Mirza Pasic - Academia.edu (original) (raw)

Papers by Mirza Pasic

Acta Informatica Medica, 2022

Proceedings of the 29th International DAAAM Symposium 2018, 2018

In the modern industry the use of lasers has proven to be very useful due to the high precision a... more In the modern industry the use of lasers has proven to be very useful due to the high precision and quality of cut. Important indicators of the cutting surface quality are roughness of the cutting surface and. In this research experiment is performed to analyse the influence of laser power , cutting speed and assist gas pressure as independent variables on dependent variables and during HSG fiber laser cutting of 1.4307 DIN stainless steel plates, 1 mm thick, using nitrogen as assist gas. During the experiment 75 samples are cut and 225 values of each cutting surface roughness and are measured. Data obtained during the experiment are analysed using regression analysis. Mathematical model is developed for each independent variable and depending on the significant independent variables. Surface roughness values are compared and analysed according to the quality categories defined by ISO 9013: 2002 (E). It can be seen that regression analysis is good tool in modelling cutting surface quality and .

Proceedings of the 29th International DAAAM Symposium 2018, 2018

In this paper, the relationship between PTA (purified terephthalic acid) price and oil price was ... more In this paper, the relationship between PTA (purified terephthalic acid) price and oil price was tested and a linear regression model was established. The following prediction models were tested on a historical oil price time series: the Same Slope, the Weighted Moving Averages, the Simple Exponential Smoothing, and the Exponential Smoothing With Additive Trend or the Holt's model. In order to determine the unknown parameters of the used models, nonlinear mathematical programming was used. Performance analysis on the given time series showed that the Same Slope model yielded better results than other tested models. The oil forecast given by the Same Slope model was then combined with the initial regression equation to establish the final PTA predicting model.

Periodicals of Engineering and Natural Sciences (PEN), 2020

The aim of this paper is to compare air quality in Sarajevo in March 2019 and March 2020 with out... more The aim of this paper is to compare air quality in Sarajevo in March 2019 and March 2020 with outbreak of the novel coronavirus SARS-CoV-2 in Sarajevo and Bosnia and Herzegovina. First preventive and protective measures were issued at the end of second week of March, while on 21 March 2020 an order imposing complete ban of movement of citizens from late afternoon until early in the morning next day was issued. This was rare opportunity to compare air quality in Sarajevo having same causes of air pollution for one part of March 2019 and March 2020 and different causes of air pollution during the lockdown and ban of movement caused by SARS-CoV-2. Statistical hypothesis testing is used to compare values during the March 2019 and March 2020 before the lockdown (the first phase) and during the lockdown (the second phase). Complete and comprehensive analysis is performed for both phases of March 2019 and March 2020, before the lockdown and during the lockdown. It is shown that there are s...

DAAAM Proceedings, 2017

The aim of this paper is to develop a mathematical model using a linear regression analysis for t... more The aim of this paper is to develop a mathematical model using a linear regression analysis for the laser cut perpendicularity depending on the cutting parameters and to compare the values of the cut perpendicularity according to ISO 9013:2002 (E) standard. Cutting parameters that are used as independent variables in this research are: laser power , cutting speed and assist gas pressure. During the experiment 75 samples of 1.4307 DIN stainless steel and 1 mm of thickness were cut on HSG fiber laser using nitrogen 2 as an assist gas. Each sample was cut using different combination of values of independent variables. Cut perpendicularity was measured on these samples with total of 225 measurements. Obtained results show that the cutting speed is only significant variable in the model and that the linear regression analysis is suitable for the analysis of the cut perpendicularity. Every experimental value of the cut perpendicularity is located in the first quality category according to ISO 9013:2002 (E) standard.

DAAAM Proceedings, 2019

This paper deals with the survey and assessment of traffic safety in Federation of Bosnia and Her... more This paper deals with the survey and assessment of traffic safety in Federation of Bosnia and Herzegovina (F B&H) and compares it to the traffic safety in Republic of Srpska (RS), Brcko District (BD) and EU countries. The assessment and comparison of traffic safety in this study is based on data collected from various referential statistical sources, the same being related to the period 2015-2016. For the analysis, a Data Envelopment Analysis (DEA) method has been selected, which enables a comparative assessment of the traffic safety of certain regions (cities, cantons, states) based on multiple indicators, such as number of traffic accidents, number of deaths, number of seriously injured compared to the number of inhabitants, road lengths, etc. DEA, as an objective and nonparametric method, does not favor any of the selected criteria, but provides equal chances to all units whose performances are being evaluated. Paper gives a brief theoretical overview of DEA method, brief survey of literature related to application of DEA method in analysis of traffic safety, data and sources of collected data, as well as developed DEA model. Conducted analysis enabled estimation of traffic safety efficacy, identification of countries/entities/districts with traffic safety not at the level of the relatively most secure countries, and estimation of possible improvements related to reduction of the total number of traffic accidents and number of people died in traffic accidents, for all countries/entities/districts. Based on the conducted analysis it can be concluded that there is a significant difference in the efficiency of traffic safety in EU countries. At the level of all EU countries, including B&H (F B&H, RS and BD), the total number of traffic accidents can be reduced by 458.142,9 or by 42% per year, while the total number of people died can be reduced by 10.674,42 or by 38% per year. The analysis has shown that the highest level of traffic safety is in Denmark, Finland, the Netherlands and Sweden, while traffic safety is the lowest in F B&H, Romania, RS and BD.

