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.

Background: Angiotensin-converting enzyme 2 (ACE2) is not only an enzyme but also a functional receptor on cell surfaces through which Severe acute respiratory syndrome coronavirus 2 (SARS-CoV2). The exact mechanism by which arterial hypertension (particularly regulated) could affect the presentation and outcome of Coronavirus disease-19 (COVID-19) has not been fully elucidated. Objective: The aim of this study was to analyze the parameters of patients with verified COVID-19 and existing arterial hypertension at the time of hospital admission and to develop neural network model. Methods: The research had a cross-sectional descriptive and analytical character, and included patients (n=634) who were hospitalized in the General Hospital “Prim. dr. Abdulah Nakas” in Sarajevo, Bosnia and Herzegovina, in the period from 01 Sep 2020 to 01 May 2021. From the hospital information system, which is used in everyday clinical work, laboratory parameters at admission were verified, along with demographic data, the comorbidities, while the outcome (recovery, death) was recorded thirty days after the admission. Results: Out of the total number, in 314 patients (200 males), arterial hypertension was verified, out of which, 56 (17.83%) patients died. Patients were divided into two groups, according to outcome, i.e., whether they survived COVID-19 infection or not. A significant difference in age (p = 0.00), erythrocyte count (p = 0.03), haemoglobin (p = 0.05), hematocrit (p = 0.03), platelets count (p = 0.00), leukocytes (p = 0.01), neutrophils (p = 0.00), lymphocytes (p = 0.00), monocytes (p = 0.00), basophils (p = 0.00), eosinophils (p = 0.00), C-reactive protein (p = 0.00) and D-dimer (p = 0.01) was noted. When patients who died and had hypertension were compared with those who died and did not have hypertension (n = 15), out of alll the analyzed parameters, the only significant difference was established in the patient’s age (p = 0.00). In case when patients with hypertension who died were compared to patients with hypertension and diabetes mellitus who died no significant differences were found between features. Conclusion: Patients with hypertension and COVID-19 who died were older, had higher values of erythrocytes, hemoglobin, hematocrit, leukocytes, neutrophils, CRP and D-dimer, and lower values of platelets, lymphocytes, monocytes, basophils and eosinophils count at admission. Compared to deaths without hypertension, the only difference that was established was that patients with hypertension were older.

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.

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 SO2, PM10, NO2, O3 and CO 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.