This paper is dedicated to machine learning, the branches of machine learning, which include the methods for solving this issue, and the practical implementation of the solution to the automatic image description generation. Automatic image caption generation is one of the frequent goals of computer vision. Image description generation models must solve a larger number of complex problems to have this task successfully solved. The objects in the image must be detected and recognized, after which a logical and syntactically correct textual description is generated. For that reason, description generation is a complex problem. It is an extremely important challenge for machine learning algorithms because it represents an impersonation of a complicated human ability to encapsulate huge amounts of highlighted visual pieces of information in descriptive language. The results of the generated descriptions are compared depending on the used pretrained convolutional networks. The BLEU metrics are used to calculate the quality of the image description. Although the solution to the problem of image description automatic generation does provide us with good results, there is yet room for improvement since there are images that are not adequately described.

For almost two years now, the world has been facing major economic challenges, precisely struggling how to adjust the business in a period of a pandemic. It can be said with great certainty that there are very few economic entities to which the pandemic has left no trace or caused visible consequences on business. However, we can perceive the crisis as a chance for further development or an opportunity to show that we can achieve better results compared to the competition. One of the ways to improve the usage of mobile application in catering facilities is the implementation of digital technologies. Accordingly, the main goal of this paper is to determine whether there is an impact of digital technologies on the usage of mobile application in catering facilities. The methods used for the research will be a survey as a method of quantitative research, and an interview as a method of qualitative research. The expected results of the research are to determine whether there is an impact of the of digital technologies on the usage of mobile application at catering facilities.

The logistics performance index (LPI) represents an important indicator of the state of logistics and its development in countries. The LPI is directly linked to the level of economic system development, and as such provides an adequate basis for the improvement of economy, through logistics and trade. The aim of this paper is to determine the impact of sensitivity analysis on the evaluation and ranking of the LPI in the Balkan countries, according to the report of the World Bank. Sensitivity analysis implies the change of the importance of six criteria based on which the LPI ranking is done. The multi-criteria decision-making model (MCDM), which consists of CRITIC and MARCOS methods for determining the LPI rank in the Balkan countries, was previously used. Criteria weights are simulated through 36 scenarios, whereby the weights of the observed criteria change in the range of 15% - 90%. The final results show that criteria values play very important role in the ranking of the Balkan countries, when it comes to the LPI.

The cornelian cherry (Cornus mas L.) is considered to be one of those medicinal plants with important nutritional and therapeutic properties. The plant shows resistance against abiotic and biotic stressors in natural growing conditions and could be suitable to use in sustainable fruit production. This study was carried out on 22 local cornelian cherry (Cornus mas L.) genotypes, which were grown northwest of Bosnia and Herzegovina. Fruits of these 22 genotypes were harvested and analyzed during the ripening period in 2018/2019. Fruit weight, length, and width ranged from 1.38 to 3.01 g, 13.84 to 19.43 mm, and 10.92 to 14.79 mm, respectively. Dry matter content was determined to be the lowest at 11.67% and the highest at 21.89%. The genotypes had vitamin C content between 25.85 and 58.75 mg/100 g. Total phenolic and anthocyanin content were found to be quite variable among genotypes and ranged from 1240 to 6958 mg gallic acid equivalents (GAE) per 100 g fresh weight (FW) and 55.57 to 205.6 mg cyaniding-3-glucoside equivalents (CGE) per 100 g FW, respectively. The content of phosphorus and iron were between 155.52 to 263.06 mg per 100 g and 0.25 to 0.93 mg per 100 g, respectively. Principal Component Analysis (PCA) showed that the first and second components accounted for 44.05% and 60.50% of the total variance, and the major proportion of the first and second components were the morphometric properties and chemical traits of the cornelian cherry fruits. The results revealed that the characterized genotypes could be important for cornelian cherry breeders as ready crossing materials to obtain new cornelian cherry varieties and shows the potential of certain genotypes as a valuable source of natural antioxidants. The results may have served as a guide towards the development of sustainable production programs for cornelian cherries as well.

In the original publication of the article, the initial of Professor Stefan Priebe has been incorrectly published as ‘P’ instead of’S’. The correct author name is given in this erratum.

Millimeter wave (mmWave) communication technique has been developed rapidly because of many advantages of high speed, large bandwidth, and ultra-low delay. However, mmWave communications systems suffer from fast fading and frequent blocking. Hence, the ideal communication environment for mmWave is line of sight (LOS) channel. To improve the efficiency and capacity of mmWave system, and to better build the Internet of Everything (IoE) service network, this paper focuses on the channel identification technique in LOS and non-line of sight (NLOS) environments. Considering the limited computing ability of user equipments (UEs), this paper proposes a novel channel identification architecture based on eigen features, i.e. eigenmatrix and eigenvector (EMEV) of channel state information (CSI). Furthermore, this paper explores clustered delay line (CDL) channel identification with mmWave, which is defined by the 3rd generation partnership project (3GPP). The experimental results show that the EMEV based scheme can achieve identification accuracy of 99.88% assuming perfect CSI. In the robustness test, the maximum noise can be tolerated is $\text{SNR} = 16 \mathbf{dB}$, with the threshold $acc\geq$ 95%. What is more, the novel architecture based on EMEV feature will reduce the comprehensive overhead by about 90%.

