In this study, a self-organizing network-based monitoring location similarity index (LSI) was coupled with Ward neural networks (WNNs) with the aim to create a more accurate, but less complex, multiple sites model for the prediction of dissolved oxygen (DO) content. This multilevel splitting approach comprises the LSI-based grouping of monitoring locations according to their similarity, and virtual splitting of processed data based on their features using WNN. The values of 18 water quality parameters monitored for 12 years at 17 sites on the Danube River flow thought Serbia were used. The optimal input combinations were selected using partial mutual information algorithm with termination based on the Akaike information criterion. LSI-based splitting has yielded two groups of monitoring sites that were modeled with separate WNN models. The number and types of selected inputs differed between those two groups of sites, which was in agreement with possible pollution sources. Multiple performance metrics have revealed that the WNN models perform similar or better than multisite DO prediction models published in the literature, while using two to four times less inputs and data patterns.",
publisher = "Springer London Ltd, London",
journal = "Neural Computing & Applications",
title = "Multilevel split of high-dimensional water quality data using artificial neural networks for the prediction of dissolved oxygen in the Danube River",
pages = "3966-3957",
number = "8",
volume = "32",
doi = "10.1007/s00521-019-04079-y"
}

Antanasijević, D., Pocajt, V., Perić-Grujić, A.,& Ristić, M.. (2020). Multilevel split of high-dimensional water quality data using artificial neural networks for the prediction of dissolved oxygen in the Danube River. in Neural Computing & Applications
Springer London Ltd, London., 32(8), 3957-3966.
https://doi.org/10.1007/s00521-019-04079-y

Antanasijević D, Pocajt V, Perić-Grujić A, Ristić M. Multilevel split of high-dimensional water quality data using artificial neural networks for the prediction of dissolved oxygen in the Danube River. in Neural Computing & Applications. 2020;32(8):3957-3966.
doi:10.1007/s00521-019-04079-y .

Antanasijević, Davor, Pocajt, Viktor, Perić-Grujić, Aleksandra, Ristić, Mirjana, "Multilevel split of high-dimensional water quality data using artificial neural networks for the prediction of dissolved oxygen in the Danube River" in Neural Computing & Applications, 32, no. 8 (2020):3957-3966,
https://doi.org/10.1007/s00521-019-04079-y . .

TY  - JOUR
AU  - Jevremović, Nenad
AU  - Kalagasidis Krušić, Melina
AU  - Antanasijević, Davor
AU  - Popović, Ivanka
PY  - 2019
UR  - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/4093
AB  - Nowadays, the extensive use of pesticides in crops production puts a significant challenge to minimize its side effects along with safe production, storage, and after-use treatment. This paper reports results related to the emission of certain pesticide formulations through the PET containers, as well as, their mitigation to the PET containers during their storage. The influence of storage time on cypermethrin migration to and through the PET was studied in short-term Collaborative International Pesticides Analytical Council test lasting up to 30 days. The PET containers were filled with pure xylene and pesticide formulations, where the amount of active substance, cypermethrin (CY), varied from 5 to 20 wt%, while the amount of emulsifier was kept constant. The results indicate that pesticide formulations diffuse to PET containers with an average increase of its initial mass up to 1.5%. The most intensive diffusion is in the first 24 months of storage, after its rate significantly decreases. It should be noted that the diffusion studied pesticide formulations are also very dependent on CY concentration. Besides the migration to the PET containers, it was also found that pesticide formulation was emitted through the PET containers in the first 17 to 24 months of storage depending on CY concentration. Emission rates were also dependent on CY concentration and were in the range of 15.3 to 38.0 mg/month center dot container. The emission through the PETcontainers was successfully predicted using artificial neural networks with R-2 = 0.94 and the mean absolute percentage error (MAPE) of only 6.2% on testing.
PB  - Springer Verlag
T2  - Environmental Science and Pollution Research
T1  - Migration of cypermethrin to and through the PET containers and artificial neural network-based estimation of its emission
EP  - 28939
IS  - 28
SP  - 28933
VL  - 26
DO  - 10.1007/s11356-019-06108-8
ER  - 

@article{
author = "Jevremović, Nenad and Kalagasidis Krušić, Melina and Antanasijević, Davor and Popović, Ivanka",
year = "2019",
abstract = "Nowadays, the extensive use of pesticides in crops production puts a significant challenge to minimize its side effects along with safe production, storage, and after-use treatment. This paper reports results related to the emission of certain pesticide formulations through the PET containers, as well as, their mitigation to the PET containers during their storage. The influence of storage time on cypermethrin migration to and through the PET was studied in short-term Collaborative International Pesticides Analytical Council test lasting up to 30 days. The PET containers were filled with pure xylene and pesticide formulations, where the amount of active substance, cypermethrin (CY), varied from 5 to 20 wt%, while the amount of emulsifier was kept constant. The results indicate that pesticide formulations diffuse to PET containers with an average increase of its initial mass up to 1.5%. The most intensive diffusion is in the first 24 months of storage, after its rate significantly decreases. It should be noted that the diffusion studied pesticide formulations are also very dependent on CY concentration. Besides the migration to the PET containers, it was also found that pesticide formulation was emitted through the PET containers in the first 17 to 24 months of storage depending on CY concentration. Emission rates were also dependent on CY concentration and were in the range of 15.3 to 38.0 mg/month center dot container. The emission through the PETcontainers was successfully predicted using artificial neural networks with R-2 = 0.94 and the mean absolute percentage error (MAPE) of only 6.2% on testing.",
publisher = "Springer Verlag",
journal = "Environmental Science and Pollution Research",
title = "Migration of cypermethrin to and through the PET containers and artificial neural network-based estimation of its emission",
pages = "28939-28933",
number = "28",
volume = "26",
doi = "10.1007/s11356-019-06108-8"
}

Jevremović, N., Kalagasidis Krušić, M., Antanasijević, D.,& Popović, I.. (2019). Migration of cypermethrin to and through the PET containers and artificial neural network-based estimation of its emission. in Environmental Science and Pollution Research
Springer Verlag., 26(28), 28933-28939.
https://doi.org/10.1007/s11356-019-06108-8

Jevremović N, Kalagasidis Krušić M, Antanasijević D, Popović I. Migration of cypermethrin to and through the PET containers and artificial neural network-based estimation of its emission. in Environmental Science and Pollution Research. 2019;26(28):28933-28939.
doi:10.1007/s11356-019-06108-8 .

Jevremović, Nenad, Kalagasidis Krušić, Melina, Antanasijević, Davor, Popović, Ivanka, "Migration of cypermethrin to and through the PET containers and artificial neural network-based estimation of its emission" in Environmental Science and Pollution Research, 26, no. 28 (2019):28933-28939,
https://doi.org/10.1007/s11356-019-06108-8 . .

TY  - JOUR
AU  - Mitrović, Tatjana
AU  - Antanasijević, Davor
AU  - Lazović, Saša
AU  - Perić-Grujić, Aleksandra
AU  - Ristić, Mirjana
PY  - 2019
UR  - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/4303
AB  - Rationalization of water quality monitoring stations nowadays is applied in many countries. In some cases, missing data from abandoned/inactive stations, spatial and temporal, could be very important, hence the use of artificial neural networks (ANNs) for virtual water quality monitoring at inactive monitoring sites was investigated. The aim was to develop single-output and simultaneous ANNs for the spatial interpolation of 18 water quality parameters at single- and multi-inactive monitoring sites on Danube River course through Serbia. Those different modeling approaches were considered in order to determine the most suitable combination of models. The variable selection and sensitivity analysis in the case of simultaneous models were performed using a modified procedure based on Monte Carlo Simulations (MCS). In general, the multi-target models tend to be more accurate than single target ones, while single output models outperform the simultaneous ones. Hence, for particular monitoring network and set of water quality parameters the optimal combination of models must be defined based on model's accuracy and computational effort needed. The MCS selection procedure has proved to be efficient only in the case of simultaneous multi-target model. MCS based analysis of input-output interactions has shown all significant interactions in the case of simultaneous single-target are grouped as a complex duster of interactions, where majority of inputs influence on several outputs. In the case multi-target model those interactions were portioned in five separate clusters, there majority of them mimic the input-output interactions that are present in single output models. The modeling strategy for study area was proposed on the basis of the performance of created models (mean average percentage error  lt  10%): simultaneous multi-target model for pH, alkalinity, conductivity, hardness, dissolved oxygen, HCO3-,SO42- and Ca, single-output multi-target models for temperature and Cl-, simultaneous single-target models for Mg and CO2, single output single target models for NO3-.
PB  - Elsevier Science Bv, Amsterdam
T2  - Science of the Total Environment
T1  - Virtual water quality monitoring at inactive monitoring sites using Monte Carlo optimized artificial neural networks: A case study of Danube River (Serbia)
EP  - 1009
SP  - 1000
VL  - 654
DO  - 10.1016/j.scitotenv.2018.11.189
ER  - 

@article{
author = "Mitrović, Tatjana and Antanasijević, Davor and Lazović, Saša and Perić-Grujić, Aleksandra and Ristić, Mirjana",
year = "2019",
abstract = "Rationalization of water quality monitoring stations nowadays is applied in many countries. In some cases, missing data from abandoned/inactive stations, spatial and temporal, could be very important, hence the use of artificial neural networks (ANNs) for virtual water quality monitoring at inactive monitoring sites was investigated. The aim was to develop single-output and simultaneous ANNs for the spatial interpolation of 18 water quality parameters at single- and multi-inactive monitoring sites on Danube River course through Serbia. Those different modeling approaches were considered in order to determine the most suitable combination of models. The variable selection and sensitivity analysis in the case of simultaneous models were performed using a modified procedure based on Monte Carlo Simulations (MCS). In general, the multi-target models tend to be more accurate than single target ones, while single output models outperform the simultaneous ones. Hence, for particular monitoring network and set of water quality parameters the optimal combination of models must be defined based on model's accuracy and computational effort needed. The MCS selection procedure has proved to be efficient only in the case of simultaneous multi-target model. MCS based analysis of input-output interactions has shown all significant interactions in the case of simultaneous single-target are grouped as a complex duster of interactions, where majority of inputs influence on several outputs. In the case multi-target model those interactions were portioned in five separate clusters, there majority of them mimic the input-output interactions that are present in single output models. The modeling strategy for study area was proposed on the basis of the performance of created models (mean average percentage error  lt  10%): simultaneous multi-target model for pH, alkalinity, conductivity, hardness, dissolved oxygen, HCO3-,SO42- and Ca, single-output multi-target models for temperature and Cl-, simultaneous single-target models for Mg and CO2, single output single target models for NO3-.",
publisher = "Elsevier Science Bv, Amsterdam",
journal = "Science of the Total Environment",
title = "Virtual water quality monitoring at inactive monitoring sites using Monte Carlo optimized artificial neural networks: A case study of Danube River (Serbia)",
pages = "1009-1000",
volume = "654",
doi = "10.1016/j.scitotenv.2018.11.189"
}

Mitrović, T., Antanasijević, D., Lazović, S., Perić-Grujić, A.,& Ristić, M.. (2019). Virtual water quality monitoring at inactive monitoring sites using Monte Carlo optimized artificial neural networks: A case study of Danube River (Serbia). in Science of the Total Environment
Elsevier Science Bv, Amsterdam., 654, 1000-1009.
https://doi.org/10.1016/j.scitotenv.2018.11.189

Mitrović T, Antanasijević D, Lazović S, Perić-Grujić A, Ristić M. Virtual water quality monitoring at inactive monitoring sites using Monte Carlo optimized artificial neural networks: A case study of Danube River (Serbia). in Science of the Total Environment. 2019;654:1000-1009.
doi:10.1016/j.scitotenv.2018.11.189 .

Mitrović, Tatjana, Antanasijević, Davor, Lazović, Saša, Perić-Grujić, Aleksandra, Ristić, Mirjana, "Virtual water quality monitoring at inactive monitoring sites using Monte Carlo optimized artificial neural networks: A case study of Danube River (Serbia)" in Science of the Total Environment, 654 (2019):1000-1009,
https://doi.org/10.1016/j.scitotenv.2018.11.189 . .

