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  - 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  - 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  - 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  - 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  - 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 . .

TY  - JOUR
AU  - Antanasijević, Davor
AU  - Antanasijević, Jelena
AU  - Pocajt, Viktor
AU  - Ušćumlić, Gordana
PY  - 2016
UR  - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/3305
AB  - A novel strategy for the prediction of the transition temperature of bent-core liquid crystals (LCs) based on the combination of multi filter feature selection and group method of data handling (GMDH) type neural networks is reported. An entire set of 243 compounds was randomly divided into a training set of 207 compounds and a test set of 36 compounds. Descriptors were selected from a pool of 2D, and two pools of 2D and 3D ones, optimized by molecular mechanics (MM) and semi-empirical (SE) method. The reduction of the pool of descriptors was performed using multi filters based on chi square and v-WSH algorithm, while the final subset selection was performed by GMDH algorithm during the learning process. The obtained 2D, MM and SE GMDH models have 11, 13 and 16 descriptors, respectively, and demonstrate good generalization and predictive ability (R-2 = 0.92). The final models were subjected to a randomization test for validation purpose. Those models appear to be not only suitable for prediction, but they also allow the identification of key structural features that alter the transition temperature of bent-core LCs.
PB  - Royal Society of Chemistry
T2  - RSC Advances
T1  - A GMDH-type neural network with multi-filter feature selection for the prediction of transition temperatures of bent-core liquid crystals
EP  - 99684
IS  - 102
SP  - 99676
VL  - 6
DO  - 10.1039/c6ra15056j
ER  - 

@article{
author = "Antanasijević, Davor and Antanasijević, Jelena and Pocajt, Viktor and Ušćumlić, Gordana",
year = "2016",
abstract = "A novel strategy for the prediction of the transition temperature of bent-core liquid crystals (LCs) based on the combination of multi filter feature selection and group method of data handling (GMDH) type neural networks is reported. An entire set of 243 compounds was randomly divided into a training set of 207 compounds and a test set of 36 compounds. Descriptors were selected from a pool of 2D, and two pools of 2D and 3D ones, optimized by molecular mechanics (MM) and semi-empirical (SE) method. The reduction of the pool of descriptors was performed using multi filters based on chi square and v-WSH algorithm, while the final subset selection was performed by GMDH algorithm during the learning process. The obtained 2D, MM and SE GMDH models have 11, 13 and 16 descriptors, respectively, and demonstrate good generalization and predictive ability (R-2 = 0.92). The final models were subjected to a randomization test for validation purpose. Those models appear to be not only suitable for prediction, but they also allow the identification of key structural features that alter the transition temperature of bent-core LCs.",
publisher = "Royal Society of Chemistry",
journal = "RSC Advances",
title = "A GMDH-type neural network with multi-filter feature selection for the prediction of transition temperatures of bent-core liquid crystals",
pages = "99684-99676",
number = "102",
volume = "6",
doi = "10.1039/c6ra15056j"
}

Antanasijević, D., Antanasijević, J., Pocajt, V.,& Ušćumlić, G.. (2016). A GMDH-type neural network with multi-filter feature selection for the prediction of transition temperatures of bent-core liquid crystals. in RSC Advances
Royal Society of Chemistry., 6(102), 99676-99684.
https://doi.org/10.1039/c6ra15056j

Antanasijević D, Antanasijević J, Pocajt V, Ušćumlić G. A GMDH-type neural network with multi-filter feature selection for the prediction of transition temperatures of bent-core liquid crystals. in RSC Advances. 2016;6(102):99676-99684.
doi:10.1039/c6ra15056j .

Antanasijević, Davor, Antanasijević, Jelena, Pocajt, Viktor, Ušćumlić, Gordana, "A GMDH-type neural network with multi-filter feature selection for the prediction of transition temperatures of bent-core liquid crystals" in RSC Advances, 6, no. 102 (2016):99676-99684,
https://doi.org/10.1039/c6ra15056j . .