ABSTRACT The effect of environmental transformations on organizational identity in universities has been addressed from different perspectives, yet considering micro-dynamics and impact on actual practices of academic work has been neglected. This article addresses this gap by analyzing how institutional field prescriptions relative to an environmental transformation have been internalized into organizational members’ practices and what effect it has on the collective understanding of organizational identity. Our analytical context is represented by two schools at the biggest Dutch higher education organization. While most studies emphasize contestation and fragmentation with multiple interpretations of organizational identity within the same higher education organization during or as a consequence of environmental transformations, the analyzed case presents contrary results. Organizational members were consistent in describing their own organizational practices across schools. The stable and shared identity is strengthened via anti-identity through two distinct mechanisms: the process of socialization and contrasting to academia. Additionally, we show how through a third mechanism (association to the professional field) organizational members draw on the institutional field prescriptions to legitimize their teaching and research practices. Thus, this paper demonstrates that organizational identity can be stable and non-fragmented even when higher education organizations face and implement changes.

Optimization of logistics processes and activities in the function of supply-chain sustainability is a great challenge for logistics companies. It is necessary to rationalize processes in accordance with the strict requirements of the market, while respecting aspects of sustainability, which is not an easy task. Multicriteria decision making can be a tool that contributes to the optimization of logistics processes in terms of making the right decisions and evaluating different strategies in different logistics subsystems. In this paper, we considered the warehousing system as one of the most important logistics subsystems in a company. Conditions and the possibility of implementing barcode technology in order to optimize warehousing processes were evaluated. We formed a strengths, weaknesses, opportunities, and threats (SWOT) matrix consisting of a total of 27 elements. In order to determine the weights of all factors at the first level of decision making and its indicators at the second level of the decision making hierarchy, an original model was developed. This model involved the creation of a novel grey full-consistency method (FUCOM-G) and integration with a SWOT analysis. Since it was a matter of group decision making, we developed a novel grey Hamy aggregator that, by adequately treating uncertainties and ambiguities, contributed to making more precise decisions. The original grey FUCOM-SWOT model based on the grey Hamy aggregator represents a contribution to the entire field of decision making and optimization of logistics processes. Based on the applied model, the obtained results showed that Weaknesses, as part of the SWOT matrix, are currently the most dominant indicators, and that the implementation of barcode technology in a warehousing system is justified.

Objectives: To investigate country-specific drivers and barriers of positive COVID-19 vaccine intentions in the Federation of Bosnia and Herzegovina (FBiH), one of the two entities comprising Bosnia and Herzegovina. Methods: A cross-sectional study design was used, using an online behavioural insights survey tool adapted to the context of FBiH. Three survey waves, each including approximately 1,000 adults, were conducted in July, September and December 2020. Fixed-effects regression analysis was used to explore the drivers, barriers and attitudes towards accepting a future COVID-19 vaccine. Results: COVID-19 risk perception, trust in health institutions and negative affect were positive predictors of positive COVID-19 vaccine intentions, as were living in urban areas and having a college education (versus having primary or secondary education). Conversely, being female, feeling that the pandemic was overhyped by the media and the country of vaccine production were negative predictors. Conclusion: This study provided snapshots on the state of attitudes regarding a future COVID-19 vaccine acceptance and hesitancy in 2020. These findings provided useful insights into the efforts to introduce and roll out the COVID-19 vaccines in FBiH. Further efforts should focus on better understanding the demographic, cultural and behavioural contexts of COVID-related vaccination perceptions in FBiH.

Background Delayed treatment of Achilles tendon ruptures is generally due to either misdiagnosis or patient delay. When the treatment is delayed more than 4 weeks, the rupture is defined as “chronic”, and almost always requires more invasive surgery and longer rehabilitation time compared with acute Achilles tendon ruptures. There is insufficient knowledge of patient experiences of sustaining and recovering from a chronic Achilles tendon rupture. Methods To evaluate patients’ experiences of suffering a chronic Achilles tendon rupture, semi-structured group interviews were conducted 4–6 years after surgical treatment using a semi-structured interview guide. The data were analyzed using qualitative content analysis described by Graneheim and Lundman. Results The experiences of ten patients (65 ± 14 years, 7 males and 3 females) were summarized into four main categories: (1) “The injury”, where the patients described immediate functional impairments, following either traumatic or non-traumatic injury mechanisms that were misinterpreted by themselves or the health-care system; (2) “The diagnosis”, where the patients expressed relief in receiving the diagnosis, but also disappointment and/or frustration related to the prior misdiagnosis and delay; (3) “The treatment”, where the patients expressed high expectations, consistent satisfaction with the surgical treatment, and addressed the importance of the physical therapist having the right expertise; and (4) “The outcomes”, where the patients expressed an overall satisfaction with the long-term outcome and no obvious limitations in physical activity, although some fear of re-injury emerged. Conclusions An Achilles tendon rupture can occur during both major and minor trauma and be misinterpreted by both the assessing health-care professional as well as the patient themselves. Surgical treatment and postoperative rehabilitation for chronic Achilles tendon rupture results in overall patient satisfaction in terms of the long-term outcomes. We emphasize the need for increased awareness of the occurrence of Achilles tendon rupture in patients with an atypical patient history.