TY  - JOUR
AU  - Radojević, Darinka
AU  - Antanasijević, Davor
AU  - Perić-Grujić, Aleksandra
AU  - Ristić, Mirjana
AU  - Pocajt, Viktor
PY  - 2019
UR  - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/4315
AB  - In recent decades, artificial neural networks (ANNs) have been used for the prediction of concentration of air pollutants in urban areas. Beside meteorological variables, periodic parameters, such as hour of the day or month of the year, have been frequently used to improve the performance of ANN models by representing variations of emission sources. In this paper, different forms of periodic parameters, i.e. smoothed cosines based approximation and normalized historical mean values, were combined with meteorological variables in order to analyze the sensitivity of the ANN model to them. Ward neural network and general regression neural network were used and compared for the prediction of daily average concentrations of SO2 and NOx in Belgrade, Serbia. Multiple performance metrics have demonstrated that models based on periodic parameters outperform the corresponding models that used only meteorological variables as inputs. Also, a newly proposed normalized historical mean MOYnmv (month of the year) proved to be more appropriate in majority of cases than the traditional cosines based approximation (MOYcos). A simple rule for the selection of the most efficient MOY form was defined depending on their mutual correlation (r). Results have shown that if MOYnmv is correlated with MOYcos with r  gt  0.8, then ANN models what uses MOYnmv provide more accurate predictions.
PB  - Turkish Natl Committee Air Pollution Res & Control-Tuncap, Buca
T2  - Atmospheric Pollution Research
T1  - The significance of periodic parameters for ANN modeling of daily SO2 and NOx concentrations: A case study of Belgrade, Serbia
EP  - 628
IS  - 2
SP  - 621
VL  - 10
DO  - 10.1016/j.apr.2018.11.004
ER  - 

@article{
author = "Radojević, Darinka and Antanasijević, Davor and Perić-Grujić, Aleksandra and Ristić, Mirjana and Pocajt, Viktor",
year = "2019",
abstract = "In recent decades, artificial neural networks (ANNs) have been used for the prediction of concentration of air pollutants in urban areas. Beside meteorological variables, periodic parameters, such as hour of the day or month of the year, have been frequently used to improve the performance of ANN models by representing variations of emission sources. In this paper, different forms of periodic parameters, i.e. smoothed cosines based approximation and normalized historical mean values, were combined with meteorological variables in order to analyze the sensitivity of the ANN model to them. Ward neural network and general regression neural network were used and compared for the prediction of daily average concentrations of SO2 and NOx in Belgrade, Serbia. Multiple performance metrics have demonstrated that models based on periodic parameters outperform the corresponding models that used only meteorological variables as inputs. Also, a newly proposed normalized historical mean MOYnmv (month of the year) proved to be more appropriate in majority of cases than the traditional cosines based approximation (MOYcos). A simple rule for the selection of the most efficient MOY form was defined depending on their mutual correlation (r). Results have shown that if MOYnmv is correlated with MOYcos with r  gt  0.8, then ANN models what uses MOYnmv provide more accurate predictions.",
publisher = "Turkish Natl Committee Air Pollution Res & Control-Tuncap, Buca",
journal = "Atmospheric Pollution Research",
title = "The significance of periodic parameters for ANN modeling of daily SO2 and NOx concentrations: A case study of Belgrade, Serbia",
pages = "628-621",
number = "2",
volume = "10",
doi = "10.1016/j.apr.2018.11.004"
}

Radojević, D., Antanasijević, D., Perić-Grujić, A., Ristić, M.,& Pocajt, V.. (2019). The significance of periodic parameters for ANN modeling of daily SO2 and NOx concentrations: A case study of Belgrade, Serbia. in Atmospheric Pollution Research
Turkish Natl Committee Air Pollution Res & Control-Tuncap, Buca., 10(2), 621-628.
https://doi.org/10.1016/j.apr.2018.11.004

Radojević D, Antanasijević D, Perić-Grujić A, Ristić M, Pocajt V. The significance of periodic parameters for ANN modeling of daily SO2 and NOx concentrations: A case study of Belgrade, Serbia. in Atmospheric Pollution Research. 2019;10(2):621-628.
doi:10.1016/j.apr.2018.11.004 .

Radojević, Darinka, Antanasijević, Davor, Perić-Grujić, Aleksandra, Ristić, Mirjana, Pocajt, Viktor, "The significance of periodic parameters for ANN modeling of daily SO2 and NOx concentrations: A case study of Belgrade, Serbia" in Atmospheric Pollution Research, 10, no. 2 (2019):621-628,
https://doi.org/10.1016/j.apr.2018.11.004 . .

TY  - JOUR
AU  - Sekulić, Zoran
AU  - Antanasijević, Davor
AU  - Stevanović, Slavica
AU  - Trivunac, Katarina
PY  - 2019
UR  - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/4323
AB  - Membrane filtration techniques are distinguished among methods for wastewater treatment and fully correspond to the requirements of the green concept of chemistry and production. The limiting factor for greater application of these methods is the phenomenon of fouling and the decline of the permeate flux. In this study, polynomial neural network based on group method data handling (GMDH) algorithm was applied to predict the performance of the complexation-microfiltration process for the removal of Pb(II), Zn(II), and Cd(II) from synthetic wastewater. The influence of working parameters such as pH, initial concentration of metal ions, type of complexing agent, and pressure on flux was experimentally determined. The data obtained were used as input parameters for the GMDH model as well as for the multiple linear regression (MLR) model. Root mean square error (RMSE), mean absolute error (MAE), and mean absolute percent error (MAPE) were used for evaluation purposes. Results showed that the developed model has excellent performance in flux prediction with R-2 of 0.9648.
PB  - Springer International Publishing Ag, Cham
T2  - Water Air and Soil Pollution
T1  - The Prediction of Heavy Metal Permeate Flux in Complexation-Microfiltration Process: Polynomial Neural Network Approach
IS  - 1
VL  - 230
DO  - 10.1007/s11270-018-4072-y
ER  - 

@article{
author = "Sekulić, Zoran and Antanasijević, Davor and Stevanović, Slavica and Trivunac, Katarina",
year = "2019",
abstract = "Membrane filtration techniques are distinguished among methods for wastewater treatment and fully correspond to the requirements of the green concept of chemistry and production. The limiting factor for greater application of these methods is the phenomenon of fouling and the decline of the permeate flux. In this study, polynomial neural network based on group method data handling (GMDH) algorithm was applied to predict the performance of the complexation-microfiltration process for the removal of Pb(II), Zn(II), and Cd(II) from synthetic wastewater. The influence of working parameters such as pH, initial concentration of metal ions, type of complexing agent, and pressure on flux was experimentally determined. The data obtained were used as input parameters for the GMDH model as well as for the multiple linear regression (MLR) model. Root mean square error (RMSE), mean absolute error (MAE), and mean absolute percent error (MAPE) were used for evaluation purposes. Results showed that the developed model has excellent performance in flux prediction with R-2 of 0.9648.",
publisher = "Springer International Publishing Ag, Cham",
journal = "Water Air and Soil Pollution",
title = "The Prediction of Heavy Metal Permeate Flux in Complexation-Microfiltration Process: Polynomial Neural Network Approach",
number = "1",
volume = "230",
doi = "10.1007/s11270-018-4072-y"
}

Sekulić, Z., Antanasijević, D., Stevanović, S.,& Trivunac, K.. (2019). The Prediction of Heavy Metal Permeate Flux in Complexation-Microfiltration Process: Polynomial Neural Network Approach. in Water Air and Soil Pollution
Springer International Publishing Ag, Cham., 230(1).
https://doi.org/10.1007/s11270-018-4072-y

Sekulić Z, Antanasijević D, Stevanović S, Trivunac K. The Prediction of Heavy Metal Permeate Flux in Complexation-Microfiltration Process: Polynomial Neural Network Approach. in Water Air and Soil Pollution. 2019;230(1).
doi:10.1007/s11270-018-4072-y .

Sekulić, Zoran, Antanasijević, Davor, Stevanović, Slavica, Trivunac, Katarina, "The Prediction of Heavy Metal Permeate Flux in Complexation-Microfiltration Process: Polynomial Neural Network Approach" in Water Air and Soil Pollution, 230, no. 1 (2019),
https://doi.org/10.1007/s11270-018-4072-y . .

TY  - JOUR
AU  - Antanasijević, Davor
AU  - Pocajt, Viktor
AU  - Perić-Grujić, Aleksandra
AU  - Ristić, Mirjana
PY  - 2019
UR  - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/4331
AB  - Urban population exposure to tropospheric ozone is a serious health concern in Europe countries. Although there are insufficient evidence to derive a level below which ozone has no effect on mortality WHO (World Health Organization) uses SOMO35 (sum of means over 35 ppb) in their health impact assessments. Is this paper, the artificial neural network (ANN) approach was used to forecast SOMO35 at the national level for a set of 24 European countries, mostly EU members. Available ozone precursors' emissions, population and climate data for the period 2003-2013 were used as inputs. Trend analysis had been performed using the linear regression of SOMO35 over time, and it has demonstrated that majority of the studied countries have a decreasing trend of SOMO35 values. The created models have made majority of predictions ( approximate to 60%) with satisfactory accuracy (relative error  lt 20%) on testing, while the best performing model had R-2 = 0.87 and overall relative error of 33.6%. The domain of applicability of the created models was analyzed using slope/mean ratio derivate from the trend analysis, which was successful in distinguishing countries with high from countries with low prediction errors. The overall relative error was reduced to  lt 14%, after the pool of countries was reduced based on the abovementioned criterion.
PB  - Elsevier Sci Ltd, Oxford
T2  - Environmental Pollution
T1  - Urban population exposure to tropospheric ozone: A multi-country forecasting of SOMO35 using artificial neural networks
EP  - 294
SP  - 288
VL  - 244
DO  - 10.1016/j.envpol.2018.10.051
ER  - 

@article{
author = "Antanasijević, Davor and Pocajt, Viktor and Perić-Grujić, Aleksandra and Ristić, Mirjana",
year = "2019",
abstract = "Urban population exposure to tropospheric ozone is a serious health concern in Europe countries. Although there are insufficient evidence to derive a level below which ozone has no effect on mortality WHO (World Health Organization) uses SOMO35 (sum of means over 35 ppb) in their health impact assessments. Is this paper, the artificial neural network (ANN) approach was used to forecast SOMO35 at the national level for a set of 24 European countries, mostly EU members. Available ozone precursors' emissions, population and climate data for the period 2003-2013 were used as inputs. Trend analysis had been performed using the linear regression of SOMO35 over time, and it has demonstrated that majority of the studied countries have a decreasing trend of SOMO35 values. The created models have made majority of predictions ( approximate to 60%) with satisfactory accuracy (relative error  lt 20%) on testing, while the best performing model had R-2 = 0.87 and overall relative error of 33.6%. The domain of applicability of the created models was analyzed using slope/mean ratio derivate from the trend analysis, which was successful in distinguishing countries with high from countries with low prediction errors. The overall relative error was reduced to  lt 14%, after the pool of countries was reduced based on the abovementioned criterion.",
publisher = "Elsevier Sci Ltd, Oxford",
journal = "Environmental Pollution",
title = "Urban population exposure to tropospheric ozone: A multi-country forecasting of SOMO35 using artificial neural networks",
pages = "294-288",
volume = "244",
doi = "10.1016/j.envpol.2018.10.051"
}

Antanasijević, D., Pocajt, V., Perić-Grujić, A.,& Ristić, M.. (2019). Urban population exposure to tropospheric ozone: A multi-country forecasting of SOMO35 using artificial neural networks. in Environmental Pollution
Elsevier Sci Ltd, Oxford., 244, 288-294.
https://doi.org/10.1016/j.envpol.2018.10.051

Antanasijević D, Pocajt V, Perić-Grujić A, Ristić M. Urban population exposure to tropospheric ozone: A multi-country forecasting of SOMO35 using artificial neural networks. in Environmental Pollution. 2019;244:288-294.
doi:10.1016/j.envpol.2018.10.051 .

Antanasijević, Davor, Pocajt, Viktor, Perić-Grujić, Aleksandra, Ristić, Mirjana, "Urban population exposure to tropospheric ozone: A multi-country forecasting of SOMO35 using artificial neural networks" in Environmental Pollution, 244 (2019):288-294,
https://doi.org/10.1016/j.envpol.2018.10.051 . .

TY  - JOUR
AU  - Adamović, Vladimir M.
AU  - Antanasijević, Davor
AU  - Ćosović, Aleksandar
AU  - Ristić, Mirjana
AU  - Pocajt, Viktor
PY  - 2018
UR  - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/3840
AB  - Although the use of municipal solid waste to generate energy can decrease dependency on fossil fuels and consequently reduces greenhouse gases emissions and areas that waste occupies, in many countries municipal solid waste is not recognized as a valuable resource and possible alternative fuel. The aim of this study is to develop a model for the prediction of primary energy production from municipal solid waste in the European countries and then to apply it to the Balkan countries in order to assess their potentials in that field. For this purpose, general regression neural network architecture was applied, and correlation and sensitivity analyses were used for optimisation of the model. The data for 16 countries from the European Union and Norway for the period 2006-2015 was used for the development of the model. The model with the best performance (coefficient of determination R-2 = 0.995 and the mean absolute percentage error MAPE = 7.757%) was applied to the data for the Balkan countries from 2006 to 2015. The obtained results indicate that there is a significant potential for utilization of municipal solid waste for energy production, which should lead to substantial savings of fossil fuels, primarily lignite which is the most common fossil fuel in the Balkans.
PB  - Pergamon-Elsevier Science Ltd, Oxford
T2  - Waste Management
T1  - An artificial neural network approach for the estimation of the primary production of energy from municipal solid waste and its application to the Balkan countries
EP  - 968
SP  - 955
VL  - 78
DO  - 10.1016/j.wasman.2018.07.012
ER  - 

@article{
author = "Adamović, Vladimir M. and Antanasijević, Davor and Ćosović, Aleksandar and Ristić, Mirjana and Pocajt, Viktor",
year = "2018",
abstract = "Although the use of municipal solid waste to generate energy can decrease dependency on fossil fuels and consequently reduces greenhouse gases emissions and areas that waste occupies, in many countries municipal solid waste is not recognized as a valuable resource and possible alternative fuel. The aim of this study is to develop a model for the prediction of primary energy production from municipal solid waste in the European countries and then to apply it to the Balkan countries in order to assess their potentials in that field. For this purpose, general regression neural network architecture was applied, and correlation and sensitivity analyses were used for optimisation of the model. The data for 16 countries from the European Union and Norway for the period 2006-2015 was used for the development of the model. The model with the best performance (coefficient of determination R-2 = 0.995 and the mean absolute percentage error MAPE = 7.757%) was applied to the data for the Balkan countries from 2006 to 2015. The obtained results indicate that there is a significant potential for utilization of municipal solid waste for energy production, which should lead to substantial savings of fossil fuels, primarily lignite which is the most common fossil fuel in the Balkans.",
publisher = "Pergamon-Elsevier Science Ltd, Oxford",
journal = "Waste Management",
title = "An artificial neural network approach for the estimation of the primary production of energy from municipal solid waste and its application to the Balkan countries",
pages = "968-955",
volume = "78",
doi = "10.1016/j.wasman.2018.07.012"
}

Adamović, V. M., Antanasijević, D., Ćosović, A., Ristić, M.,& Pocajt, V.. (2018). An artificial neural network approach for the estimation of the primary production of energy from municipal solid waste and its application to the Balkan countries. in Waste Management
Pergamon-Elsevier Science Ltd, Oxford., 78, 955-968.
https://doi.org/10.1016/j.wasman.2018.07.012

Adamović VM, Antanasijević D, Ćosović A, Ristić M, Pocajt V. An artificial neural network approach for the estimation of the primary production of energy from municipal solid waste and its application to the Balkan countries. in Waste Management. 2018;78:955-968.
doi:10.1016/j.wasman.2018.07.012 .