TY  - JOUR
AU  - Šiljić-Tomić, Aleksandra
AU  - Antanasijević, Davor
AU  - Perić-Grujić, Aleksandra
AU  - Ristić, Mirjana
AU  - Pocajt, Viktor
PY  - 2016
UR  - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/3368
PB  - Springer Heidelberg, Heidelberg
T2  - Environmental Science and Pollution Research
T1  - Response to comment of Taher Rajaee and Salar Khani on "Artificial neural network modelling of biological oxygen demand in rivers at the national level with input selection based on Monte Carlo simulations" [Siljic et al., Environ Sci Pollut Res (2015) 22
EP  - +
IS  - 4
SP  - 3978
VL  - 23
DO  - 10.1007/s11356-015-5978-1
ER  - 

@article{
author = "Šiljić-Tomić, Aleksandra and Antanasijević, Davor and Perić-Grujić, Aleksandra and Ristić, Mirjana and Pocajt, Viktor",
year = "2016",
publisher = "Springer Heidelberg, Heidelberg",
journal = "Environmental Science and Pollution Research",
title = "Response to comment of Taher Rajaee and Salar Khani on "Artificial neural network modelling of biological oxygen demand in rivers at the national level with input selection based on Monte Carlo simulations" [Siljic et al., Environ Sci Pollut Res (2015) 22",
pages = "+-3978",
number = "4",
volume = "23",
doi = "10.1007/s11356-015-5978-1"
}

Šiljić-Tomić, A., Antanasijević, D., Perić-Grujić, A., Ristić, M.,& Pocajt, V.. (2016). Response to comment of Taher Rajaee and Salar Khani on "Artificial neural network modelling of biological oxygen demand in rivers at the national level with input selection based on Monte Carlo simulations" [Siljic et al., Environ Sci Pollut Res (2015) 22. in Environmental Science and Pollution Research
Springer Heidelberg, Heidelberg., 23(4), 3978-+.
https://doi.org/10.1007/s11356-015-5978-1

Šiljić-Tomić A, Antanasijević D, Perić-Grujić A, Ristić M, Pocajt V. Response to comment of Taher Rajaee and Salar Khani on "Artificial neural network modelling of biological oxygen demand in rivers at the national level with input selection based on Monte Carlo simulations" [Siljic et al., Environ Sci Pollut Res (2015) 22. in Environmental Science and Pollution Research. 2016;23(4):3978-+.
doi:10.1007/s11356-015-5978-1 .

Šiljić-Tomić, Aleksandra, Antanasijević, Davor, Perić-Grujić, Aleksandra, Ristić, Mirjana, Pocajt, Viktor, "Response to comment of Taher Rajaee and Salar Khani on "Artificial neural network modelling of biological oxygen demand in rivers at the national level with input selection based on Monte Carlo simulations" [Siljic et al., Environ Sci Pollut Res (2015) 22" in Environmental Science and Pollution Research, 23, no. 4 (2016):3978-+,
https://doi.org/10.1007/s11356-015-5978-1 . .

TY  - JOUR
AU  - Antanasijević, Jelena
AU  - Antanasijević, Davor
AU  - Pocajt, Viktor
AU  - Trišović, Nemanja
AU  - Fodor-Csorba, Katalin
PY  - 2016
UR  - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/3392
AB  - Accelerating progress in the discovery of new bent-core liquid crystal (LC) materials with enhanced features relies on the understanding of structure-property relationships that underline the formation of LC phases. The aim of this study was to develop a model for the prediction of LC behaviour of five-ring bent-core systems using a QSPR approach that combines dimension reduction techniques (e.g. genetic algorithms etc.) for the selection of molecular descriptors and decision trees, multivariate adaptive regression splines (MARS) and artificial neural networks (ANN) as classification methods. A total of 27 models based on separate pools of calculated molecular descriptors (2D; 2D and 3D) and published experimental outcomes were evaluated. Overall, the results suggest that the acquired ANN LC classifiers are usable for the prediction of LC behaviour. The best of these models showed high accuracy and precision (91% and 97%). Since the best classifier is able to successfully capture trends in a homologous series, it can be used not only to screen new bent-core structures for potential LCs, but also for the estimation of influence of structural modifications on LC phase formation, as well as for the evaluation of LC phase stability.
PB  - Royal Society of Chemistry
T2  - RSC Advances
T1  - A QSPR study on the liquid crystallinity of five-ring bent-core molecules using decision trees, MARS and artificial neural networks
EP  - 18464
IS  - 22
SP  - 18452
VL  - 6
DO  - 10.1039/c5ra20775d
ER  - 