TEM Journal, 2020

In this paper five neural network models were developed using NARX-SP neural network type in orde... more In this paper five neural network models were developed using NARX-SP neural network type in order to predict air pollutants concentrations (SO2, PM10, NO2, O3 and CO ) for the 72nd hour ahead for Sarajevo. Hourly values of air pollutants concentrations and meteorological parameters (air temperature, pressure and humidity, wind speed and direction) for Sarajevo were used. Optimal model was selected based on the values of R2, MSE and the complexity of models. Optimal neural network model can predict air pollutants concentrations for the 72nd hour ahead with high accuracy, as well as for all hours up to 72nd hour.

International Journal for Quality Research, 2020

Neural networks are important method of machine learning that can be used to predict air quality ... more Neural networks are important method of machine learning that can be used to predict air quality with high accuracy. Using NARX-SP neural network type, several neural network models are developed to predict concentration of air pollutants in Sarajevo for two prediction cases, for 24th and 48th hour ahead, with different combinations of inputs and outputs. The data used in this paper contain hourly values of meteorological parameters (air humidity, pressure and temperature, wind speed and direction) and concentrations of 2 , 10 , 2 , 3 and from 2016 to 2018. Optimal models are selected for both prediction cases. It is concluded that the optimal models have very good performances and can be used to predict concentration of pollutants in Sarajevo with great accuracy and contribute to improve quality of life. By adequate application of optimal models, concentration of air pollutants can be predicted for each hour over the next 48 hours.

Proceedings of the 30th International DAAAM Symposium 2019, 2019

Acta Informatica Medica, 2022

Proceedings of the 29th International DAAAM Symposium 2018, 2018

In the modern industry the use of lasers has proven to be very useful due to the high precision a... more In the modern industry the use of lasers has proven to be very useful due to the high precision and quality of cut. Important indicators of the cutting surface quality are roughness of the cutting surface and. In this research experiment is performed to analyse the influence of laser power , cutting speed and assist gas pressure as independent variables on dependent variables and during HSG fiber laser cutting of 1.4307 DIN stainless steel plates, 1 mm thick, using nitrogen as assist gas. During the experiment 75 samples are cut and 225 values of each cutting surface roughness and are measured. Data obtained during the experiment are analysed using regression analysis. Mathematical model is developed for each independent variable and depending on the significant independent variables. Surface roughness values are compared and analysed according to the quality categories defined by ISO 9013: 2002 (E). It can be seen that regression analysis is good tool in modelling cutting surface quality and .

Proceedings of the 29th International DAAAM Symposium 2018, 2018

In this paper, the relationship between PTA (purified terephthalic acid) price and oil price was ... more In this paper, the relationship between PTA (purified terephthalic acid) price and oil price was tested and a linear regression model was established. The following prediction models were tested on a historical oil price time series: the Same Slope, the Weighted Moving Averages, the Simple Exponential Smoothing, and the Exponential Smoothing With Additive Trend or the Holt's model. In order to determine the unknown parameters of the used models, nonlinear mathematical programming was used. Performance analysis on the given time series showed that the Same Slope model yielded better results than other tested models. The oil forecast given by the Same Slope model was then combined with the initial regression equation to establish the final PTA predicting model.

Periodicals of Engineering and Natural Sciences (PEN), 2020

The aim of this paper is to compare air quality in Sarajevo in March 2019 and March 2020 with out... more The aim of this paper is to compare air quality in Sarajevo in March 2019 and March 2020 with outbreak of the novel coronavirus SARS-CoV-2 in Sarajevo and Bosnia and Herzegovina. First preventive and protective measures were issued at the end of second week of March, while on 21 March 2020 an order imposing complete ban of movement of citizens from late afternoon until early in the morning next day was issued. This was rare opportunity to compare air quality in Sarajevo having same causes of air pollution for one part of March 2019 and March 2020 and different causes of air pollution during the lockdown and ban of movement caused by SARS-CoV-2. Statistical hypothesis testing is used to compare values during the March 2019 and March 2020 before the lockdown (the first phase) and during the lockdown (the second phase). Complete and comprehensive analysis is performed for both phases of March 2019 and March 2020, before the lockdown and during the lockdown. It is shown that there are s...