Adamović, Vladimir M., Antanasijević, Davor, Ćosović, Aleksandar, Ristić, Mirjana, Pocajt, Viktor, "An artificial neural network approach for the estimation of the primary production of energy from municipal solid waste and its application to the Balkan countries" in Waste Management, 78 (2018):955-968,
https://doi.org/10.1016/j.wasman.2018.07.012 . .

TY  - JOUR
AU  - Antanasijević, Davor
AU  - Antanasijević, Jelena
AU  - Pocajt, Viktor
PY  - 2018
UR  - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/3873
AB  - A dataset containing transition temperature values for 243 bent-core liquid crystal (LC) compounds was used to develop quantitative structure property relationship (QSPR) models using only 2D molecular descriptors and general regression neural network (GRNN). Beside a standard analogue GRNN model, another GRNN model with fuzzy digital response was created with the aim to estimate the prediction error for each compound. Two approaches for the selection of most relevant subset of descriptors, namely the partial mutual information (PMI) and self-organizing maps combined with chi square ranking, were also compared. The best results were obtained using analogue GRNN model based on PMI selected subset (R-2 = 0.91), with the mean absolute error (MAE) lower in comparison with previously published corresponding QSPR models. The digital PMI-GRNN model enabled distinction between high and low accurate predictions, i.e. ones with absolute error higher than mean absolute error (MAE) and others with absolute error  lt = MAE, with the accuracy of 81%.
PB  - Pergamon-Elsevier Science Ltd, Oxford
T2  - Engineering Applications of Artificial Intelligence
T1  - Prediction of the transition temperature of bent-core liquid crystals using fuzzy "digital thermometer" model based on artificial neural networks
EP  - 258
SP  - 251
VL  - 71
DO  - 10.1016/j.engappai.2018.03.009
ER  - 

@article{
author = "Antanasijević, Davor and Antanasijević, Jelena and Pocajt, Viktor",
year = "2018",
abstract = "A dataset containing transition temperature values for 243 bent-core liquid crystal (LC) compounds was used to develop quantitative structure property relationship (QSPR) models using only 2D molecular descriptors and general regression neural network (GRNN). Beside a standard analogue GRNN model, another GRNN model with fuzzy digital response was created with the aim to estimate the prediction error for each compound. Two approaches for the selection of most relevant subset of descriptors, namely the partial mutual information (PMI) and self-organizing maps combined with chi square ranking, were also compared. The best results were obtained using analogue GRNN model based on PMI selected subset (R-2 = 0.91), with the mean absolute error (MAE) lower in comparison with previously published corresponding QSPR models. The digital PMI-GRNN model enabled distinction between high and low accurate predictions, i.e. ones with absolute error higher than mean absolute error (MAE) and others with absolute error  lt = MAE, with the accuracy of 81%.",
publisher = "Pergamon-Elsevier Science Ltd, Oxford",
journal = "Engineering Applications of Artificial Intelligence",
title = "Prediction of the transition temperature of bent-core liquid crystals using fuzzy "digital thermometer" model based on artificial neural networks",
pages = "258-251",
volume = "71",
doi = "10.1016/j.engappai.2018.03.009"
}

Antanasijević, D., Antanasijević, J.,& Pocajt, V.. (2018). Prediction of the transition temperature of bent-core liquid crystals using fuzzy "digital thermometer" model based on artificial neural networks. in Engineering Applications of Artificial Intelligence
Pergamon-Elsevier Science Ltd, Oxford., 71, 251-258.
https://doi.org/10.1016/j.engappai.2018.03.009

Antanasijević D, Antanasijević J, Pocajt V. Prediction of the transition temperature of bent-core liquid crystals using fuzzy "digital thermometer" model based on artificial neural networks. in Engineering Applications of Artificial Intelligence. 2018;71:251-258.
doi:10.1016/j.engappai.2018.03.009 .

Antanasijević, Davor, Antanasijević, Jelena, Pocajt, Viktor, "Prediction of the transition temperature of bent-core liquid crystals using fuzzy "digital thermometer" model based on artificial neural networks" in Engineering Applications of Artificial Intelligence, 71 (2018):251-258,
https://doi.org/10.1016/j.engappai.2018.03.009 . .

TY  - JOUR
AU  - Šiljić-Tomić, Aleksandra
AU  - Antanasijević, Davor
AU  - Ristić, Mirjana
AU  - Perić-Grujić, Aleksandra
AU  - Pocajt, Viktor
PY  - 2018
UR  - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/3974
AB  - Accurate prediction of water quality parameters (WQPs) is an important task in the management of water resources. Artificial neural networks (ANNs) are frequently applied for dissolved oxygen (DO) prediction, but often only their interpolation performance is checked. The aims of this research, beside interpolation, were the determination of extrapolation performance of ANN model, which was developed for the prediction of DO content in the Danube River, and the assessment of relationship between the significance of inputs and prediction error in the presence of values which were of out of the range of training. The applied ANN is a polynomial neural network (PNN) which performs embedded selection of most important inputs during learning, and provides a model in the form of linear and non-linear polynomial functions, which can then be used for a detailed analysis of the significance of inputs. Available dataset that contained 1912 monitoring records for 17 water quality parameters was split into a "regular" subset that contains normally distributed and low variability data, and an "extreme" subset that contains monitoring records with outlier values. The results revealed that the non-linear PNN model has good interpolation performance (R-2 = 0.82), but it was not robust in extrapolation (R-2 = 0.63). The analysis of extrapolation results has shown that the prediction errors are correlated with the significance of inputs. Namely, the out-of-training range values of the inputs with low importance do not affect significantly the PNN model performance, but their influence can be biased by the presence of multi-outlier monitoring records. Subsequently, linear PNN models were successfully applied to study the effect of water quality parameters on DO content. It was observed that DO level is mostly affected by temperature, pH, biological oxygen demand (BOD) and phosphorus concentration, while in extreme conditions the importance of alkalinity and bicarbonates rises over pH and BOD.
PB  - Elsevier Science Bv, Amsterdam
T2  - Science of the Total Environment
T1  - A linear and non-linear polynomial neural network modeling of dissolved oxygen content in surface water: Inter- and extrapolation performance with inputs' significance analysis
EP  - 1046
SP  - 1038
VL  - 610
DO  - 10.1016/j.scitotenv.2017.08.192
ER  - 

@article{
author = "Šiljić-Tomić, Aleksandra and Antanasijević, Davor and Ristić, Mirjana and Perić-Grujić, Aleksandra and Pocajt, Viktor",
year = "2018",
abstract = "Accurate prediction of water quality parameters (WQPs) is an important task in the management of water resources. Artificial neural networks (ANNs) are frequently applied for dissolved oxygen (DO) prediction, but often only their interpolation performance is checked. The aims of this research, beside interpolation, were the determination of extrapolation performance of ANN model, which was developed for the prediction of DO content in the Danube River, and the assessment of relationship between the significance of inputs and prediction error in the presence of values which were of out of the range of training. The applied ANN is a polynomial neural network (PNN) which performs embedded selection of most important inputs during learning, and provides a model in the form of linear and non-linear polynomial functions, which can then be used for a detailed analysis of the significance of inputs. Available dataset that contained 1912 monitoring records for 17 water quality parameters was split into a "regular" subset that contains normally distributed and low variability data, and an "extreme" subset that contains monitoring records with outlier values. The results revealed that the non-linear PNN model has good interpolation performance (R-2 = 0.82), but it was not robust in extrapolation (R-2 = 0.63). The analysis of extrapolation results has shown that the prediction errors are correlated with the significance of inputs. Namely, the out-of-training range values of the inputs with low importance do not affect significantly the PNN model performance, but their influence can be biased by the presence of multi-outlier monitoring records. Subsequently, linear PNN models were successfully applied to study the effect of water quality parameters on DO content. It was observed that DO level is mostly affected by temperature, pH, biological oxygen demand (BOD) and phosphorus concentration, while in extreme conditions the importance of alkalinity and bicarbonates rises over pH and BOD.",
publisher = "Elsevier Science Bv, Amsterdam",
journal = "Science of the Total Environment",
title = "A linear and non-linear polynomial neural network modeling of dissolved oxygen content in surface water: Inter- and extrapolation performance with inputs' significance analysis",
pages = "1046-1038",
volume = "610",
doi = "10.1016/j.scitotenv.2017.08.192"
}

Šiljić-Tomić, A., Antanasijević, D., Ristić, M., Perić-Grujić, A.,& Pocajt, V.. (2018). A linear and non-linear polynomial neural network modeling of dissolved oxygen content in surface water: Inter- and extrapolation performance with inputs' significance analysis. in Science of the Total Environment
Elsevier Science Bv, Amsterdam., 610, 1038-1046.
https://doi.org/10.1016/j.scitotenv.2017.08.192

Šiljić-Tomić A, Antanasijević D, Ristić M, Perić-Grujić A, Pocajt V. A linear and non-linear polynomial neural network modeling of dissolved oxygen content in surface water: Inter- and extrapolation performance with inputs' significance analysis. in Science of the Total Environment. 2018;610:1038-1046.
doi:10.1016/j.scitotenv.2017.08.192 .

Šiljić-Tomić, Aleksandra, Antanasijević, Davor, Ristić, Mirjana, Perić-Grujić, Aleksandra, Pocajt, Viktor, "A linear and non-linear polynomial neural network modeling of dissolved oxygen content in surface water: Inter- and extrapolation performance with inputs' significance analysis" in Science of the Total Environment, 610 (2018):1038-1046,
https://doi.org/10.1016/j.scitotenv.2017.08.192 . .

TY  - JOUR
AU  - Antanasijević, Davor
AU  - Pocajt, Viktor
AU  - Antanasijević, Jelena
AU  - Perić-Grujić, Aleksandra
AU  - Ristić, M.
PY  - 2018
UR  - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/3983
AB  - In this paper, a novel self-organizing network (SON) based similarity index and its application for the optimization of sampling locations in an existing river water quality monitoring network (WQMN) is presented. A rationalization of the River Danube WQMN on its stretch through Serbia was performed using the proposed SON2-based similarity index. A high-dimensional dataset was used, which is composed of 18 water quality parameters that were collected during the period 2002-2010 at 17 monitoring locations. The SON-based seasonal classification that divides 12months into the cold, moderate, and warm seasons was employed, whereas its second application on each seasonal class yielded subclasses that were used to compare the monitoring locations. The obtained SON2-based similarity index can be utilized for analysing seasonal variations, as well as overall similarities among neighbouring sites. Based on the calculated similarities of locations and characteristics of the River Danube basin a rationalized WQMN, which uses 30% less monitoring sites, has been proposed.
PB  - Wiley, Hoboken
T2  - River Research and Applications
T1  - A novel SON2-based similarity index and its application for the rationalization of river water quality monitoring network
EP  - 152
IS  - 2
SP  - 144
VL  - 34
DO  - 10.1002/rra.3231
ER  - 

@article{
author = "Antanasijević, Davor and Pocajt, Viktor and Antanasijević, Jelena and Perić-Grujić, Aleksandra and Ristić, M.",
year = "2018",
abstract = "In this paper, a novel self-organizing network (SON) based similarity index and its application for the optimization of sampling locations in an existing river water quality monitoring network (WQMN) is presented. A rationalization of the River Danube WQMN on its stretch through Serbia was performed using the proposed SON2-based similarity index. A high-dimensional dataset was used, which is composed of 18 water quality parameters that were collected during the period 2002-2010 at 17 monitoring locations. The SON-based seasonal classification that divides 12months into the cold, moderate, and warm seasons was employed, whereas its second application on each seasonal class yielded subclasses that were used to compare the monitoring locations. The obtained SON2-based similarity index can be utilized for analysing seasonal variations, as well as overall similarities among neighbouring sites. Based on the calculated similarities of locations and characteristics of the River Danube basin a rationalized WQMN, which uses 30% less monitoring sites, has been proposed.",
publisher = "Wiley, Hoboken",
journal = "River Research and Applications",
title = "A novel SON2-based similarity index and its application for the rationalization of river water quality monitoring network",
pages = "152-144",
number = "2",
volume = "34",
doi = "10.1002/rra.3231"
}

Antanasijević, D., Pocajt, V., Antanasijević, J., Perić-Grujić, A.,& Ristić, M.. (2018). A novel SON2-based similarity index and its application for the rationalization of river water quality monitoring network. in River Research and Applications
Wiley, Hoboken., 34(2), 144-152.
https://doi.org/10.1002/rra.3231

Antanasijević D, Pocajt V, Antanasijević J, Perić-Grujić A, Ristić M. A novel SON2-based similarity index and its application for the rationalization of river water quality monitoring network. in River Research and Applications. 2018;34(2):144-152.
doi:10.1002/rra.3231 .

