University of Donja Gorica
  • Podgorica, Montenegro
Recent publications
The paper refers to a new method to quantify the energy losses due to frictional effects and imperfections in contacts in the case of real industrial tribomechanical systems. Whereby energy losses represent an integral indicator of quality of the real industrial tribomechanical system, in terms of the characteristics of the contact element materials, geometric accuracy, and manufacturing and assembly errors. This paper presents a complex theoretical model based on the differential equation of motion of a real tribomechanical system down a steep plane. The outputs of the theoretical model are exact mathematical expressions that define the current values of the coefficient of friction and the friction-caused energy losses. The measuring system enables the quantification of current values of the distance traveled per unit of time. Based on a series of experimentally determined values of distance traveled per unit of time, the values of energy losses of the real industrial tribomechanical system are determined using the developed theoretical model and the appropriate software support. The obtained results indicate a high reliability, a large potential, and a wide range of possible applications of the proposed method.
Aluminium provides many advantages as a construction material in civil engineering, such as for example light weight, functionality by extruded profiles and corrosion resistance. It is obvious to use these advantages also for trusses. However, most aluminium alloys develop zones of weakening due to welding. The so called heat affected zones (HAZ) reduce the load‐bearing capacity of welded aluminium joints by up to 50%. Consequently, the design and execution of welded X‐joints within lattice girders are challenging. Indeed, the design of welded aluminium X‐joints is not specifically treated in EN 1999. Until now, the calculation of aluminium welded X‐joints relies on the steel standard EN 1993‐1‐8, which does not take into account the characteristic of aluminium. This results in errors and inefficient design. Thus, in this experimental research project the behavior of welded X‐joints in real‐scale models is explored. To this purpose, tests have been carried out on lattice girders made from aluminium alloy EN AW 6082 T6. In total, six girders with varying coefficient β and shape of the hollow section of brace members have been investigated. Thereby, the girders were loaded vertically until the failure of the X‐joints. Strains at the brace and chord members were measured by strain gauges and respective stresses were derived. In addition, a comparative analysis between experimentally and theoretically ‐ based on Eurocodes (EN 1993 part 1‐8 and EN 1999 part 1‐1) ‐ obtained results has been made. The analysis shows that the reduction of the load‐bearing capacity of welded aluminium X‐joints due to the HAZ is not constant but varies with the value of coefficient β and the shape of the cross‐section of the brace member. Obviously, the design of welded aluminium X‐joints based on EN 1993‐1‐8 applying a constant value for the HAZ does not reflect the true behavior of these joints as it leads to a quite conservative design approach.
Purpose: The aim of this study was to evaluate the psychometric properties of the Farsi version of the Surgical Anxiety Questionnaire. Design: Cross-sectional study. Methods: This study was performed on 402 patients who were candidates for elective surgery in Mashhad [East Iran) hospitals in winter 2021. After forward-backward translation, face and content validity checks were performed qualitatively. The construct validity was assessed by exploratory and confirmatory factor analysis. Data analysis was performed with SPSS 16 and AMOS 26. Findings: In exploratory factor analysis, two factors were extracted: concerns about surgery and anesthesia; and post-discharge concerns, which explained 52% of the total variance. The Cronbach’s alpha for the entire questionnaire was 0.91 and for the subscales ranged from 0.80 to 0.87. The final model had a good fit as determined by confirmatory factor analysis. Conclusions: The Farsi version of the surgical anxiety questionnaire has acceptable validity and reliability. The existence of this scale measuring domain-specific anxiety allows for further research in this area
Physiological changes associated with aging increase the risk for the development of age-related diseases. This increase is non-specific to the type of age-related disease, although each disease develops through a unique pathophysiologic mechanism. People who age at a faster rate develop age-related diseases earlier in their life. They have an older “biological age” compared to their “chronological age”. Early detection of individuals with accelerated aging would allow timely intervention to postpone the onset of age-related diseases. This would increase their life expectancy and their length of good quality life. The goal of this study was to investigate whether retinal microvascular complexity could be used as a biomarker of biological age. Retinal images of 68 participants ages ranging from 19 to 82 years were collected in an observational cross-sectional study. Twenty of the old participants had age-related diseases such as hypertension, type 2 diabetes, and/or Alzheimer’s dementia. The rest of the participants were healthy. Retinal images were captured by a hand-held, non-mydriatic fundus camera and quantification of the microvascular complexity was performed by using Sholl’s, box-counting fractal, and lacunarity analysis. In the healthy subjects, increasing chronological age was associated with lower retinal microvascular complexity measured by Sholl’s analysis. Decreased box-counting fractal dimension was present in old patients, and this decrease was 2.1 times faster in participants who had age-related diseases (p = 0.047). Retinal microvascular complexity could be a promising new biomarker of biological age. The data from this study is the first of this kind collected in Montenegro. It is freely available for use.
Health informatics plays a crucial role in modern healthcare provision. Training and continuous education are essential to bolster the healthcare workforce on health informatics. In this work, we present the training events within EU-funded DigNest project. The aim of the training events, the subjects offered, and the overall evaluation of the results are described in this paper.
