Analyzing students’ academic performance is important for evaluating enrollment criteria which establish the standards required for pupils who finished secondary school to gain admission to a higher education institution. The aims of this research were to develop a machine learning prediction Decision Tree classification model and analyze the performance of engineering students based on their performances during secondary school education. The performance of students was analyzed and measured as a binomial response whether students successfully finished the first and the second study years. The developed model examined general success, number of awards obtained at competitions, special awards, average grades in mathematics, physics, and one of the official state languages during secondary school as predictor variables. The number of courses transferred from the first into the second study year and students’ GPA obtained during the first study year were added as predictor variables in the analysis and development of a prediction model for the students’ performance during the second study year and their enrollment in the third study year. Developed machine learning prediction model showed that for the performance of enrolled students in the first study year general success of students during secondary school is the most important predictor variable, followed by mathematics and physics grades. However, for the performance of the students enrolled in the second study year the most important predictor variable was number of the courses transferred from the first into the second study year, followed by students’ GPA obtained during the first study year and general success. Machine learning Decision Tree classification modeling was shown to be an adequate tool for the prediction of the performance of engineering students during the first and second study years.

The specific geographic location of Sarajevo, which is located in a valley surrounded by mountains, provides the opportunity to analyze the relation between the concentration of PM10 and meteorological parameters with and without temperature inversion. The main aim of this paper was to develop forecasting models of the hourly average of PM10 values in the Sarajevo urban area based on meteorological parameters measured in Sarajevo and on the Bjelasnica mountain with and without temperature inversion by using principal component regression (PCR). Also, this research explored and analyzed the differences in the values of the meteorological parameters and PM10 in Sarajevo with and without temperature inversion, and the difference in temperatures between Sarajevo and Bjelasnica with temperature inversion using statistical hypothesis testing with a total of 240 hypothesis tests performed. The measurements of meteorological parameters were taken from 2020 to 2022 for both Sarajevo (630 m) and the Bjelasnica mountain (2067 m), which allowed for the identification of time periods with and without temperature inversion, while measurements of PM10 were taken only in Sarajevo. Data were collected during the heating season (November, December, January, February and March). Since analyses have shown that only January and November had time periods with and without temperature inversion during each hour of the day, a total of seven cases were identified: two cases with and five cases without temperature inversion. For each case, three PCR models were developed using all principal components, backward elimination and eigenvalue principal component elimination criteria (λ<1). A total of 21 models were developed. The performance of the models were evaluated based on the coefficient of determination R2 and the standard error SE. The backward elimination models were shown to have high performances with the highest value of R2= 97.19 and the lowest value of SE=1.32. The study showed that some principal components with eigenvalues λ<1 were significantly related to the independent variable PM10 and thus were retained in the PCR models. In the study, it was shown that backward elimination PCR was an adequate tool to develop PM10 forecasting models with high performances and that it could be useful for authorities for early warnings or other action to protect citizens from very harmful pollution. Hypothesis tests showed different relations of meteorological parameters and PM10 with and without temperature inversion.

Background: During the process of the treatment of COVID-19 hospitalized patients, physicians still face a lot of unknowns and problems. Despite the application of the treatment protocol, it is still unknown why the medical status of a certain number of patients worsens and ends with death. Many factors were analyzed for the prediction of the clinical outcome of the patients using different methods. The aim of this paper was to develop a prediction model based on initial laboratory blood test results, accompanying comorbidities, and demographics to help physicians to better understand the medical state of patients with respect to possible clinical outcomes using neural networks, hypothesis testing, and confidence intervals. Methods: The research had retrospective-prospective, descriptive, and analytical character. As inputs for this research, 12 components of laboratory blood test results, six accompanying comorbidities, and demographics (age and gender) data were collected from hospital information system in Sarajevo for each patient from a sample of 634 hospitalized patients. Clinical outcome of the hospitalized patients, survival or death, was recorded 30 days after admission to the hospital. The prediction model was designed using a neural network. In addition, formal hypothesis tests were performed to investigate whether there were significant differences in laboratory blood test results and age between patients who died and those who survived, including the construction of 95% confidence intervals. Results: In this paper, 11 neural networks were developed with different threshold values to determine the optimal neural network with the highest prediction performance. The performances of the neural networks were evaluated by accuracy, precision, sensitivity, and specificity. Optimal neural network model evaluation metrics are: accuracy = 87.78%, precision = 96.37%, sensitivity = 90.07%, and specificity = 62.16%. Significantly higher values (P < 0.05) of blood laboratory result components and age were detected in patients who died. Conclusion: Optimal neural network model, results of hypothesis tests, and confidence intervals could help to predict, analyze, and better understand the medical state of COVID-19 hospitalized patients and thus reduce the mortality rate.