Antanasijević, Davor, Pocajt, Viktor, Antanasijević, Jelena, Perić-Grujić, Aleksandra, Ristić, M., "A novel SON2-based similarity index and its application for the rationalization of river water quality monitoring network" in River Research and Applications, 34, no. 2 (2018):144-152,
https://doi.org/10.1002/rra.3231 . .

TY  - JOUR
AU  - Adamović, Vladimir M.
AU  - Antanasijević, Davor
AU  - Ristić, Mirjana
AU  - Perić-Grujić, Aleksandra
AU  - Pocajt, Viktor
PY  - 2018
UR  - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/3994
AB  - This paper presents a development of general regression neural network (a form of artificial neural network) models for the prediction of annual quantities of hazardous chemical and healthcare waste at the national level. Hazardous waste is being generated from many different sources and therefore it is not possible to conduct accurate predictions of the total amount of hazardous waste using traditional methodologies. Since they represent about 40% of the total hazardous waste in the European Union, chemical and healthcare waste were specifically selected for this research. Broadly available social, economic, industrial and sustainability indicators were used as input variables and the optimal sets were selected using correlation analysis and sensitivity analysis. The obtained values of coefficients of determination for the final models were 0.999 for the prediction of chemical hazardous waste and 0.975 for the prediction of healthcare and biological hazardous waste. The predicting capabilities of the models for both types of waste are high, since there were no predictions with errors greater than 25%. Also, results of this research demonstrate that the human development index can replace gross domestic product and in this context even represent a better indicator of socio-economic conditions at the national level.
PB  - Springer, New York
T2  - Journal of Material Cycles and Waste Management
T1  - An optimized artificial neural network model for the prediction of rate of hazardous chemical and healthcare waste generation at the national level
EP  - 1750
IS  - 3
SP  - 1736
VL  - 20
DO  - 10.1007/s10163-018-0741-6
ER  - 

@article{
author = "Adamović, Vladimir M. and Antanasijević, Davor and Ristić, Mirjana and Perić-Grujić, Aleksandra and Pocajt, Viktor",
year = "2018",
abstract = "This paper presents a development of general regression neural network (a form of artificial neural network) models for the prediction of annual quantities of hazardous chemical and healthcare waste at the national level. Hazardous waste is being generated from many different sources and therefore it is not possible to conduct accurate predictions of the total amount of hazardous waste using traditional methodologies. Since they represent about 40% of the total hazardous waste in the European Union, chemical and healthcare waste were specifically selected for this research. Broadly available social, economic, industrial and sustainability indicators were used as input variables and the optimal sets were selected using correlation analysis and sensitivity analysis. The obtained values of coefficients of determination for the final models were 0.999 for the prediction of chemical hazardous waste and 0.975 for the prediction of healthcare and biological hazardous waste. The predicting capabilities of the models for both types of waste are high, since there were no predictions with errors greater than 25%. Also, results of this research demonstrate that the human development index can replace gross domestic product and in this context even represent a better indicator of socio-economic conditions at the national level.",
publisher = "Springer, New York",
journal = "Journal of Material Cycles and Waste Management",
title = "An optimized artificial neural network model for the prediction of rate of hazardous chemical and healthcare waste generation at the national level",
pages = "1750-1736",
number = "3",
volume = "20",
doi = "10.1007/s10163-018-0741-6"
}

Adamović, V. M., Antanasijević, D., Ristić, M., Perić-Grujić, A.,& Pocajt, V.. (2018). An optimized artificial neural network model for the prediction of rate of hazardous chemical and healthcare waste generation at the national level. in Journal of Material Cycles and Waste Management
Springer, New York., 20(3), 1736-1750.
https://doi.org/10.1007/s10163-018-0741-6

Adamović VM, Antanasijević D, Ristić M, Perić-Grujić A, Pocajt V. An optimized artificial neural network model for the prediction of rate of hazardous chemical and healthcare waste generation at the national level. in Journal of Material Cycles and Waste Management. 2018;20(3):1736-1750.
doi:10.1007/s10163-018-0741-6 .

Adamović, Vladimir M., Antanasijević, Davor, Ristić, Mirjana, Perić-Grujić, Aleksandra, Pocajt, Viktor, "An optimized artificial neural network model for the prediction of rate of hazardous chemical and healthcare waste generation at the national level" in Journal of Material Cycles and Waste Management, 20, no. 3 (2018):1736-1750,
https://doi.org/10.1007/s10163-018-0741-6 . .

TY  - JOUR
AU  - Antanasijević, Davor
AU  - Matić-Bujagić, Ivana
AU  - Grujić, Svetlana
AU  - Laušević, Mila
PY  - 2018
UR  - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/4020
AB  - In this paper, multivariate analysis of sterol concentrations detected in river sediment samples was performed. In order to remove co-dependence of values, concentrations of sterols were transformed using centered log-ratio (CLR) transformation. The main objective of the work was to point out the damaging effects of working in the wrong geometry on the principal component analysis (PCA) assessment of sterol pollution. In order to determine if the dimension lost have effect on the principal component analysis of sterols in sediments, we have performed the PCA using raw and log-ratio transformed sterol data. Additionally, two rounded zero replacement approaches, i.e. a simple-substitution method (DL/2, 0.55DL and DL/root 2) and multiplicative replacement strategy (0.65 DL), were compared in order to determine if the replacement values have an effect on PCA results and conclusions. Relevant differences were noted by comparing the results of the principal component analysis obtained with raw data and log-ratio transformed sterol data. Only the PC loadings obtained from the CLR PCA allowed the clear distinction between human-sourced pollution and biogenic sources of sterols, whereas in the case of PCA with raw data loadings were all grouped almost in a single quadrant. For the small proportion of rounded zeros (not more than 10%), two different replacement approaches did not have any effect on transformed PCA output. The results presented in this work have shown that the effect of "closure" in the sterol data can be easily observed from the PCA biplot, and that it obstructs the evaluation of human contribution to pollution of river sediments. Therefore, prior to the PCA, sterol concentrations must be CLR transformed in order to perform a reliable assessment of the sewage contamination.
PB  - Elsevier Science Bv, Amsterdam
T2  - Microchemical Journal
T1  - Effect of compositional data in the multivariate analysis of sterol concentrations in river sediments
EP  - 195
SP  - 188
VL  - 139
DO  - 10.1016/j.microc.2018.02.031
ER  - 

@article{
author = "Antanasijević, Davor and Matić-Bujagić, Ivana and Grujić, Svetlana and Laušević, Mila",
year = "2018",
abstract = "In this paper, multivariate analysis of sterol concentrations detected in river sediment samples was performed. In order to remove co-dependence of values, concentrations of sterols were transformed using centered log-ratio (CLR) transformation. The main objective of the work was to point out the damaging effects of working in the wrong geometry on the principal component analysis (PCA) assessment of sterol pollution. In order to determine if the dimension lost have effect on the principal component analysis of sterols in sediments, we have performed the PCA using raw and log-ratio transformed sterol data. Additionally, two rounded zero replacement approaches, i.e. a simple-substitution method (DL/2, 0.55DL and DL/root 2) and multiplicative replacement strategy (0.65 DL), were compared in order to determine if the replacement values have an effect on PCA results and conclusions. Relevant differences were noted by comparing the results of the principal component analysis obtained with raw data and log-ratio transformed sterol data. Only the PC loadings obtained from the CLR PCA allowed the clear distinction between human-sourced pollution and biogenic sources of sterols, whereas in the case of PCA with raw data loadings were all grouped almost in a single quadrant. For the small proportion of rounded zeros (not more than 10%), two different replacement approaches did not have any effect on transformed PCA output. The results presented in this work have shown that the effect of "closure" in the sterol data can be easily observed from the PCA biplot, and that it obstructs the evaluation of human contribution to pollution of river sediments. Therefore, prior to the PCA, sterol concentrations must be CLR transformed in order to perform a reliable assessment of the sewage contamination.",
publisher = "Elsevier Science Bv, Amsterdam",
journal = "Microchemical Journal",
title = "Effect of compositional data in the multivariate analysis of sterol concentrations in river sediments",
pages = "195-188",
volume = "139",
doi = "10.1016/j.microc.2018.02.031"
}

Antanasijević, D., Matić-Bujagić, I., Grujić, S.,& Laušević, M.. (2018). Effect of compositional data in the multivariate analysis of sterol concentrations in river sediments. in Microchemical Journal
Elsevier Science Bv, Amsterdam., 139, 188-195.
https://doi.org/10.1016/j.microc.2018.02.031

Antanasijević D, Matić-Bujagić I, Grujić S, Laušević M. Effect of compositional data in the multivariate analysis of sterol concentrations in river sediments. in Microchemical Journal. 2018;139:188-195.
doi:10.1016/j.microc.2018.02.031 .

Antanasijević, Davor, Matić-Bujagić, Ivana, Grujić, Svetlana, Laušević, Mila, "Effect of compositional data in the multivariate analysis of sterol concentrations in river sediments" in Microchemical Journal, 139 (2018):188-195,
https://doi.org/10.1016/j.microc.2018.02.031 . .

TY  - JOUR
AU  - Antanasijević, Davor
AU  - Pocajt, Viktor
AU  - Perić-Grujić, Aleksandra
AU  - Ristić, Mirjana
PY  - 2018
UR  - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/4024
AB  - Traffic-related air pollutant emissions have become a global environmental problem, especially in urban areas. The estimation of pollutant emissions is based on complex models that require the use of detailed travel-activity data, which is often unavailable and in particular, in developing countries. In order to overcome this issue, an alternative multiple-input-multiple-output general regression neural network model, based on basic socioeconomic and transport related indicators, is proposed for the simultaneous prediction of sulphur oxides (SOx), nitrogen oxides (NOx), ammonia (NH3 ), non-methane volatile organic compounds (NMVOC) and particulate matter emissions at the national level. The best model, created using only six inputs, has MAPE (mean absolute percentage error) values on testing in the range of 12-15% for all studied pollutants, except NMVOC (MAPE = 21%). The obtained predictions for SOx, NH3 and PM10 emissions were in good agreement with the reported emissions (R-2  gt = 0.93), while the predictions for NOx and NMVOC are somewhat less accurate (R-2 approximate to 0.85). It can be concluded that the presented ANN approach can offer a simple and relatively accurate alternative method for the estimation of traffic-related air pollutant emissions.
PB  - Turkish Natl Committee Air Pollution Res & Control-Tuncap, Buca
T2  - Atmospheric Pollution Research
T1  - Multiple-input-multiple-output general regression neural networks model for the simultaneous estimation of traffic-related air pollutant emissions
EP  - 397
IS  - 2
SP  - 388
VL  - 9
DO  - 10.1016/j.apr.2017.10.011
ER  - 

@article{
author = "Antanasijević, Davor and Pocajt, Viktor and Perić-Grujić, Aleksandra and Ristić, Mirjana",
year = "2018",
abstract = "Traffic-related air pollutant emissions have become a global environmental problem, especially in urban areas. The estimation of pollutant emissions is based on complex models that require the use of detailed travel-activity data, which is often unavailable and in particular, in developing countries. In order to overcome this issue, an alternative multiple-input-multiple-output general regression neural network model, based on basic socioeconomic and transport related indicators, is proposed for the simultaneous prediction of sulphur oxides (SOx), nitrogen oxides (NOx), ammonia (NH3 ), non-methane volatile organic compounds (NMVOC) and particulate matter emissions at the national level. The best model, created using only six inputs, has MAPE (mean absolute percentage error) values on testing in the range of 12-15% for all studied pollutants, except NMVOC (MAPE = 21%). The obtained predictions for SOx, NH3 and PM10 emissions were in good agreement with the reported emissions (R-2  gt = 0.93), while the predictions for NOx and NMVOC are somewhat less accurate (R-2 approximate to 0.85). It can be concluded that the presented ANN approach can offer a simple and relatively accurate alternative method for the estimation of traffic-related air pollutant emissions.",
publisher = "Turkish Natl Committee Air Pollution Res & Control-Tuncap, Buca",
journal = "Atmospheric Pollution Research",
title = "Multiple-input-multiple-output general regression neural networks model for the simultaneous estimation of traffic-related air pollutant emissions",
pages = "397-388",
number = "2",
volume = "9",
doi = "10.1016/j.apr.2017.10.011"
}

Antanasijević, D., Pocajt, V., Perić-Grujić, A.,& Ristić, M.. (2018). Multiple-input-multiple-output general regression neural networks model for the simultaneous estimation of traffic-related air pollutant emissions. in Atmospheric Pollution Research
Turkish Natl Committee Air Pollution Res & Control-Tuncap, Buca., 9(2), 388-397.
https://doi.org/10.1016/j.apr.2017.10.011

Antanasijević D, Pocajt V, Perić-Grujić A, Ristić M. Multiple-input-multiple-output general regression neural networks model for the simultaneous estimation of traffic-related air pollutant emissions. in Atmospheric Pollution Research. 2018;9(2):388-397.
doi:10.1016/j.apr.2017.10.011 .

Antanasijević, Davor, Pocajt, Viktor, Perić-Grujić, Aleksandra, Ristić, Mirjana, "Multiple-input-multiple-output general regression neural networks model for the simultaneous estimation of traffic-related air pollutant emissions" in Atmospheric Pollution Research, 9, no. 2 (2018):388-397,
https://doi.org/10.1016/j.apr.2017.10.011 . .

