Pulmonary emphysema is a complicated disease caused by irreversible damage to the wall of the pulmonary alveoli and causes 5% of the total mortality worldwide. This paper presents the development of an artificial neural network (ANN) for the diagnosis of pulmonary emphysema. Following biomarkers were used for the development of the ANN: AAT (alphal-antitrypsin), FEV1 (forced expiratory volume in 1 second), FVC (forced vital capacity) and FEV1/FVC (ratio forced expiratory volume in 1 second / forced vital capacity). The dataset consisted of 300 patients: 210 healthy subjects and 90 subject with disease. The neural network has 4 input parameters and 1 output parameter. For the final architecture, a neural network with 13 neurons in hidden layer was chosen based on the training results. The developed ANN has shown good performance and has a potential for use in this field.

This paper focuses on the problem of diagnosing polycystic ovary syndrome (PCOS), which is one of the leading disorders of the female endocrine system. Although the incidence of this syndrome is quite high, physicians and patients still often encounter problems in their detection, as well as with the ineffectiveness of prescribed therapy. For the development of expert system, a database containing following parameters was used: oligo ovulation, anovulation, free testosterone, free androgen index (FAI), calculated bioavailable testosterone, androstendione, dehydroepiandrosterone, ovarian volume, number of follicles, obesity. The presented dataset contains 1000 samples distributed in two categories: (1) heatlhy subjects and (2) subjects with disease. The purpose of the developed system is to classify instances with polycystic ovary syndrome using artificial neural networks (ANN s). The overall performance evaluation of the system resulted with accuracy of96.1 %, sensitivity of96.8% and specificity of90% indicating significant potential of ANNs in this field. Since the system predicted a total of 157 positive and 23 negative, this leads us to the result that the sensitivity of our system is 96.8%, specificity 90% and accuracy 96.1 %.

The aim of this paper is to investigate the state of performance of audit firms registered in the Republic of Serbia, as well as the factors that manage performance. The research is based on the entire population of audit firms, based on financial reports for the period 2019-2020. that are publicly available. The performance of audit firms will be investigated from the aspect of profitability performance, where the indicators of return on assets nad return on equity is most often used. Performance analysis will be presented through descriptive statistical analysis. Performance management will be analyzed in terms of the impact of independent factors on ROA and ROE. The following will be defined as independent factors: the size of the audit firm, liquidity, indebtedness, belonging to the big four, growth and the like. The research of the influence of independent factors on the dependent variables of the performance of audit firms will be conducted on the basis of regression analysis. The results of descriptive analysis should indicate the state and trend of performance of audit firms, while the results of regression analysis should indicate the nature of the factors that drive the performance of audit firms.

The success of a company depends on the employees, so the challenge for managers is to monitor their needs continuously and find ways to encourage them to work and achieve goals. By using a combination of compatible material and non-material techniques within motivation strategies, managers link long-term company goals and rewarding employees for work and achievements. The aim of this paper is to get insight into the used motivation techniques and strategic approach to motivation in companies in the Federation of BiH (FBiH). The survey was conducted in early 2019 and covered 63 companies. The most commonly used material motivation techniques are salaries, bonuses, and paid leave, and the most commonly used nonmaterial techniques are appropriate working hours, information on work results and the possibility of advancement. Almost half of the managers state that there are established rules for motivating employees in their companies, slightly more than ¼ point out that there is an established plan for motivating employees that is continuously implemented. Only a part of the surveyed companies, have a continuous, systematic way of monitoring employee motivation. Assessing motivation and taking corrective action is most often carried out by top management, two or more times a year. The results indicate that some companies in the FBiH have not yet realized that the human factor is a key factor in achieving better business results. In order for motivation to be truly effective, it must be approached in a planned and continuous manner.

—The power system state estimation (SE) algorithm estimates the complex bus voltages based on the available set of measurements. Because phasor measurement units (PMUs) are becoming more widely employed in transmission power systems, a fast SE solver capable of exploiting PMUs’ high sample rates is required. To accomplish this, we present a method for training a model based on graph neural networks (GNNs) to learn estimates from PMU voltage and current measurements, which, once it is trained, has a linear computational complexity with respect to the number of nodes in the power system. We propose an original GNN implementation over the power system’s factor graph to simplify the incorporation of various types and numbers of measurements both on power system buses and branches. Fur-thermore, we augment the factor graph to improve the robustness of GNN predictions. Training and test examples were generated by randomly sampling sets of power system measurements and annotated with the exact solutions of linear SE with PMUs. The numerical results demonstrate that the GNN model provides an accurate approximation of the SE solutions. Additionally, errors caused by PMU malfunctions or the communication failures that make the SE problem unobservable have a local effect and do not deteriorate the results in the rest of the power system.