The SARS-CoV-2 pandemic has been the main public health issue since the end of 2019. The vaccination campaign in Bosnia and Herzegovina started in April 2021, with several vaccines available. Our study aimed to evaluate the acceptance, effects, and tolerability of vaccines against SARS-CoV-2 among cancer patients. We conducted a cross-sectional, observational study between 22 October and 30 November 2021, at the Clinic of Oncology, Clinical Center University of Sarajevo. Patients were enrolled during their regular visit to the Clinic of Oncology by agreeing to complete an individual paper questionnaire. The study included 1063 patients with malignant diseases, of whom 681 (64.1%) were adequately vaccinated patients. In the study population, 76.9% of patients reported that they did not experience any side effects due to vaccination, while only 0.5% had side effects, causing a delay in their treatment. Among adequately vaccinated patients, there were 40 patients (3.8%) who were infected with SARS-CoV-2 after the second or booster dose of the vaccine. Five patients (0.5%) were hospitalized due to COVID-19 after being adequately vaccinated. The findings of our study suggest that cancer patients have a higher acceptance of vaccines against SARS-CoV-2 than the general population in Bosnia and Herzegovina. Vaccination side effects are tolerable and do not cause major delays in specific cancer treatment. The protective effects of COVID-19 vaccines in the cancer patients presented in our study are comparable to available results of similar studies, which included the general population.

In this research, the results of bentonite characterization (pH value of bentonite suspension, point of zero charge, cation exchange capacity,  SEM, XRF, DTG) are presented. The results of lead (II) removal efficiency at initial lead (II) concentrations of 200, 300 and 400 mg/L, and biosorbent dosage of 1 gram in 50 ml of lead(II) solution,  are also presented, as well as the values of the Freundlich and Langmuir constants from the Freundlich and Langmuir adsorption isotherms. The obtained results showed that removal efficiency is high for all three examined initial lead (II) concentrations, and it is above 99%. The lead (II) removal efficiency slightly decreases with an increase in initial lead concentration. Experimental data obtained from adsorption experiment with contact time of 2.5 minutes, stirring rate 100 rpm, temperature 250C and pH value 5 are better fitted with the linearized Langmuir equation isotherm, giving an R2 value closest to unity (0.9994), than to linearized Freundlich equation (0.9886).

Traffic safety is one of the key issues nowadays, given the fact that a large number of people lose their lives in traffic accidents every day. There are various influential factors in the occurrence of traffic accidents, the number of vehicles being one of them. This paper assesses the traffic safety in Montenegro in the period 1998-2020 by applying the multiphase modeling with a purpose to obtain comparative results which enable implementation of adequate strategies. A total of six scenarios were formed with two inputs and two outputs in a DEA (Data Envelopment Analysis) model, with the number of registered vehicles per year being an input in all scenarios. In addition, as inputs, the scenarios included AADT (Annual Average Daily Traffic), passengers in road transport, passenger-km by road transport, goods transported by road, tone-km by road, and passengers in local transport. The number of traffic accidents with casualties, the number of traffic accidents with material damage, the number of fatal cases and the number of injured persons, depending on a scenario, were observed as outputs. After the DEA model, IMF SWARA (Improved Fuzzy Stepwise Weight Assessment Ratio Analysis) was applied to determine the weights of inputs and outputs, while the final state of traffic safety by years was determined using the MARCOS (Measurement of alternatives and ranking according to COmpromise solution) method.

Sequencing of cell-free DNA (cfDNA) in cancer patients' plasma offers a minimally-invasive solution to detect tumor cell genomic alterations to aid real-time clinical decision-making. The reliability of copy number detection decreases at lower cfDNA tumor fractions, limiting utility at earlier stages of the disease. To test a novel strategy for detection of allelic imbalance, we developed a prostate cancer bespoke assay, PCF_SELECT, that includes an innovative sequencing panel covering ∼25 000 high minor allele frequency SNPs and tailored analytical solutions to enable allele-informed evaluation. First, we assessed it on plasma samples from 50 advanced prostate cancer patients. We then confirmed improved detection of genomic alterations in samples with <10% tumor fractions when compared against an independent assay. Finally, we applied PCF_SELECT to serial plasma samples intensively collected from three patients previously characterized as harboring alterations involving DNA repair genes and consequently offered PARP inhibition. We identified more extensive pan-genome allelic imbalance than previously recognized in prostate cancer. We confirmed high sensitivity detection of BRCA2 allelic imbalance with decreasing tumor fractions resultant from treatment and identified complex ATM genomic states that may be incongruent with protein losses. Overall, we present a framework for sensitive detection of allele-specific copy number changes in cfDNA.