TY  - JOUR
AU  - Šiljić-Tomić, Aleksandra
AU  - Antanasijević, Davor
AU  - Ristić, Mirjana
AU  - Perić-Grujić, Aleksandra
AU  - Pocajt, Viktor
PY  - 2018
UR  - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/4028
AB  - This paper presents an application of experimental design for the optimization of artificial neural network (ANN) for the prediction of dissolved oxygen (DO) content in the Danube River. The aim of this research was to obtain a more reliable ANN model that uses fewer monitoring records, by simultaneous optimization of the following model parameters: number of monitoring sites, number of historical monitoring data (expressed in years), and number of input water quality parameters used. Box-Behnken three-factor at three levels experimental design was applied for simultaneous spatial, temporal, and input variables optimization of the ANN model. The prediction of DO was performed using a feed-forward back-propagation neural network (BPNN), while the selection of most important inputs was done off-model using multi-filter approach that combines a chi-square ranking in the first step with a correlation-based elimination in the second step. The contour plots of absolute and relative error response surfaces were utilized to determine the optimal values of design factors. From the contour plots, two BPNN models that cover entire Danube flow through Serbia are proposed: an upstream model (BPNN-UP) that covers 8 monitoring sites prior to Belgrade and uses 12 inputs measured in the 7-year period and a downstream model (BPNN-DOWN) which covers 9 monitoring sites and uses 11 input parameters measured in the 6-year period. The main difference between the two models is that BPNN-UP utilizes inputs such as BOD, P, and PO43-, which is in accordance with the fact that this model covers northern part of Serbia (Vojvodina Autonomous Province) which is well-known for agricultural production and extensive use of fertilizers. Both models have shown very good agreement between measured and predicted DO (with R-2  gt = 0.86) and demonstrated that they can effectively forecast DO content in the Danube River.
PB  - Springer Heidelberg, Heidelberg
T2  - Environmental Science and Pollution Research
T1  - Application of experimental design for the optimization of artificial neural network-based water quality model: a case study of dissolved oxygen prediction
EP  - 9370
IS  - 10
SP  - 9360
VL  - 25
DO  - 10.1007/s11356-018-1246-5
ER  - 

@article{
author = "Šiljić-Tomić, Aleksandra and Antanasijević, Davor and Ristić, Mirjana and Perić-Grujić, Aleksandra and Pocajt, Viktor",
year = "2018",
abstract = "This paper presents an application of experimental design for the optimization of artificial neural network (ANN) for the prediction of dissolved oxygen (DO) content in the Danube River. The aim of this research was to obtain a more reliable ANN model that uses fewer monitoring records, by simultaneous optimization of the following model parameters: number of monitoring sites, number of historical monitoring data (expressed in years), and number of input water quality parameters used. Box-Behnken three-factor at three levels experimental design was applied for simultaneous spatial, temporal, and input variables optimization of the ANN model. The prediction of DO was performed using a feed-forward back-propagation neural network (BPNN), while the selection of most important inputs was done off-model using multi-filter approach that combines a chi-square ranking in the first step with a correlation-based elimination in the second step. The contour plots of absolute and relative error response surfaces were utilized to determine the optimal values of design factors. From the contour plots, two BPNN models that cover entire Danube flow through Serbia are proposed: an upstream model (BPNN-UP) that covers 8 monitoring sites prior to Belgrade and uses 12 inputs measured in the 7-year period and a downstream model (BPNN-DOWN) which covers 9 monitoring sites and uses 11 input parameters measured in the 6-year period. The main difference between the two models is that BPNN-UP utilizes inputs such as BOD, P, and PO43-, which is in accordance with the fact that this model covers northern part of Serbia (Vojvodina Autonomous Province) which is well-known for agricultural production and extensive use of fertilizers. Both models have shown very good agreement between measured and predicted DO (with R-2  gt = 0.86) and demonstrated that they can effectively forecast DO content in the Danube River.",
publisher = "Springer Heidelberg, Heidelberg",
journal = "Environmental Science and Pollution Research",
title = "Application of experimental design for the optimization of artificial neural network-based water quality model: a case study of dissolved oxygen prediction",
pages = "9370-9360",
number = "10",
volume = "25",
doi = "10.1007/s11356-018-1246-5"
}

Šiljić-Tomić, A., Antanasijević, D., Ristić, M., Perić-Grujić, A.,& Pocajt, V.. (2018). Application of experimental design for the optimization of artificial neural network-based water quality model: a case study of dissolved oxygen prediction. in Environmental Science and Pollution Research
Springer Heidelberg, Heidelberg., 25(10), 9360-9370.
https://doi.org/10.1007/s11356-018-1246-5

Šiljić-Tomić A, Antanasijević D, Ristić M, Perić-Grujić A, Pocajt V. Application of experimental design for the optimization of artificial neural network-based water quality model: a case study of dissolved oxygen prediction. in Environmental Science and Pollution Research. 2018;25(10):9360-9370.
doi:10.1007/s11356-018-1246-5 .

Šiljić-Tomić, Aleksandra, Antanasijević, Davor, Ristić, Mirjana, Perić-Grujić, Aleksandra, Pocajt, Viktor, "Application of experimental design for the optimization of artificial neural network-based water quality model: a case study of dissolved oxygen prediction" in Environmental Science and Pollution Research, 25, no. 10 (2018):9360-9370,
https://doi.org/10.1007/s11356-018-1246-5 . .

TY  - JOUR
AU  - Egerić, Marija
AU  - Smičiklas, Ivana D.
AU  - Mraković, Ana
AU  - Jović, Mihajlo D.
AU  - Šljivić-Ivanović, Marija Z.
AU  - Antanasijević, Davor
AU  - Ristić, Mirjana
PY  - 2018
UR  - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/4029
AB  - BACKGROUNDSeashell waste (SW) is rich in biogenic calcium carbonate and potentially can substitute geological sources in various applications, such as the separation of heavy metals and radionuclides from contaminated solutions. This study aims to compare SW sorption efficiency towards different chemical species (Cu2+, Zn2+, Pb2+ and Sr2+) and to evaluate the effects of various factors based on the experimental data and modeling approach. RESULTSThe reaction of SW with aqueous metal solutions is a combination of several processes that result in metal retention, Ca2+ release, and changes in pH. SW demonstrates variable selectivity for investigated cations, depending on their concentrations and reaction times. Maximum sorption capacities declined in the order Zn2+  gt  Pb2+ approximate to Sr2+  gt  Cu2+. The model based on general regression neural network (GRNN) architecture was developed, which enabled prediction of removal efficiency taking into account the process specific, metal specific parameters and their non-linear interactions. Initial concentration and covalent radius of a cation exhibit the highest, while the initial pH the lowest significance. CONCLUSIONEcological problems caused by SW accumulation in coastal areas could be mitigated by mastering technologies for their practical utilization. The results obtained facilitate the understanding of cationic pollutants removal by SW in the range of experimental conditions, while the GRNN approach demonstrates advantages in modeling complex sorption processes.
PB  - Wiley, Hoboken
T2  - Journal of Chemical Technology and Biotechnology
T1  - Experimental and theoretical consideration of the factors influencing cationic pollutants retention by seashell waste
EP  - 1487
IS  - 5
SP  - 1477
VL  - 93
DO  - 10.1002/jctb.5516
ER  - 

@article{
author = "Egerić, Marija and Smičiklas, Ivana D. and Mraković, Ana and Jović, Mihajlo D. and Šljivić-Ivanović, Marija Z. and Antanasijević, Davor and Ristić, Mirjana",
year = "2018",
abstract = "BACKGROUNDSeashell waste (SW) is rich in biogenic calcium carbonate and potentially can substitute geological sources in various applications, such as the separation of heavy metals and radionuclides from contaminated solutions. This study aims to compare SW sorption efficiency towards different chemical species (Cu2+, Zn2+, Pb2+ and Sr2+) and to evaluate the effects of various factors based on the experimental data and modeling approach. RESULTSThe reaction of SW with aqueous metal solutions is a combination of several processes that result in metal retention, Ca2+ release, and changes in pH. SW demonstrates variable selectivity for investigated cations, depending on their concentrations and reaction times. Maximum sorption capacities declined in the order Zn2+  gt  Pb2+ approximate to Sr2+  gt  Cu2+. The model based on general regression neural network (GRNN) architecture was developed, which enabled prediction of removal efficiency taking into account the process specific, metal specific parameters and their non-linear interactions. Initial concentration and covalent radius of a cation exhibit the highest, while the initial pH the lowest significance. CONCLUSIONEcological problems caused by SW accumulation in coastal areas could be mitigated by mastering technologies for their practical utilization. The results obtained facilitate the understanding of cationic pollutants removal by SW in the range of experimental conditions, while the GRNN approach demonstrates advantages in modeling complex sorption processes.",
publisher = "Wiley, Hoboken",
journal = "Journal of Chemical Technology and Biotechnology",
title = "Experimental and theoretical consideration of the factors influencing cationic pollutants retention by seashell waste",
pages = "1487-1477",
number = "5",
volume = "93",
doi = "10.1002/jctb.5516"
}

Egerić, M., Smičiklas, I. D., Mraković, A., Jović, M. D., Šljivić-Ivanović, M. Z., Antanasijević, D.,& Ristić, M.. (2018). Experimental and theoretical consideration of the factors influencing cationic pollutants retention by seashell waste. in Journal of Chemical Technology and Biotechnology
Wiley, Hoboken., 93(5), 1477-1487.
https://doi.org/10.1002/jctb.5516

Egerić M, Smičiklas ID, Mraković A, Jović MD, Šljivić-Ivanović MZ, Antanasijević D, Ristić M. Experimental and theoretical consideration of the factors influencing cationic pollutants retention by seashell waste. in Journal of Chemical Technology and Biotechnology. 2018;93(5):1477-1487.
doi:10.1002/jctb.5516 .

Egerić, Marija, Smičiklas, Ivana D., Mraković, Ana, Jović, Mihajlo D., Šljivić-Ivanović, Marija Z., Antanasijević, Davor, Ristić, Mirjana, "Experimental and theoretical consideration of the factors influencing cationic pollutants retention by seashell waste" in Journal of Chemical Technology and Biotechnology, 93, no. 5 (2018):1477-1487,
https://doi.org/10.1002/jctb.5516 . .

TY  - JOUR
AU  - Antanasijević, Davor
AU  - Pocajt, Viktor
AU  - Ristić, Mirjana
AU  - Perić-Grujić, Aleksandra
PY  - 2017
UR  - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/3555
AB  - Sustainable development as a concept that aims to enhance the quality of life without affecting environment has been in focus in European policies since the last decade of 20th century. The objectives of EU Sustainable Development Strategy (EU SDS) are grouped into ten thematic areas, where almost each theme has at least one headline and several operational sustainable development indicators (SDIs). A large number of SDIs is needed to evaluate all EU SDS goals, which imposes the use of multivariate data mining techniques. This paper presents an empirical study carried out to assess the sustainability performance of European countries using the differential multi criteria analysis (DMCA) technique. The PROMETHEE (Preference Ranking Organization MeTHod for Enrichment Evaluations) was applied on 38 headline and operational SDIs defined under the EU SDS. This DMCA was applied to 30 European countries over a 10-year period (2004-2014) with the aim to determine the theme specific, as well as, overall sustainability progress. The DMCA reveals that the majority of European countries have made progress in sustainability in the studied period, where Czech Republic, Germany, Hungary and Sweden, have enhanced their sustainability performance concerning all themes. There are only two countries, namely Greece and Ireland, which have not made overall progress in this period. Also, above the average progress has been made concerning social inclusion, sustainable transport, and climate change and energy, while in all other themes additional efforts should be made in order to ensure sustainable performance progress in future years. Although the progress in reducing uneven development between EU members has been made, after 2009 a positive trend can be observed only in a limited number of SDS themes.
PB  - Elsevier Sci Ltd, Oxford
T2  - Journal of Cleaner Production
T1  - A differential multi-criteria analysis for the assessment of sustainability performance of European countries: Beyond country ranking
EP  - 220
SP  - 213
VL  - 165
DO  - 10.1016/j.jclepro.2017.07.131
ER  - 

@article{
author = "Antanasijević, Davor and Pocajt, Viktor and Ristić, Mirjana and Perić-Grujić, Aleksandra",
year = "2017",
abstract = "Sustainable development as a concept that aims to enhance the quality of life without affecting environment has been in focus in European policies since the last decade of 20th century. The objectives of EU Sustainable Development Strategy (EU SDS) are grouped into ten thematic areas, where almost each theme has at least one headline and several operational sustainable development indicators (SDIs). A large number of SDIs is needed to evaluate all EU SDS goals, which imposes the use of multivariate data mining techniques. This paper presents an empirical study carried out to assess the sustainability performance of European countries using the differential multi criteria analysis (DMCA) technique. The PROMETHEE (Preference Ranking Organization MeTHod for Enrichment Evaluations) was applied on 38 headline and operational SDIs defined under the EU SDS. This DMCA was applied to 30 European countries over a 10-year period (2004-2014) with the aim to determine the theme specific, as well as, overall sustainability progress. The DMCA reveals that the majority of European countries have made progress in sustainability in the studied period, where Czech Republic, Germany, Hungary and Sweden, have enhanced their sustainability performance concerning all themes. There are only two countries, namely Greece and Ireland, which have not made overall progress in this period. Also, above the average progress has been made concerning social inclusion, sustainable transport, and climate change and energy, while in all other themes additional efforts should be made in order to ensure sustainable performance progress in future years. Although the progress in reducing uneven development between EU members has been made, after 2009 a positive trend can be observed only in a limited number of SDS themes.",
publisher = "Elsevier Sci Ltd, Oxford",
journal = "Journal of Cleaner Production",
title = "A differential multi-criteria analysis for the assessment of sustainability performance of European countries: Beyond country ranking",
pages = "220-213",
volume = "165",
doi = "10.1016/j.jclepro.2017.07.131"
}

Antanasijević, D., Pocajt, V., Ristić, M.,& Perić-Grujić, A.. (2017). A differential multi-criteria analysis for the assessment of sustainability performance of European countries: Beyond country ranking. in Journal of Cleaner Production
Elsevier Sci Ltd, Oxford., 165, 213-220.
https://doi.org/10.1016/j.jclepro.2017.07.131

Antanasijević D, Pocajt V, Ristić M, Perić-Grujić A. A differential multi-criteria analysis for the assessment of sustainability performance of European countries: Beyond country ranking. in Journal of Cleaner Production. 2017;165:213-220.
doi:10.1016/j.jclepro.2017.07.131 .