Classification problems have been part of numerous real-life applications in fields of security, medicine, agriculture, and more. Due to the wide range of applications, there is a constant need for more accurate and efficient methods. Besides more efficient and better classification algorithms, the optimal feature set is a significant factor for better classification accuracy. In general, more features can better describe instances, but besides showing differences between instances of different classes, it can also capture many similarities that lead to wrong classification. Determining the optimal feature set can be considered a hard optimization problem for which different metaheuristics, like swarm intelligence algorithms can be used. In this paper, we propose an adaptation of hybridized swarm intelligence (SI) algorithm for feature selection problem. To test the quality of the proposed method, classification was done by k-means algorithm and it was tested on 17 benchmark datasets from the UCI repository. The results are compared to similar approaches from the literature where SI algorithms were used for feature selection, which proves the quality of the proposed hybridized SI method. The proposed method achieved better classification accuracy for 16 datasets. Higher classification accuracy was achieved while simultaneously reducing the number of used features.

The text is a review of the book Ka filozofiji prava kao filozofiji ljudskih prava written by Jasminka Hasanbegović and published by Dosije studio, Belgrade, 2021.

The aim of the paper is to investigate the impact of SEO on the business performance of a private university in Sarajevo. Thus, the main research question provides the finding on how does the implementation of SEO influence the performance of the business. Moreover, the tested hypothesis presents whether SEO positively influences the business performance of International Burch University (IBU). The research strategy is to analyze primary data derived from a case study, which is generated following a conversation with the Head of the IBU Marketing and PR team. The data sample is derived from Google Analytics (focusing on the number of visits and sessions, average engagement time, keywords and SERP positioning). Seobility tools are employed in data analysis. Business performance is calculated through the IBU CRM system, focusing on student enrolment. Findings indicate that increasing a site's rankings on search engine results pages (SERPs) led to a variety of positive outcomes for companies including an increase in the number of visitors to the site, an increase in the average amount of time users spent on the site, increased user engagement, and an increase in student enrollment, which resulted in IBU increased annual sales revenue. It will benefit many different groups, including the government, which will benefit in both microeconomic and macroeconomic senses, digital marketing enthusiasts and SEO experts, and the academic world, which will benefit as a framework for future studies and research in the field of SEO recognition and implementation in business queries.

In this work, we present a novel multi-modal trajectory prediction architecture. We decompose the uncertainty of future trajectories along higher-level scene characteristics and lower-level motion characteristics, and model multi-modality along both dimensions separately. The scene uncertainty is captured in a joint manner, where diversity of scene modes is ensured by training multiple separate anchor networks which specialize to different scene realizations. At the same time, each network outputs multiple trajectories that cover smaller deviations given a scene mode, thus capturing motion modes. In addition, we train our architectures with an outlier-robust regression loss function, which offers a trade-off between the outlier-sensitive L2 and outlier-insensitive L1 losses. Our scene anchor model achieves improvements over the state of the art on the INTERACTION dataset, outperforming the StarNet architecture from our previous work.

Este trabalho irá abordar sobre a criação das rodovias que se mantêm em efeitos ambientais, a fim de inserir qualidade em seu uso e das disposições das faunas que as insere, por vez que se observa os fragmentos que se exercem por decorrência das pressões que sofrem. Por isso, foi abordado os aspectos e maneiras que isso se estrutura, forma essa que sobre os efeitos se dispõe e classifica as contemplações das rodovias. As garantias de requisitos tornam que o surgimento das passagens e o funcionamento contribua na biodiversidade. Como intuito de enfatizar os procedimentos e recursos que se aproveitam nas suas apresentações, distribuindo assim trechos de rodovias ecológicas pelo Brasil. Os impactos fornecem sobre a fauna métodos de diminuir qualquer tipo de acidente em rodovias, em principal pelas mortes de animais que são gerados nos perigos dos trechos. Contudo, se elabora o controle de melhoria, fazendo com que implante instalações seguras que diminua a incidência desses riscos gerados.

Abstract Banat Naked Neck is the most important indigenous breed of chickens in Serbia. Marginalized until recently, it is becoming increasingly popular due to its adaptability and good productivity in alternative production systems. However, its history and the current breeding model pose challenges for breed preservation and future improvement. This study aimed to assess the genetic diversity and structure of four subpopulations of Banat Naked Neck from different districts in Serbia (West Backa, North Banat, South Banat and Kolubara) using D-loop mitochondrial DNA sequences and a set of 30 microsatellite markers. Seven haplotypes in the phylogenetic analysis of D-loop mitochondrial DNA suggested maternal origin related to the Indian subcontinent, while haplotype and nucleotide diversity averaged 0.731 ± 0.053 and 0.0067 ± 0.0018, respectively. Microsatellite genotyping showed an average detected number of alleles per locus of 5.129 ± 0.237, while the observed and expected heterozygosity averaged 0.560 ± 0.018 and 0.631 ± 0.014, respectively. Genetic differentiation estimated through FST was 0.051 (p < .001). Two clusters in STRUCTURE analysis showed possible separation of two older subpopulations (South Banat and Kolubara) from the two more recent ones (West Backa and North Banat). This first comprehensive study of genetic diversity serves as the basis for future preservation, use and improvement of the Banat Naked Neck breed.