DAAAM Proceedings, 2017

The aim of this paper is to develop a mathematical model using a linear regression analysis for t... more The aim of this paper is to develop a mathematical model using a linear regression analysis for the laser cut perpendicularity depending on the cutting parameters and to compare the values of the cut perpendicularity according to ISO 9013:2002 (E) standard. Cutting parameters that are used as independent variables in this research are: laser power , cutting speed and assist gas pressure. During the experiment 75 samples of 1.4307 DIN stainless steel and 1 mm of thickness were cut on HSG fiber laser using nitrogen 2 as an assist gas. Each sample was cut using different combination of values of independent variables. Cut perpendicularity was measured on these samples with total of 225 measurements. Obtained results show that the cutting speed is only significant variable in the model and that the linear regression analysis is suitable for the analysis of the cut perpendicularity. Every experimental value of the cut perpendicularity is located in the first quality category according to ISO 9013:2002 (E) standard.

DAAAM Proceedings, 2019

This paper deals with the survey and assessment of traffic safety in Federation of Bosnia and Her... more This paper deals with the survey and assessment of traffic safety in Federation of Bosnia and Herzegovina (F B&H) and compares it to the traffic safety in Republic of Srpska (RS), Brcko District (BD) and EU countries. The assessment and comparison of traffic safety in this study is based on data collected from various referential statistical sources, the same being related to the period 2015-2016. For the analysis, a Data Envelopment Analysis (DEA) method has been selected, which enables a comparative assessment of the traffic safety of certain regions (cities, cantons, states) based on multiple indicators, such as number of traffic accidents, number of deaths, number of seriously injured compared to the number of inhabitants, road lengths, etc. DEA, as an objective and nonparametric method, does not favor any of the selected criteria, but provides equal chances to all units whose performances are being evaluated. Paper gives a brief theoretical overview of DEA method, brief survey of literature related to application of DEA method in analysis of traffic safety, data and sources of collected data, as well as developed DEA model. Conducted analysis enabled estimation of traffic safety efficacy, identification of countries/entities/districts with traffic safety not at the level of the relatively most secure countries, and estimation of possible improvements related to reduction of the total number of traffic accidents and number of people died in traffic accidents, for all countries/entities/districts. Based on the conducted analysis it can be concluded that there is a significant difference in the efficiency of traffic safety in EU countries. At the level of all EU countries, including B&H (F B&H, RS and BD), the total number of traffic accidents can be reduced by 458.142,9 or by 42% per year, while the total number of people died can be reduced by 10.674,42 or by 38% per year. The analysis has shown that the highest level of traffic safety is in Denmark, Finland, the Netherlands and Sweden, while traffic safety is the lowest in F B&H, Romania, RS and BD.

TEM Journal, 2020

In this paper five neural network models were developed using NARX-SP neural network type in orde... more In this paper five neural network models were developed using NARX-SP neural network type in order to predict air pollutants concentrations (SO2, PM10, NO2, O3 and CO ) for the 72nd hour ahead for Sarajevo. Hourly values of air pollutants concentrations and meteorological parameters (air temperature, pressure and humidity, wind speed and direction) for Sarajevo were used. Optimal model was selected based on the values of R2, MSE and the complexity of models. Optimal neural network model can predict air pollutants concentrations for the 72nd hour ahead with high accuracy, as well as for all hours up to 72nd hour.

International Journal for Quality Research, 2020

Neural networks are important method of machine learning that can be used to predict air quality ... more Neural networks are important method of machine learning that can be used to predict air quality with high accuracy. Using NARX-SP neural network type, several neural network models are developed to predict concentration of air pollutants in Sarajevo for two prediction cases, for 24th and 48th hour ahead, with different combinations of inputs and outputs. The data used in this paper contain hourly values of meteorological parameters (air humidity, pressure and temperature, wind speed and direction) and concentrations of 2 , 10 , 2 , 3 and from 2016 to 2018. Optimal models are selected for both prediction cases. It is concluded that the optimal models have very good performances and can be used to predict concentration of pollutants in Sarajevo with great accuracy and contribute to improve quality of life. By adequate application of optimal models, concentration of air pollutants can be predicted for each hour over the next 48 hours.

Proceedings of the 30th International DAAAM Symposium 2019, 2019