Antanasijević, Davor, Pocajt, Viktor, Ristić, Mirjana, Perić-Grujić, Aleksandra, "A differential multi-criteria analysis for the assessment of sustainability performance of European countries: Beyond country ranking" in Journal of Cleaner Production, 165 (2017):213-220,
https://doi.org/10.1016/j.jclepro.2017.07.131 . .

TY  - JOUR
AU  - Stamenković, Lidija J.
AU  - Antanasijević, Davor
AU  - Ristić, Mirjana
AU  - Perić-Grujić, Aleksandra
AU  - Pocajt, Viktor
PY  - 2017
UR  - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/3610
AB  - Nitrogen oxides (NOx) emissions into the atmosphere have multiple negative effects on the environment and effects directly and indirectly on human health. This paper describes the development of a model for NO (x) emission prediction at the national level based on artificial neural networks (ANNs) and on widely available sustainability, industrial, and economical parameters as input variables. In this study, 11 sustainability, industrial, and economical parameters were chosen as potential input variables. The ANN models were trained, validated, and tested with available data for 17 European countries, USA, China, Japan, Russia, and India for the years 2001 to 2008. The ANN modeling was performed using general regression neural network (GRNN), and correlation and variance inflation factor (VIF) analysis were applied to reduce the number of input variables. The best results were obtained using the selection of inputs based on the correlation between input variables, which provided a more accurate prediction than the GRNN model created with all initial selected input variables. Sensitivity analysis showed that the input variables with the largest influences on the GRNN model results were (in descending order) electricity production from oil sources, agricultural land, fossil fuel energy consumption, number of vehicles, gross domestic product, energy use, and electricity production from coal sources.
PB  - Springer, Dordrecht
T2  - Air Quality Atmosphere and Health
T1  - Prediction of nitrogen oxides emissions at the national level based on optimized artificial neural network model
EP  - 23
IS  - 1
SP  - 15
VL  - 10
DO  - 10.1007/s11869-016-0403-6
ER  - 

@article{
author = "Stamenković, Lidija J. and Antanasijević, Davor and Ristić, Mirjana and Perić-Grujić, Aleksandra and Pocajt, Viktor",
year = "2017",
abstract = "Nitrogen oxides (NOx) emissions into the atmosphere have multiple negative effects on the environment and effects directly and indirectly on human health. This paper describes the development of a model for NO (x) emission prediction at the national level based on artificial neural networks (ANNs) and on widely available sustainability, industrial, and economical parameters as input variables. In this study, 11 sustainability, industrial, and economical parameters were chosen as potential input variables. The ANN models were trained, validated, and tested with available data for 17 European countries, USA, China, Japan, Russia, and India for the years 2001 to 2008. The ANN modeling was performed using general regression neural network (GRNN), and correlation and variance inflation factor (VIF) analysis were applied to reduce the number of input variables. The best results were obtained using the selection of inputs based on the correlation between input variables, which provided a more accurate prediction than the GRNN model created with all initial selected input variables. Sensitivity analysis showed that the input variables with the largest influences on the GRNN model results were (in descending order) electricity production from oil sources, agricultural land, fossil fuel energy consumption, number of vehicles, gross domestic product, energy use, and electricity production from coal sources.",
publisher = "Springer, Dordrecht",
journal = "Air Quality Atmosphere and Health",
title = "Prediction of nitrogen oxides emissions at the national level based on optimized artificial neural network model",
pages = "23-15",
number = "1",
volume = "10",
doi = "10.1007/s11869-016-0403-6"
}

Stamenković, L. J., Antanasijević, D., Ristić, M., Perić-Grujić, A.,& Pocajt, V.. (2017). Prediction of nitrogen oxides emissions at the national level based on optimized artificial neural network model. in Air Quality Atmosphere and Health
Springer, Dordrecht., 10(1), 15-23.
https://doi.org/10.1007/s11869-016-0403-6

Stamenković LJ, Antanasijević D, Ristić M, Perić-Grujić A, Pocajt V. Prediction of nitrogen oxides emissions at the national level based on optimized artificial neural network model. in Air Quality Atmosphere and Health. 2017;10(1):15-23.
doi:10.1007/s11869-016-0403-6 .

Stamenković, Lidija J., Antanasijević, Davor, Ristić, Mirjana, Perić-Grujić, Aleksandra, Pocajt, Viktor, "Prediction of nitrogen oxides emissions at the national level based on optimized artificial neural network model" in Air Quality Atmosphere and Health, 10, no. 1 (2017):15-23,
https://doi.org/10.1007/s11869-016-0403-6 . .

TY  - JOUR
AU  - Antanasijević, Davor
AU  - Antanasijević, Jelena
AU  - Trišović, Nemanja
AU  - Ušćumlić, Gordana
AU  - Pocajt, Viktor
PY  - 2017
UR  - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/3614
AB  - Succinimides, which contain a pharmacophore responsible for anticonvulsant activity, are frequently used antiepileptic drugs and the synthesis of their new derivatives with improved efficacy and tolerability presents an important task. Nowadays, multitarget/tasking methodologies focused on quantitative-structure activity relationships (mt-QSAR/mtk-QSAR) have an important role in the rational design of drugs since they enable simultaneous prediction of several standard measures of biological activities at diverse experimental conditions and against different biological targets. Relating to this very topic, the mt-QSAR/mtk-QSAR methodology can give only binary classification models, and as such, in this study a regression mtk-QSAR (rmtk-QSAR) model based on a novel modular neural network (MNN) has been proposed. The MNN uses standard classification mtk-QSAR models as input modules, while the regression is performed by the output module. The rmtk-QSAR model has been successfully developed for the simultaneous prediction of anticonvulsant activity and neurotoxicity of succinimides, with a satisfactory accuracy in testing (R-2 = 0.87). Thus, the proposed mtk-QSAR regression method can be regarded as a viable alternative to the standard QSAR methodology.
PB  - Amer Chemical Soc, Washington
T2  - Molecular Pharmaceutics
T1  - From Classification to Regression Multitasking QSAR Modeling Using a Novel Modular Neural Network: Simultaneous Prediction of Anticonvulsant Activity and Neurotoxicity of Succinimides
EP  - 4484
IS  - 12
SP  - 4476
VL  - 14
DO  - 10.1021/acs.molpharmaceut.7b00582
ER  - 

@article{
author = "Antanasijević, Davor and Antanasijević, Jelena and Trišović, Nemanja and Ušćumlić, Gordana and Pocajt, Viktor",
year = "2017",
abstract = "Succinimides, which contain a pharmacophore responsible for anticonvulsant activity, are frequently used antiepileptic drugs and the synthesis of their new derivatives with improved efficacy and tolerability presents an important task. Nowadays, multitarget/tasking methodologies focused on quantitative-structure activity relationships (mt-QSAR/mtk-QSAR) have an important role in the rational design of drugs since they enable simultaneous prediction of several standard measures of biological activities at diverse experimental conditions and against different biological targets. Relating to this very topic, the mt-QSAR/mtk-QSAR methodology can give only binary classification models, and as such, in this study a regression mtk-QSAR (rmtk-QSAR) model based on a novel modular neural network (MNN) has been proposed. The MNN uses standard classification mtk-QSAR models as input modules, while the regression is performed by the output module. The rmtk-QSAR model has been successfully developed for the simultaneous prediction of anticonvulsant activity and neurotoxicity of succinimides, with a satisfactory accuracy in testing (R-2 = 0.87). Thus, the proposed mtk-QSAR regression method can be regarded as a viable alternative to the standard QSAR methodology.",
publisher = "Amer Chemical Soc, Washington",
journal = "Molecular Pharmaceutics",
title = "From Classification to Regression Multitasking QSAR Modeling Using a Novel Modular Neural Network: Simultaneous Prediction of Anticonvulsant Activity and Neurotoxicity of Succinimides",
pages = "4484-4476",
number = "12",
volume = "14",
doi = "10.1021/acs.molpharmaceut.7b00582"
}

Antanasijević, D., Antanasijević, J., Trišović, N., Ušćumlić, G.,& Pocajt, V.. (2017). From Classification to Regression Multitasking QSAR Modeling Using a Novel Modular Neural Network: Simultaneous Prediction of Anticonvulsant Activity and Neurotoxicity of Succinimides. in Molecular Pharmaceutics
Amer Chemical Soc, Washington., 14(12), 4476-4484.
https://doi.org/10.1021/acs.molpharmaceut.7b00582

Antanasijević D, Antanasijević J, Trišović N, Ušćumlić G, Pocajt V. From Classification to Regression Multitasking QSAR Modeling Using a Novel Modular Neural Network: Simultaneous Prediction of Anticonvulsant Activity and Neurotoxicity of Succinimides. in Molecular Pharmaceutics. 2017;14(12):4476-4484.
doi:10.1021/acs.molpharmaceut.7b00582 .

Antanasijević, Davor, Antanasijević, Jelena, Trišović, Nemanja, Ušćumlić, Gordana, Pocajt, Viktor, "From Classification to Regression Multitasking QSAR Modeling Using a Novel Modular Neural Network: Simultaneous Prediction of Anticonvulsant Activity and Neurotoxicity of Succinimides" in Molecular Pharmaceutics, 14, no. 12 (2017):4476-4484,
https://doi.org/10.1021/acs.molpharmaceut.7b00582 . .

TY  - JOUR
AU  - Adamović, Vladimir M.
AU  - Antanasijević, Davor
AU  - Ristić, Mirjana
AU  - Perić-Grujić, Aleksandra
AU  - Pocajt, Viktor
PY  - 2017
UR  - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/3675
AB  - This paper presents the development of a general regression neural network (GRNN) model for the prediction of annual municipal solid waste (MSW) generation at the national level for 44 countries of different size, population and economic development level. Proper modelling of MSW generation is essential for the planning of MSW management system as well as for the simulation of various environmental impact scenarios. The main objective of this work was to examine the potential influence of economy crisis (global or local) on the forecast of MSW generation obtained by the GRNN model. The existence of the so-called structural breaks that occur because of the economic crisis in the studied period (2000-2012) for each country was determined and confirmed using the Chow test and Quandt-Andrews test. Two GRNN models, one which did not take into account the influence of the economic crisis (GRNN) and another one which did (SB-GRNN), were developed. The novelty of the applied method is that it uses broadly available social, economic and demographic indicators and indicators of sustainability, together with GRNN and structural break testing for the prediction of MSW generation at the national level. The obtained results demonstrate that the SB-GRNN model provide more accurate predictions than the model which neglected structural breaks, with a mean absolute percentage error (MAPE) of 4.0 % compared to 6.7 % generated by the GRNN model. The proposed model enhanced with structural breaks can be a viable alternative for a more accurate prediction of MSW generation at the national level, especially for developing countries for which a lack of MSW data is notable.
PB  - Springer Heidelberg, Heidelberg
T2  - Environmental Science and Pollution Research
T1  - Prediction of municipal solid waste generation using artificial neural network approach enhanced by structural break analysis
EP  - 311
IS  - 1
SP  - 299
VL  - 24
DO  - 10.1007/s11356-016-7767-x
ER  - 

@article{
author = "Adamović, Vladimir M. and Antanasijević, Davor and Ristić, Mirjana and Perić-Grujić, Aleksandra and Pocajt, Viktor",
year = "2017",
abstract = "This paper presents the development of a general regression neural network (GRNN) model for the prediction of annual municipal solid waste (MSW) generation at the national level for 44 countries of different size, population and economic development level. Proper modelling of MSW generation is essential for the planning of MSW management system as well as for the simulation of various environmental impact scenarios. The main objective of this work was to examine the potential influence of economy crisis (global or local) on the forecast of MSW generation obtained by the GRNN model. The existence of the so-called structural breaks that occur because of the economic crisis in the studied period (2000-2012) for each country was determined and confirmed using the Chow test and Quandt-Andrews test. Two GRNN models, one which did not take into account the influence of the economic crisis (GRNN) and another one which did (SB-GRNN), were developed. The novelty of the applied method is that it uses broadly available social, economic and demographic indicators and indicators of sustainability, together with GRNN and structural break testing for the prediction of MSW generation at the national level. The obtained results demonstrate that the SB-GRNN model provide more accurate predictions than the model which neglected structural breaks, with a mean absolute percentage error (MAPE) of 4.0 % compared to 6.7 % generated by the GRNN model. The proposed model enhanced with structural breaks can be a viable alternative for a more accurate prediction of MSW generation at the national level, especially for developing countries for which a lack of MSW data is notable.",
publisher = "Springer Heidelberg, Heidelberg",
journal = "Environmental Science and Pollution Research",
title = "Prediction of municipal solid waste generation using artificial neural network approach enhanced by structural break analysis",
pages = "311-299",
number = "1",
volume = "24",
doi = "10.1007/s11356-016-7767-x"
}

Adamović, V. M., Antanasijević, D., Ristić, M., Perić-Grujić, A.,& Pocajt, V.. (2017). Prediction of municipal solid waste generation using artificial neural network approach enhanced by structural break analysis. in Environmental Science and Pollution Research
Springer Heidelberg, Heidelberg., 24(1), 299-311.
https://doi.org/10.1007/s11356-016-7767-x

Adamović VM, Antanasijević D, Ristić M, Perić-Grujić A, Pocajt V. Prediction of municipal solid waste generation using artificial neural network approach enhanced by structural break analysis. in Environmental Science and Pollution Research. 2017;24(1):299-311.
doi:10.1007/s11356-016-7767-x .