@article{
author = "Antanasijević, Jelena and Antanasijević, Davor and Pocajt, Viktor and Trišović, Nemanja and Fodor-Csorba, Katalin",
year = "2016",
abstract = "Accelerating progress in the discovery of new bent-core liquid crystal (LC) materials with enhanced features relies on the understanding of structure-property relationships that underline the formation of LC phases. The aim of this study was to develop a model for the prediction of LC behaviour of five-ring bent-core systems using a QSPR approach that combines dimension reduction techniques (e.g. genetic algorithms etc.) for the selection of molecular descriptors and decision trees, multivariate adaptive regression splines (MARS) and artificial neural networks (ANN) as classification methods. A total of 27 models based on separate pools of calculated molecular descriptors (2D; 2D and 3D) and published experimental outcomes were evaluated. Overall, the results suggest that the acquired ANN LC classifiers are usable for the prediction of LC behaviour. The best of these models showed high accuracy and precision (91% and 97%). Since the best classifier is able to successfully capture trends in a homologous series, it can be used not only to screen new bent-core structures for potential LCs, but also for the estimation of influence of structural modifications on LC phase formation, as well as for the evaluation of LC phase stability.",
publisher = "Royal Society of Chemistry",
journal = "RSC Advances",
title = "A QSPR study on the liquid crystallinity of five-ring bent-core molecules using decision trees, MARS and artificial neural networks",
pages = "18464-18452",
number = "22",
volume = "6",
doi = "10.1039/c5ra20775d"
}

Antanasijević, J., Antanasijević, D., Pocajt, V., Trišović, N.,& Fodor-Csorba, K.. (2016). A QSPR study on the liquid crystallinity of five-ring bent-core molecules using decision trees, MARS and artificial neural networks. in RSC Advances
Royal Society of Chemistry., 6(22), 18452-18464.
https://doi.org/10.1039/c5ra20775d

Antanasijević J, Antanasijević D, Pocajt V, Trišović N, Fodor-Csorba K. A QSPR study on the liquid crystallinity of five-ring bent-core molecules using decision trees, MARS and artificial neural networks. in RSC Advances. 2016;6(22):18452-18464.
doi:10.1039/c5ra20775d .

Antanasijević, Jelena, Antanasijević, Davor, Pocajt, Viktor, Trišović, Nemanja, Fodor-Csorba, Katalin, "A QSPR study on the liquid crystallinity of five-ring bent-core molecules using decision trees, MARS and artificial neural networks" in RSC Advances, 6, no. 22 (2016):18452-18464,
https://doi.org/10.1039/c5ra20775d . .

TY  - JOUR
AU  - Stamenković, Lidija J.
AU  - Antanasijević, Davor
AU  - Ristić, Mirjana
AU  - Perić-Grujić, Aleksandra
AU  - Pocajt, Viktor
PY  - 2015
UR  - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/2954
AB  - The aim of this work was to create an ANN model for the prediction of GHG emissions in the Republic of Serbia in the period 1995-2013. Because of the lack of GHG emission data and inputs for Serbia, the ANN model was initially developed for Bulgaria, using the gross domestic product per capita (GDP) and annual energy production per capita (GPE) as inputs. The model was trained and validated with the data for Bulgaria for the period from 1990 to 2011,using Recurrent Neural Network (RNN) architecture. The results obtained for Serbia indicate a good agreement between the calculated and predicted GHG emissions in 1998, with an error of only 3%. The predicted change in the emission of GHG in the studied period is in agreement with social and economical factors that can be related to the changes in GHG emissions(e.g. emission reduction of about 10% in 1999). The RNN model predicts that the GHG emissions in 2013was above the level in 1998, but still lower than the GHG emissions calculated for the year 1990.
AB  - Cilj ovog rada je bio kreiranje modela, zasnovanog na veštačkim neuronskim mrežama, za predviđanje emisije GHG u Republici Srbiji. Zbog nedostatka podataka o GHG emisiji u Republici Srbiji, model je razvijen korišćenjem podataka za Republiku Bugarsku, a zatim je primenjen i na Republiku Srbiju. Kao ulazni parametri korišćeni su bruto d omaći proizvod po stanovniku (BDP) i godišnja proizvodnja energije po stanovniku (GPE). Model je treniran i testiran sa podacima za Bugarsku za period od 1990 do 2011. godine, pri čemu je korišćena rekurentna neuronska mreža (RNN). Rezultati za Republiku Srbiju pokazuju dobro slaganje između proračunate i modelom predviđene vrednosti emisije GHG za 1998. godinu, sa odstupanjem od svega 3%. Analiza predviđenog trenda ukazuje na promene u emisiji koje su bile posledica društvenih okolnosti (smanjenje emisije od oko 10% tokom 1999. godine). Model pokazuje da je emisija GHG-a u 2013. godini prestigla nivo iz 1998. godine, ali će i dalje biti ispod vrednosti emisije proračunate za 1990. godinu.
PB  - Naučno-stručno društvo za zaštitu životne sredine Srbije - Ecologica, Beograd
T2  - Ecologica
T1  - Estimation of GHG emission in Serbia for period 1995-2013 using recurent neural networks
T1  - Emisije gasova staklene bašte u Srbiji za period 1995-2013. godina primenom rekurentnih neuronskih mreža
EP  - 492
IS  - 79
SP  - 488
VL  - 22
UR  - https://hdl.handle.net/21.15107/rcub_technorep_2954
ER  - 