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 statistical evidences that during the lockdown period mean concentration values of O3 and NO2 are smaller than mean values during same period in March 2019, while mean concentration value of PM10 is greater than mean value during same period in March 2019. Also, statistical hypothesis testing is used to compare concentration of air pollutants before and during lockdown period in March 2020. It is shown that mean concentration values of PM10 and O3 are greater during lockdown period, while mean concentration value of NO2 before the lockdown in March 2020 is greater than during the lockdown period. Coefficients of correlation as the measure of the strength of linear association between air pollutants PM10, O3 and NO2 and meteorological parameters air temperature, humidity and pressure, wind speed and wind direction are calculated as well.

This paper presents the use of Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method to determine the optimum process parameters in plasma arc cutting of stainless steel. Two input process parameters, cutting speed and plasma gas pressure are considered and experiments are conducted based on Taguchi L9 orthogonal array. After performing the experiments, the surface roughness, cut perpendicularity and kerf width are measured. The analysis of variance (ANOVA) are performed in order to identify the effect of each input process parameters on the output responses. The results indicate that TOPSIS method is appropriate for solving multi-criteria optimization of process parameters. Results also showed that cutting speed of 2500 mm/min and plasma gas pressure of 6 bar are the optimum combination of process parameters.

This paper presents the use of Technique for Order Preference by Similarity to Ideal Solution (TOPSIS) method to determine the optimum process parameters in plasma arc cutting of stainless steel. Two input process parameters, cutting speed and plasma gas pressure are considered and experiments are conducted based on Taguchi L9 orthogonal array. After performing the experiments, the surface roughness, cut perpendicularity and kerf width are measured. The analysis of variance (ANOVA) are performed in order to identify the effect of each input process parameters on the output responses. The results indicate that TOPSIS method is appropriate for solving multi-criteria optimization of process parameters. Results also showed that cutting speed of 2500 mm/min and plasma gas pressure of 6 bar are the optimum combination of process parameters.

The REBUS project emerged in countries where the younger generations are reluctant to engage in private business and entrepreneurship, preferring “safe” employment at the public (state owned) enterprises. Their awareness of own entrepreneurship potentials is very low, while the capacity of talented and skilled students often stays unutilized once being employed. Thus the REBUS project supports embedding entrepreneurship to the South East Europe and Russian universities, at the same time creating network for cooperation between EU and partner countries. One of the first activities was identification, analysis and description of common practices in entrepreneurship education. For this purpose, a comprehensive desk research was combined with expert interviews to inquire about approaches of learning and teaching, connections to lessons, courses and extracurricular activities and approaches to validate entrepreneurial competences. The stocktaking related to the knowledge and differentiation on entrepreneurial competences, leading questions of the surveys related to gaps between formalised (HE) and informal (personal oriented, e.g. in internships) learning and assessment, potentials for enhancements of acquisition of those competences, validation of entrepreneurial competences and selection of key sub-competences. This paper presents results of research and needs analysis (stocktaking) and project objectives and first results.

Media in Bosnia and Herzegovina recently published that between 70 and 80 percent of public utilities are hardy able to pay their accounts payable and at least half of them has fulfilled the conditions for the opening of bankruptcy proceedings, according to estimates made by the Association of Bankruptcy Administrators. Similar situation is in other Western Balkan countries; budgets of public utility companies are not able to settle obligations. Why is it becoming convenient, also followed by deterioration of public infrastructure and worsening of public services provision quality, and how can such declining process be reversed? The paper presents research on this topic, focusing specially to water utilities, and offering potential responses to these questions.

Inventory systems that use continuous review policy are under risk during lead time, when stock-out can occur. Therefore, system must have enough on-hand units to prevent such situations. Generally, in inventory control literature it can be found that lead time demand follows normal distribution and all other conclusions are derived from this assumption. However, in real life this does not have to be true, so it is of crucial importance to get better estimates of stochastic demand parameters over lead time. The objective of this research is to estimate the optimal (s, Q) continuous review inventory policy parameters that reduce risk of stock-out during lead time and to enhance robustness of such estimated parameters. This is done using approach we propose for demand modeling. Performances and adequacy of the proposed approach for lead time demand modeling, with various demand patterns, and its application in (s, Q) continuous inventory models are obtained by simulation and show very good results.