Adamović, Vladimir M., Antanasijević, Davor, Ristić, Mirjana, Perić-Grujić, Aleksandra, Pocajt, Viktor, "Prediction of municipal solid waste generation using artificial neural network approach enhanced by structural break analysis" in Environmental Science and Pollution Research, 24, no. 1 (2017):299-311,
https://doi.org/10.1007/s11356-016-7767-x . .

TY  - JOUR
AU  - Sekulić, Zoran
AU  - Antanasijević, Davor
AU  - Stevanović, S.
AU  - Trivunac, Katarina
PY  - 2017
UR  - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/3722
AB  - Complexation-microfiltration process for removal of heavy metal ions such as lead, cadmium and zinc from water had been investigated. Two soluble derivates of cellulose was selected as complexing agents. The dependence of the removal efficiency from the operating parameters (pH value, pressure, concentration of metal ion, concentration of complexing agent and type of counter ion) was established. Two approaches of preparation of input data and two different artificial neural network architectures, general regression neural network and back-propagation neural network have been used for modeling of experimental data. The extrapolation ability of selected architectures, i.e., the prediction of rejection coefficient with inputs beyond the calibration range of original model, was also determined. The predictions were successful, and after evaluation of performances, the models that were developed gave relatively good results of mean absolute percentage error from 4 to 14% and R-squared from 0.717 to 0.852 for general regression neural network and from 0.897 to 0.955 for back-propagation neural network.
PB  - Springer, New York
T2  - International Journal of Environmental Science and Technology
T1  - Application of artificial neural networks for estimating Cd, Zn, Pb removal efficiency from wastewater using complexation-microfiltration process
EP  - 1396
IS  - 7
SP  - 1383
VL  - 14
DO  - 10.1007/s13762-017-1248-8
ER  - 

@article{
author = "Sekulić, Zoran and Antanasijević, Davor and Stevanović, S. and Trivunac, Katarina",
year = "2017",
abstract = "Complexation-microfiltration process for removal of heavy metal ions such as lead, cadmium and zinc from water had been investigated. Two soluble derivates of cellulose was selected as complexing agents. The dependence of the removal efficiency from the operating parameters (pH value, pressure, concentration of metal ion, concentration of complexing agent and type of counter ion) was established. Two approaches of preparation of input data and two different artificial neural network architectures, general regression neural network and back-propagation neural network have been used for modeling of experimental data. The extrapolation ability of selected architectures, i.e., the prediction of rejection coefficient with inputs beyond the calibration range of original model, was also determined. The predictions were successful, and after evaluation of performances, the models that were developed gave relatively good results of mean absolute percentage error from 4 to 14% and R-squared from 0.717 to 0.852 for general regression neural network and from 0.897 to 0.955 for back-propagation neural network.",
publisher = "Springer, New York",
journal = "International Journal of Environmental Science and Technology",
title = "Application of artificial neural networks for estimating Cd, Zn, Pb removal efficiency from wastewater using complexation-microfiltration process",
pages = "1396-1383",
number = "7",
volume = "14",
doi = "10.1007/s13762-017-1248-8"
}

Sekulić, Z., Antanasijević, D., Stevanović, S.,& Trivunac, K.. (2017). Application of artificial neural networks for estimating Cd, Zn, Pb removal efficiency from wastewater using complexation-microfiltration process. in International Journal of Environmental Science and Technology
Springer, New York., 14(7), 1383-1396.
https://doi.org/10.1007/s13762-017-1248-8

Sekulić Z, Antanasijević D, Stevanović S, Trivunac K. Application of artificial neural networks for estimating Cd, Zn, Pb removal efficiency from wastewater using complexation-microfiltration process. in International Journal of Environmental Science and Technology. 2017;14(7):1383-1396.
doi:10.1007/s13762-017-1248-8 .

Sekulić, Zoran, Antanasijević, Davor, Stevanović, S., Trivunac, Katarina, "Application of artificial neural networks for estimating Cd, Zn, Pb removal efficiency from wastewater using complexation-microfiltration process" in International Journal of Environmental Science and Technology, 14, no. 7 (2017):1383-1396,
https://doi.org/10.1007/s13762-017-1248-8 . .

TY  - CHAP
AU  - Deljanin, Isidora
AU  - Antanasijević, Davor
AU  - Pocajt, Viktor
AU  - Perić-Grujić, Aleksandra
AU  - Ristić, Mirjana
PY  - 2016
UR  - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/3175
AB  - The global population growth, urbanization and the increased energy demand led to serious changes in the environment. Numerous anthropogenic activities release a variety of toxic and potentially toxic pollutants into the environment, some of which are heavy metals. Even though the global concern over their health impacts has been increasing over the last decades and the adverse effects of heavy metals have been thoroughly studied, heavy metal pollution is still one of the key environmental problems worldwide. Many regulations in this field in the past years contributed to the decrease of the emission of heavy metals; however, this kind of pollution still poses a health threat, especially in developing countries. Heavy metals are persistent in the environment and their elevated emission during longer period of time can cause contamination of the environment. They are emitted in all environmental media, but can also be easily transported between them due to the atmospheric deposition, water runoff, etc., and thus accumulate in the environment or penetrate the food chains. The main routes of human exposure to heavy metals are through ingestion, inhalation or via dermal contact. Hence, there is a need for better understanding of absorption, distribution and deposition of heavy metals in the human body. This information is of a crucial importance for the evaluation of heavy metal potential health implications. In this chapter, an overview of the heavy metal health hazards is presented as a consequence of heavy metal pollution, their availability and cycling between different media in the environment.
PB  - Nova Science Publishers, Inc.
T2  - Heavy Metals and Health
T1  - Health hazards of heavy metal pollution
EP  - 46
SP  - 1
UR  - https://hdl.handle.net/21.15107/rcub_technorep_3175
ER  - 

@inbook{
author = "Deljanin, Isidora and Antanasijević, Davor and Pocajt, Viktor and Perić-Grujić, Aleksandra and Ristić, Mirjana",
year = "2016",
abstract = "The global population growth, urbanization and the increased energy demand led to serious changes in the environment. Numerous anthropogenic activities release a variety of toxic and potentially toxic pollutants into the environment, some of which are heavy metals. Even though the global concern over their health impacts has been increasing over the last decades and the adverse effects of heavy metals have been thoroughly studied, heavy metal pollution is still one of the key environmental problems worldwide. Many regulations in this field in the past years contributed to the decrease of the emission of heavy metals; however, this kind of pollution still poses a health threat, especially in developing countries. Heavy metals are persistent in the environment and their elevated emission during longer period of time can cause contamination of the environment. They are emitted in all environmental media, but can also be easily transported between them due to the atmospheric deposition, water runoff, etc., and thus accumulate in the environment or penetrate the food chains. The main routes of human exposure to heavy metals are through ingestion, inhalation or via dermal contact. Hence, there is a need for better understanding of absorption, distribution and deposition of heavy metals in the human body. This information is of a crucial importance for the evaluation of heavy metal potential health implications. In this chapter, an overview of the heavy metal health hazards is presented as a consequence of heavy metal pollution, their availability and cycling between different media in the environment.",
publisher = "Nova Science Publishers, Inc.",
journal = "Heavy Metals and Health",
booktitle = "Health hazards of heavy metal pollution",
pages = "46-1",
url = "https://hdl.handle.net/21.15107/rcub_technorep_3175"
}

Deljanin, I., Antanasijević, D., Pocajt, V., Perić-Grujić, A.,& Ristić, M.. (2016). Health hazards of heavy metal pollution. in Heavy Metals and Health
Nova Science Publishers, Inc.., 1-46.
https://hdl.handle.net/21.15107/rcub_technorep_3175

Deljanin I, Antanasijević D, Pocajt V, Perić-Grujić A, Ristić M. Health hazards of heavy metal pollution. in Heavy Metals and Health. 2016;:1-46.
https://hdl.handle.net/21.15107/rcub_technorep_3175 .

Deljanin, Isidora, Antanasijević, Davor, Pocajt, Viktor, Perić-Grujić, Aleksandra, Ristić, Mirjana, "Health hazards of heavy metal pollution" in Heavy Metals and Health (2016):1-46,
https://hdl.handle.net/21.15107/rcub_technorep_3175 .

TY  - JOUR
AU  - Šiljić-Tomić, Aleksandra
AU  - Antanasijević, Davor
AU  - Ristić, Mirjana
AU  - Perić-Grujić, Aleksandra
AU  - Pocajt, Viktor
PY  - 2016
UR  - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/3254
AB  - This paper describes the application of artificial neural network models for the prediction of biological oxygen demand (BOD) levels in the Danube River. Eighteen regularly monitored water quality parameters at 17 stations on the river stretch passing through Serbia were used as input variables. The optimization of the model was performed in three consecutive steps: firstly, the spatial influence of a monitoring station was examined; secondly, the monitoring period necessary to reach satisfactory performance was determined; and lastly, correlation analysis was applied to evaluate the relationship among water quality parameters. Root-mean-square error (RMSE) was used to evaluate model performance in the first two steps, whereas in the last step, multiple statistical indicators of performance were utilized. As a result, two optimized models were developed, a general regression neural network model (labeled GRNN-1) that covers the monitoring stations from the Danube inflow to the city of Novi Sad and a GRNN model (labeled GRNN-2) that covers the stations from the city of Novi Sad to the border with Romania. Both models demonstrated good agreement between the predicted and actually observed BOD values.
PB  - Springer, Dordrecht
T2  - Environmental Monitoring and Assessment
T1  - Modeling the BOD of Danube River in Serbia using spatial, temporal, and input variables optimized artificial neural network models
IS  - 5
VL  - 188
DO  - 10.1007/s10661-016-5308-1
ER  - 

@article{
author = "Šiljić-Tomić, Aleksandra and Antanasijević, Davor and Ristić, Mirjana and Perić-Grujić, Aleksandra and Pocajt, Viktor",
year = "2016",
abstract = "This paper describes the application of artificial neural network models for the prediction of biological oxygen demand (BOD) levels in the Danube River. Eighteen regularly monitored water quality parameters at 17 stations on the river stretch passing through Serbia were used as input variables. The optimization of the model was performed in three consecutive steps: firstly, the spatial influence of a monitoring station was examined; secondly, the monitoring period necessary to reach satisfactory performance was determined; and lastly, correlation analysis was applied to evaluate the relationship among water quality parameters. Root-mean-square error (RMSE) was used to evaluate model performance in the first two steps, whereas in the last step, multiple statistical indicators of performance were utilized. As a result, two optimized models were developed, a general regression neural network model (labeled GRNN-1) that covers the monitoring stations from the Danube inflow to the city of Novi Sad and a GRNN model (labeled GRNN-2) that covers the stations from the city of Novi Sad to the border with Romania. Both models demonstrated good agreement between the predicted and actually observed BOD values.",
publisher = "Springer, Dordrecht",
journal = "Environmental Monitoring and Assessment",
title = "Modeling the BOD of Danube River in Serbia using spatial, temporal, and input variables optimized artificial neural network models",
number = "5",
volume = "188",
doi = "10.1007/s10661-016-5308-1"
}

Šiljić-Tomić, A., Antanasijević, D., Ristić, M., Perić-Grujić, A.,& Pocajt, V.. (2016). Modeling the BOD of Danube River in Serbia using spatial, temporal, and input variables optimized artificial neural network models. in Environmental Monitoring and Assessment
Springer, Dordrecht., 188(5).
https://doi.org/10.1007/s10661-016-5308-1

Šiljić-Tomić A, Antanasijević D, Ristić M, Perić-Grujić A, Pocajt V. Modeling the BOD of Danube River in Serbia using spatial, temporal, and input variables optimized artificial neural network models. in Environmental Monitoring and Assessment. 2016;188(5).
doi:10.1007/s10661-016-5308-1 .

Šiljić-Tomić, Aleksandra, Antanasijević, Davor, Ristić, Mirjana, Perić-Grujić, Aleksandra, Pocajt, Viktor, "Modeling the BOD of Danube River in Serbia using spatial, temporal, and input variables optimized artificial neural network models" in Environmental Monitoring and Assessment, 188, no. 5 (2016),
https://doi.org/10.1007/s10661-016-5308-1 . .