@article{
author = "Stamenković, Lidija J. and Antanasijević, Davor and Ristić, Mirjana and Perić-Grujić, Aleksandra and Pocajt, Viktor",
year = "2015",
abstract = "The aim of this work was to create an ANN model for the prediction of GHG emissions in the Republic of Serbia in the period 1995-2013. Because of the lack of GHG emission data and inputs for Serbia, the ANN model was initially developed for Bulgaria, using the gross domestic product per capita (GDP) and annual energy production per capita (GPE) as inputs. The model was trained and validated with the data for Bulgaria for the period from 1990 to 2011,using Recurrent Neural Network (RNN) architecture. The results obtained for Serbia indicate a good agreement between the calculated and predicted GHG emissions in 1998, with an error of only 3%. The predicted change in the emission of GHG in the studied period is in agreement with social and economical factors that can be related to the changes in GHG emissions(e.g. emission reduction of about 10% in 1999). The RNN model predicts that the GHG emissions in 2013was above the level in 1998, but still lower than the GHG emissions calculated for the year 1990., Cilj ovog rada je bio kreiranje modela, zasnovanog na veštačkim neuronskim mrežama, za predviđanje emisije GHG u Republici Srbiji. Zbog nedostatka podataka o GHG emisiji u Republici Srbiji, model je razvijen korišćenjem podataka za Republiku Bugarsku, a zatim je primenjen i na Republiku Srbiju. Kao ulazni parametri korišćeni su bruto d omaći proizvod po stanovniku (BDP) i godišnja proizvodnja energije po stanovniku (GPE). Model je treniran i testiran sa podacima za Bugarsku za period od 1990 do 2011. godine, pri čemu je korišćena rekurentna neuronska mreža (RNN). Rezultati za Republiku Srbiju pokazuju dobro slaganje između proračunate i modelom predviđene vrednosti emisije GHG za 1998. godinu, sa odstupanjem od svega 3%. Analiza predviđenog trenda ukazuje na promene u emisiji koje su bile posledica društvenih okolnosti (smanjenje emisije od oko 10% tokom 1999. godine). Model pokazuje da je emisija GHG-a u 2013. godini prestigla nivo iz 1998. godine, ali će i dalje biti ispod vrednosti emisije proračunate za 1990. godinu.",
publisher = "Naučno-stručno društvo za zaštitu životne sredine Srbije - Ecologica, Beograd",
journal = "Ecologica",
title = "Estimation of GHG emission in Serbia for period 1995-2013 using recurent neural networks, Emisije gasova staklene bašte u Srbiji za period 1995-2013. godina primenom rekurentnih neuronskih mreža",
pages = "492-488",
number = "79",
volume = "22",
url = "https://hdl.handle.net/21.15107/rcub_technorep_2954"
}

Stamenković, L. J., Antanasijević, D., Ristić, M., Perić-Grujić, A.,& Pocajt, V.. (2015). Estimation of GHG emission in Serbia for period 1995-2013 using recurent neural networks. in Ecologica
Naučno-stručno društvo za zaštitu životne sredine Srbije - Ecologica, Beograd., 22(79), 488-492.
https://hdl.handle.net/21.15107/rcub_technorep_2954

Stamenković LJ, Antanasijević D, Ristić M, Perić-Grujić A, Pocajt V. Estimation of GHG emission in Serbia for period 1995-2013 using recurent neural networks. in Ecologica. 2015;22(79):488-492.
https://hdl.handle.net/21.15107/rcub_technorep_2954 .