The association between urine amylase levels and the development of post-operative complications after Whipple resection is still unknown. The aim of this study was to determine the prognostic value of urine amylase levels for post-operative complications in patients who underwent Whipple resection. In this retrospective-prospective cohort study we analyzed amylase levels in urine, serum, and drains in 52 patients who underwent Whipple resection preoperatively and on Post-operative Day 1 (POD1) after the intervention. Patients were followed up for 3 months to assess their predictive value for post-operative complications. In patients with complications, urine amylase levels were significantly higher on POD1 than before resection (198.89 ± 28.41 vs. 53.70 ± 7.44, p=0.000). Considering the sensitivity and specificity of the urine amylase level on POD1, an area under the ROC curve of 0.918 was obtained (p<0.001, 95% Confidence interval [CI]: 0.894-0.942). Patients with urine amylase levels ≥140.00 U/L had significantly higher risks of post-operative pancreatic fistula (POPF) grade C (definition of POPF done according to the ISGP) (RR:20.26; 95% CI: 1.18-347.07; p=0.038), readmission to hospital (RR: 6.61; 95% CI: 1.53-28.58; p=0.011), reoperation (RR: 5.67; 95% CI: 1.27-25.27; p=0.023), and mortality (RR:17.00; 95% CI: 2.33-123.80; p=0.005) than patients with urine amylase levels <140.00 U/L. Urine amylase levels on POD1 displayed strong and significant positive correlations with serum amylase levels (r=0.92, p=0.001) and amylase levels in drains (r=0.86, p=0.002). We can conclude that urine amylase levels on POD1 have good prognostic value for post-operative complications after Whipple resection and might be used as an additional predictive risk factor.

Uvod: Depresivnost, anksiozonost i stres predstavljaju značajan javnozdravstveni problem kako u svijetu, tako i u Republici Srpskoj. Ovi mentalni poremećaji se učestalije javljaju kod pacijenata oboljelih od hroničnih bolesti. Cilj: Ispitati zastupljenost depresivnosti, anksioznosti i stresa kod oboljelih od hroničnih bolesti (hipertenzija, astma, hronična obstruktivna bolest pluća, dijabetes melitus, maligne bolesti, stanje poslije infarkta miokarda). Ispitati uticaj sociodemografskih faktora (pol, dob, stručna sprema, sadašnji radni status, porodični status) na prevalenciju depresivnosti, anksioznosti i stresa. Ispitati korišćenje anksiolitika za smanjenje prisutnih simptoma. Materijal i metode: Istraživanje je studija presjeka, provedena anketiranjem pacijenata starijih od 18 godina registrovanih u timovima porodične medicine Domu zdravlja Banja Luka u periodu od 1.08.2018. do 1.04.2019. Za procjenu postojanja anksioznosti, depresivnosti i stresa korištena je DASS– 21 skala, sociodemografski podaci su upisivani u samostalno kreiran upitnik. Pacijenti su izabrani iz registra pacijenata sa hroničnim bolestima. Rezultati: Istraživanjem je obuhvaćeno 405 pacijenata oboljelih od hroničnih bolesti. U odnosu na pacijente oboljele od drugih hroničnih bolesti u grupi pacijenata nakon infarkta miokarda statistički značajno najviše je bila izražena depresivnost (p=0.008, 95% CI 8.761-14.412); anksioznost (P= 0.002, 95% CI 19.2444-15.2038) i stres (p=0.016, 95% CI 13.130-18.655). U grupi pacijenata sa hroničnim bolestima 156 (38,5%) pacijenata koristi lijekove za smanjenje tegoba. Zaključak: Rezultati našeg istraživanja su pokazali visok nivo stresa, anksioznosti i depresivnosti kod pacijenata oboljelih od hroničnih bolesti, što upućuje na potrebu preduzimanja mjera za smanjenje stepena ovih mentalnih poremećaja.

Due to the SARS-CoV-2 pandemic, the faculties have been met with the task of modifying the traditional teaching environment to remote teaching. During two semesters of remote teaching, the students of the Department of Psychology from the Faculty of Humanities and Social Sciences of University of Mostar have been assessing their skills of using technologies, their motivation for class attendance and assignment completion, as well as their time management skills; they have evaluated the teaching process, reported on technical difficulties and assessed the general satisfaction with the remote teaching process. The results of this research show that students have shown a greater assessment of skills of using technology during the second semester of the remote teaching process, while no difference was established in the level of motivation for class attendance and assignment completion, and no difference was found in time management skills between the two semesters. As far as the satisfaction with remote teaching is concerned, the students marked the teaching process with an average grade of “very good” in both semesters, although the mark “excellent” was given more frequently in the second semester than expected per case. The average grade of satisfaction with the teaching process offers insight into the efficacy of adaption to remote teaching, and also opens up space for further improvement.

Upper esophageal sphincter opening (UESO), and laryngeal vestibule closure (LVC) are two essential kinematic events whose timings are crucial for adequate bolus clearance and airway protection during swallowing. Their temporal characteristics can be quantified through time‐consuming analysis of videofluoroscopic swallow studies (VFSS).