TY  - JOUR
AU  - Crnković, Dragan
AU  - Antanasijević, Davor
AU  - Pocajt, Viktor
AU  - Perić-Grujić, Aleksandra
AU  - Antonović, Dušan
AU  - Ristić, Mirjana
PY  - 2016
UR  - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/3274
AB  - The aim of this study was to evaluate the quality of freshwater sediments by means of three chemometric techniques for multi-criteria analysis and decision: self-organizing network (SON), self-organizing map (SOM) and PROMETHEE&GAIA (Preference Ranking Organization Method for Enrichment Evaluation with Geometrical Analysis for Interactive Aid). Selected chemometric techniques were applied to the results of Pb, Cd, Zn, Cu, Ni, Cr, Hg and As content in thirty Danube and fourteen Sava river sediment samples from Serbia. The potential toxicity of sediments was estimated using Probable Effect Concentrations quotients (mean PEC-Q). According to the SON analysis the Danube sediment samples were divided into three classes, Class I (mean PEC-Q range 0.27-0.51), Class II (mean PEC-Qrange 0:50-0.70), and Class III (mean PEC-Qrange 0.77-0.97), while the Sava samples were divided into two classes, Class II (two samples, mean PEC-Qvalues 0.65 and 0.69) and Class III (mean PEC-Q range 0.69-1.00). Using the SOM cluster analysis, both Danube and Sava sediment samples were classified into five subclusters, on the basis of the metal concentration level and further ranked into three levels (for remediation, moderately polluted and not polluted) by the use of multi-criteria ranking PROMETHEE method. Graphical presentation of the results obtained by PROMETHEE method using GAIA descriptive tool has provided an insight into the distribution of examined elements in sediments and has shown a significant correlation between some elements. On the basis of the results obtained, it has been concluded that the proposed chemometric approach could provide useful information in the sediment quality assessment.
PB  - Elsevier, Amsterdam
T2  - Catena
T1  - Unsupervised classification and multi-criteria decision analysis as chemometric tools for the assessment of sediment quality: A case study of the Danube and Sava River
EP  - 22
SP  - 11
VL  - 144
DO  - 10.1016/j.catena.2016.04.025
ER  - 

@article{
author = "Crnković, Dragan and Antanasijević, Davor and Pocajt, Viktor and Perić-Grujić, Aleksandra and Antonović, Dušan and Ristić, Mirjana",
year = "2016",
abstract = "The aim of this study was to evaluate the quality of freshwater sediments by means of three chemometric techniques for multi-criteria analysis and decision: self-organizing network (SON), self-organizing map (SOM) and PROMETHEE&GAIA (Preference Ranking Organization Method for Enrichment Evaluation with Geometrical Analysis for Interactive Aid). Selected chemometric techniques were applied to the results of Pb, Cd, Zn, Cu, Ni, Cr, Hg and As content in thirty Danube and fourteen Sava river sediment samples from Serbia. The potential toxicity of sediments was estimated using Probable Effect Concentrations quotients (mean PEC-Q). According to the SON analysis the Danube sediment samples were divided into three classes, Class I (mean PEC-Q range 0.27-0.51), Class II (mean PEC-Qrange 0:50-0.70), and Class III (mean PEC-Qrange 0.77-0.97), while the Sava samples were divided into two classes, Class II (two samples, mean PEC-Qvalues 0.65 and 0.69) and Class III (mean PEC-Q range 0.69-1.00). Using the SOM cluster analysis, both Danube and Sava sediment samples were classified into five subclusters, on the basis of the metal concentration level and further ranked into three levels (for remediation, moderately polluted and not polluted) by the use of multi-criteria ranking PROMETHEE method. Graphical presentation of the results obtained by PROMETHEE method using GAIA descriptive tool has provided an insight into the distribution of examined elements in sediments and has shown a significant correlation between some elements. On the basis of the results obtained, it has been concluded that the proposed chemometric approach could provide useful information in the sediment quality assessment.",
publisher = "Elsevier, Amsterdam",
journal = "Catena",
title = "Unsupervised classification and multi-criteria decision analysis as chemometric tools for the assessment of sediment quality: A case study of the Danube and Sava River",
pages = "22-11",
volume = "144",
doi = "10.1016/j.catena.2016.04.025"
}

Crnković, D., Antanasijević, D., Pocajt, V., Perić-Grujić, A., Antonović, D.,& Ristić, M.. (2016). Unsupervised classification and multi-criteria decision analysis as chemometric tools for the assessment of sediment quality: A case study of the Danube and Sava River. in Catena
Elsevier, Amsterdam., 144, 11-22.
https://doi.org/10.1016/j.catena.2016.04.025

Crnković D, Antanasijević D, Pocajt V, Perić-Grujić A, Antonović D, Ristić M. Unsupervised classification and multi-criteria decision analysis as chemometric tools for the assessment of sediment quality: A case study of the Danube and Sava River. in Catena. 2016;144:11-22.
doi:10.1016/j.catena.2016.04.025 .

Crnković, Dragan, Antanasijević, Davor, Pocajt, Viktor, Perić-Grujić, Aleksandra, Antonović, Dušan, Ristić, Mirjana, "Unsupervised classification and multi-criteria decision analysis as chemometric tools for the assessment of sediment quality: A case study of the Danube and Sava River" in Catena, 144 (2016):11-22,
https://doi.org/10.1016/j.catena.2016.04.025 . .

TY  - JOUR
AU  - Stamenković, Lidija J.
AU  - Antanasijević, Davor
AU  - Ristić, Mirjana
AU  - Perić-Grujić, Aleksandra
AU  - Pocajt, Viktor
PY  - 2016
UR  - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/3279
AB  - This paper describes the development of an artificial neural network (ANN) model based on economical and sustainability indicators for the prediction of annual non-methane volatile organic compounds (NMVOCs) emissions in China for the period 2005-2011 and its comparison with inventory emission factor models. The NMVOCs emissions in China were estimated using ANN model which was created using available data for nine European countries, which NMVOC emission per capita approximately correspond to the Chinese emissions, for the period 2004-2012. The forward input selection strategy was used to compare the significance of particular inputs for the prediction of NMVOC emissions in the nine selected EU countries and China. The final ANN model was trained using only five input variables, and it has demonstrated similar accuracy in predicting NMVOC emissions for the selected EU countries that were used for the development of the model and then for China for which the input dataset was previously unknown to the ANN model. The obtained mean absolute percentage error (MAPE) values were 8 % for EU countries and 5 % for China. Also, the temporal trend of NMVOC emissions predicted in this study is generally consistent with the trend obtained using inventory emission models. The proposed ANN approach can represent a viable alternative for the prediction of NMVOC emissions at the national level, in particular for developing countries which are usually lacking emission data.
PB  - Springer Heidelberg, Heidelberg
T2  - Environmental Science and Pollution Research
T1  - Estimation of NMVOC emissions using artificial neural networks and economical and sustainability indicators as inputs
EP  - 10762
IS  - 11
SP  - 10753
VL  - 23
DO  - 10.1007/s11356-016-6279-z
ER  - 

@article{
author = "Stamenković, Lidija J. and Antanasijević, Davor and Ristić, Mirjana and Perić-Grujić, Aleksandra and Pocajt, Viktor",
year = "2016",
abstract = "This paper describes the development of an artificial neural network (ANN) model based on economical and sustainability indicators for the prediction of annual non-methane volatile organic compounds (NMVOCs) emissions in China for the period 2005-2011 and its comparison with inventory emission factor models. The NMVOCs emissions in China were estimated using ANN model which was created using available data for nine European countries, which NMVOC emission per capita approximately correspond to the Chinese emissions, for the period 2004-2012. The forward input selection strategy was used to compare the significance of particular inputs for the prediction of NMVOC emissions in the nine selected EU countries and China. The final ANN model was trained using only five input variables, and it has demonstrated similar accuracy in predicting NMVOC emissions for the selected EU countries that were used for the development of the model and then for China for which the input dataset was previously unknown to the ANN model. The obtained mean absolute percentage error (MAPE) values were 8 % for EU countries and 5 % for China. Also, the temporal trend of NMVOC emissions predicted in this study is generally consistent with the trend obtained using inventory emission models. The proposed ANN approach can represent a viable alternative for the prediction of NMVOC emissions at the national level, in particular for developing countries which are usually lacking emission data.",
publisher = "Springer Heidelberg, Heidelberg",
journal = "Environmental Science and Pollution Research",
title = "Estimation of NMVOC emissions using artificial neural networks and economical and sustainability indicators as inputs",
pages = "10762-10753",
number = "11",
volume = "23",
doi = "10.1007/s11356-016-6279-z"
}

Stamenković, L. J., Antanasijević, D., Ristić, M., Perić-Grujić, A.,& Pocajt, V.. (2016). Estimation of NMVOC emissions using artificial neural networks and economical and sustainability indicators as inputs. in Environmental Science and Pollution Research
Springer Heidelberg, Heidelberg., 23(11), 10753-10762.
https://doi.org/10.1007/s11356-016-6279-z

Stamenković LJ, Antanasijević D, Ristić M, Perić-Grujić A, Pocajt V. Estimation of NMVOC emissions using artificial neural networks and economical and sustainability indicators as inputs. in Environmental Science and Pollution Research. 2016;23(11):10753-10762.
doi:10.1007/s11356-016-6279-z .

Stamenković, Lidija J., Antanasijević, Davor, Ristić, Mirjana, Perić-Grujić, Aleksandra, Pocajt, Viktor, "Estimation of NMVOC emissions using artificial neural networks and economical and sustainability indicators as inputs" in Environmental Science and Pollution Research, 23, no. 11 (2016):10753-10762,
https://doi.org/10.1007/s11356-016-6279-z . .

TY  - JOUR
AU  - Antanasijević, Jelena
AU  - Pocajt, Viktor
AU  - Antanasijević, Davor
AU  - Trišović, Nemanja
AU  - Fodor-Csorba, Katalin
PY  - 2016
UR  - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/3284
AB  - Accurate prediction of transition temperature is very helpful for the design of new liquid crystals (LCs) because even small changes in structure can dramatically alter the transition temperature, and therefore the synthesis of LCs should not be governed only by chemical intuition. A quantitative structure-property relationship (QSPR) study was performed on 243 five-ring bent-core LCs in order to predict their clearing temperatures using molecular descriptors. Decision tree and multivariate adaptive regression splines (MARS), techniques well suited for high-dimensional data analysis, were applied to select important descriptors (dimension reduction) and to generate nonlinear models. These techniques were applied both on two-dimensional (2D) descriptors only and on the pool of 2D and 3D descriptors (2& 3D). The obtained QSPR models were tested using 15% of available data, and their performance and ability to generalise were analysed using multiple statistical metrics. The best results for the external test set were obtained using the MARS model created with 2& 3D descriptors, with a high correlation coefficient of r = 0.95 and a root mean squared error of 7.41 K. All metrics suggest that the proposed QSPR model, generated by MARS, is a robust and satisfactorily accurate approach for the prediction of clearing temperatures of bent-core LCs. [GRAPHICS] .
PB  - Taylor & Francis Ltd, Abingdon
T2  - Liquid Crystals
T1  - Prediction of clearing temperatures of bent-core liquid crystals using decision trees and multivariate adaptive regression splines
EP  - 1037
IS  - 8
SP  - 1028
VL  - 43
DO  - 10.1080/02678292.2016.1155769
ER  - 

@article{
author = "Antanasijević, Jelena and Pocajt, Viktor and Antanasijević, Davor and Trišović, Nemanja and Fodor-Csorba, Katalin",
year = "2016",
abstract = "Accurate prediction of transition temperature is very helpful for the design of new liquid crystals (LCs) because even small changes in structure can dramatically alter the transition temperature, and therefore the synthesis of LCs should not be governed only by chemical intuition. A quantitative structure-property relationship (QSPR) study was performed on 243 five-ring bent-core LCs in order to predict their clearing temperatures using molecular descriptors. Decision tree and multivariate adaptive regression splines (MARS), techniques well suited for high-dimensional data analysis, were applied to select important descriptors (dimension reduction) and to generate nonlinear models. These techniques were applied both on two-dimensional (2D) descriptors only and on the pool of 2D and 3D descriptors (2& 3D). The obtained QSPR models were tested using 15% of available data, and their performance and ability to generalise were analysed using multiple statistical metrics. The best results for the external test set were obtained using the MARS model created with 2& 3D descriptors, with a high correlation coefficient of r = 0.95 and a root mean squared error of 7.41 K. All metrics suggest that the proposed QSPR model, generated by MARS, is a robust and satisfactorily accurate approach for the prediction of clearing temperatures of bent-core LCs. [GRAPHICS] .",
publisher = "Taylor & Francis Ltd, Abingdon",
journal = "Liquid Crystals",
title = "Prediction of clearing temperatures of bent-core liquid crystals using decision trees and multivariate adaptive regression splines",
pages = "1037-1028",
number = "8",
volume = "43",
doi = "10.1080/02678292.2016.1155769"
}

Antanasijević, J., Pocajt, V., Antanasijević, D., Trišović, N.,& Fodor-Csorba, K.. (2016). Prediction of clearing temperatures of bent-core liquid crystals using decision trees and multivariate adaptive regression splines. in Liquid Crystals
Taylor & Francis Ltd, Abingdon., 43(8), 1028-1037.
https://doi.org/10.1080/02678292.2016.1155769

Antanasijević J, Pocajt V, Antanasijević D, Trišović N, Fodor-Csorba K. Prediction of clearing temperatures of bent-core liquid crystals using decision trees and multivariate adaptive regression splines. in Liquid Crystals. 2016;43(8):1028-1037.
doi:10.1080/02678292.2016.1155769 .

Antanasijević, Jelena, Pocajt, Viktor, Antanasijević, Davor, Trišović, Nemanja, Fodor-Csorba, Katalin, "Prediction of clearing temperatures of bent-core liquid crystals using decision trees and multivariate adaptive regression splines" in Liquid Crystals, 43, no. 8 (2016):1028-1037,
https://doi.org/10.1080/02678292.2016.1155769 . .