Stamenković, Lidija J., Antanasijević, Davor, Ristić, Mirjana, Perić-Grujić, Aleksandra, Pocajt, Viktor, "Estimation of GHG emission in Serbia for period 1995-2013 using recurent neural networks" in Ecologica, 22, no. 79 (2015):488-492,
https://hdl.handle.net/21.15107/rcub_technorep_2954 .

TY  - JOUR
AU  - Antanasijević, Davor
AU  - Pocajt, Viktor
AU  - Ristić, Mirjana
AU  - Perić-Grujić, Aleksandra
PY  - 2015
UR  - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/2987
AB  - This paper presents a new approach for the estimation of energy-related GHG (greenhouse gas) emissions at the national level that combines the simplicity of the concept of GHG intensity and the generalization capabilities of ANNs (artificial neural networks). The main objectives of this work includes the determination of the accuracy of a GRNN (general regression neural network) model applied for the prediction of EC (energy consumption) and GHG intensity of energy consumption, utilizing general country statistics as inputs, as well as analysis of the accuracy of energy-related GHG emissions obtained by multiplying the two aforementioned outputs. The models were developed using historical data from the period 2004-2012, for a set of 26 European countries (EU Members). The obtained results demonstrate that the GRNN GHG intensity model provides a more accurate prediction, with the MAPE (mean absolute percentage error) of 4.5%, than tested MLR (multiple linear regression) and second-order and third-order non-linear MPR (multiple polynomial regression) models. Also, the GRNN EC model has high accuracy (MAPE = 3.6%), and therefore both GRNN models and the proposed approach can be considered as suitable for the calculation of GHG emissions. The energy-related predicted GHG emissions were very similar to the actual GHG emissions of EU Members (MAPE = 6.4%).
PB  - Pergamon-Elsevier Science Ltd, Oxford
T2  - Energy
T1  - Modeling of energy consumption and related GHG (greenhouse gas) intensity and emissions in Europe using general regression neural networks
EP  - 824
SP  - 816
VL  - 84
DO  - 10.1016/j.energy.2015.03.060
ER  - 

@article{
author = "Antanasijević, Davor and Pocajt, Viktor and Ristić, Mirjana and Perić-Grujić, Aleksandra",
year = "2015",
abstract = "This paper presents a new approach for the estimation of energy-related GHG (greenhouse gas) emissions at the national level that combines the simplicity of the concept of GHG intensity and the generalization capabilities of ANNs (artificial neural networks). The main objectives of this work includes the determination of the accuracy of a GRNN (general regression neural network) model applied for the prediction of EC (energy consumption) and GHG intensity of energy consumption, utilizing general country statistics as inputs, as well as analysis of the accuracy of energy-related GHG emissions obtained by multiplying the two aforementioned outputs. The models were developed using historical data from the period 2004-2012, for a set of 26 European countries (EU Members). The obtained results demonstrate that the GRNN GHG intensity model provides a more accurate prediction, with the MAPE (mean absolute percentage error) of 4.5%, than tested MLR (multiple linear regression) and second-order and third-order non-linear MPR (multiple polynomial regression) models. Also, the GRNN EC model has high accuracy (MAPE = 3.6%), and therefore both GRNN models and the proposed approach can be considered as suitable for the calculation of GHG emissions. The energy-related predicted GHG emissions were very similar to the actual GHG emissions of EU Members (MAPE = 6.4%).",
publisher = "Pergamon-Elsevier Science Ltd, Oxford",
journal = "Energy",
title = "Modeling of energy consumption and related GHG (greenhouse gas) intensity and emissions in Europe using general regression neural networks",
pages = "824-816",
volume = "84",
doi = "10.1016/j.energy.2015.03.060"
}

Antanasijević, D., Pocajt, V., Ristić, M.,& Perić-Grujić, A.. (2015). Modeling of energy consumption and related GHG (greenhouse gas) intensity and emissions in Europe using general regression neural networks. in Energy
Pergamon-Elsevier Science Ltd, Oxford., 84, 816-824.
https://doi.org/10.1016/j.energy.2015.03.060

Antanasijević D, Pocajt V, Ristić M, Perić-Grujić A. Modeling of energy consumption and related GHG (greenhouse gas) intensity and emissions in Europe using general regression neural networks. in Energy. 2015;84:816-824.
doi:10.1016/j.energy.2015.03.060 .

Antanasijević, Davor, Pocajt, Viktor, Ristić, Mirjana, Perić-Grujić, Aleksandra, "Modeling of energy consumption and related GHG (greenhouse gas) intensity and emissions in Europe using general regression neural networks" in Energy, 84 (2015):816-824,
https://doi.org/10.1016/j.energy.2015.03.060 . .

TY  - JOUR
AU  - Stamenković, Lidija J.
AU  - Antanasijević, Davor
AU  - Ristić, Mirjana
AU  - Perić-Grujić, Aleksandra
AU  - Pocajt, Viktor
PY  - 2015
UR  - http://TechnoRep.tmf.bg.ac.rs/handle/123456789/2997
AB  - The aim of this study was to develop a model for forecasting CH4 emissions at the national level, using artificial neural networks (ANN) with broadly available sustainability, economical and industrial indicators as their inputs. ANN modeling was performed using two different types of architecture; a backpropagation neural network (BPNN) and a general regression neural network (GRNN). A conventional multiple linear regression (MLR) model was also developed in order to compare the model performance and assess which model provides the best results. ANN and MLR models were developed and tested using the same annual data for 20 European countries. The ANN model demonstrated very good performance, significantly better than the MLR model. It was shown that a forecast of CH4 emissions at the national level using the ANN model could be made successfully and accurately for a future period of up to two years, thereby opening the possibility to apply such a modeling technique, which could be used to support the implementation of sustainable development strategies and environmental management policies.
PB  - Srpsko hemijsko društvo, Beograd
T2  - Journal of the Serbian Chemical Society
T1  - Modeling of methane emissions using the artificial neural network approach
EP  - 433
IS  - 3
SP  - 421
VL  - 80
DO  - 10.2298/JSC020414110S
ER  - 

@article{
author = "Stamenković, Lidija J. and Antanasijević, Davor and Ristić, Mirjana and Perić-Grujić, Aleksandra and Pocajt, Viktor",
year = "2015",
abstract = "The aim of this study was to develop a model for forecasting CH4 emissions at the national level, using artificial neural networks (ANN) with broadly available sustainability, economical and industrial indicators as their inputs. ANN modeling was performed using two different types of architecture; a backpropagation neural network (BPNN) and a general regression neural network (GRNN). A conventional multiple linear regression (MLR) model was also developed in order to compare the model performance and assess which model provides the best results. ANN and MLR models were developed and tested using the same annual data for 20 European countries. The ANN model demonstrated very good performance, significantly better than the MLR model. It was shown that a forecast of CH4 emissions at the national level using the ANN model could be made successfully and accurately for a future period of up to two years, thereby opening the possibility to apply such a modeling technique, which could be used to support the implementation of sustainable development strategies and environmental management policies.",
publisher = "Srpsko hemijsko društvo, Beograd",
journal = "Journal of the Serbian Chemical Society",
title = "Modeling of methane emissions using the artificial neural network approach",
pages = "433-421",
number = "3",
volume = "80",
doi = "10.2298/JSC020414110S"
}

Stamenković, L. J., Antanasijević, D., Ristić, M., Perić-Grujić, A.,& Pocajt, V.. (2015). Modeling of methane emissions using the artificial neural network approach. in Journal of the Serbian Chemical Society
Srpsko hemijsko društvo, Beograd., 80(3), 421-433.
https://doi.org/10.2298/JSC020414110S

Stamenković LJ, Antanasijević D, Ristić M, Perić-Grujić A, Pocajt V. Modeling of methane emissions using the artificial neural network approach. in Journal of the Serbian Chemical Society. 2015;80(3):421-433.
doi:10.2298/JSC020414110S .

Stamenković, Lidija J., Antanasijević, Davor, Ristić, Mirjana, Perić-Grujić, Aleksandra, Pocajt, Viktor, "Modeling of methane emissions using the artificial neural network approach" in Journal of the Serbian Chemical Society, 80, no. 3 (2015):421-433,
https://doi.org/10.2298/JSC020414110S . .