In this paper, we present a study on the utilization of smart medical wearables and the user manuals of such devices. A total of 342 individuals provided input for 18 questions that address user behavior in the investigated context and the connections between various assessments and preferences. The presented work clusters individuals based on their professional relation to user manuals and analyzes the obtained results separately for these groups.
The YOLO series of object detection algorithms, including YOLOv4 and YOLOv5, have shown superior performance in various medical diagnostic tasks, surpassing human ability in some cases. However, their black-box nature has limited their adoption in medical applications that require trust and explainability of model decisions. To address this issue, visual explanations for AI models, known as visual XAI, have been proposed in the form of heatmaps that highlight regions in the input that contributed most to a particular decision. Gradient-based approaches, such as Grad-CAM [1], and non-gradient-based approaches, such as Eigen-CAM [2], are applicable to YOLO models and do not require new layer implementation. This paper evaluates the performance of Grad-CAM and Eigen-CAM on the VinDrCXR Chest X-ray Abnormalities Detection dataset [3] and discusses the limitations of these methods for explaining model decisions to data scientists.
Physiological changes associated with aging increase the risk for the development of age-related diseases. This increase is nonspecific to the type of age-related disease, although each desease develops through a unique pathophysiologic mechanism. People who age at a faster rate develop age-related diseases earlier in their life. They have an older “biological age” compared to their “chronological age”. Early detection of individuals with accelerated aging would allow timely intervention to postpone the onset of age-related diseases. This would not only increase their life expectancy, but would also increase their length of good quality life. The goal of this study was to investigate whether retinal microvascular complexity could be used as a biomarker of biological age. To test this, retinal images of 68 participants ages ranging from 19 to 82 years were collected in an observational cross-sectional study. Twenty of the old participants had age-related diseases such as hypertension, type 2 diabetes, and/or Alzheimer’s dementia, while the rest of the participants were healthy. Retinal images were captured by a hand-held, non-mydriatic fundus camera and quantification of the microvascular complexity was performed by using Sholl’s, box-counting fractal, and lacunarity analysis. In healthy subjects, increasing chronological age was associated with lower retinal microvascular complexity measured by Sholl’s analysis (young healthy vs. old healthy mean=716.1 vs. 637.6, p=0.010). Decreased box-counting fractal dimension was present in old patients with age-related diseases (old healthy vs. old with age-related diseases mean=1.358 vs. 1.324, p=0.031). Retinal microvascular complexity could be a promising new biomarker of biological age.
This research describes the use of high-performance computing (HPC) and deep learning to create prediction models that could be deployed on edge AI devices equipped with camera and installed in poultry farms. The main idea is to leverage an existing IoT farming platform and use HPC offline to run deep learning to train the models for object detection and object segmentation, where the objects are chickens in images taken on farm. The models can be ported from HPC to edge AI devices to create a new type of computer vision kit to enhance the existing digital poultry farm platform. Such new sensors enable implementing functions such as counting chickens, detection of dead chickens, and even assessing their weight or detecting uneven growth. These functions combined with the monitoring of environmental parameters, could enable early disease detection and improve the decision-making process. The experiment focused on Faster R-CNN architectures and AutoML was used to identify the most suitable architecture for chicken detection and segmentation for the given dataset. For the selected architectures, further hyperparameter optimization was carried out and we achieved the accuracy of AP = 85%, AP50 = 98%, and AP75 = 96% for object detection and AP = 90%, AP50 = 98%, and AP75 = 96% for instance segmentation. These models were installed on edge AI devices and evaluated in the online mode on actual poultry farms. Initial results are promising, but further development of the dataset and improvements in prediction models is needed.
This paper focuses on solving digital transformation challenges in educational system. In addition to traditional information systems employed in education there is a trend of adding new features based on the latest megatrends such as artificial intelligence and blockchain. Specifically, this paper discusses an approach on how blockchain technology can be utilized to implement a system for keeping student records and diploma verification. Including blockchain technology in the process of keeping records on students' diplomas may bring many benefits. It provides students with control of their academic identity and provides means for displaying verified credentials in their electronic records, which may simplify later use of their electronic CVs or copies of diplomas. The use of blockchain should increase trust into electronic records to all of the stakeholders involved in the process and could in the near future minimize the possibility to modify or falsify student credentials.
This study aimed to investigate the application of machine learning techniques for disease prediction. Three popular machine learning algorithms, Random Forest, Support Vector Machines and Naive Bayes, were employed and their performance was evaluated. Results showed that the best performing model was based on Random Forest algorithm with the average accuracy of 87%. This model has been additionally tuned in order to achieve even better performance, which resulted with 90% accuracy. This study highlights the potential of AI in disease prediction and provides insights into the importance of algorithm selection and tuning for optimal performance.
The concentrations of cadmium (Cd), lead (Pb), mercury (Hg) and arsenic (As) were determined in 455 samples of 27 species of vegetables and 28 different processed vegetables collected during the period from January 2015 to December 2017. Vegetables (n = 387) and vegetable products (n = 68) originated from 31 countries, including Serbia. The samples were analysed by inductively coupled plasma – optical emission spectrometry (ICP-OES). The concentrations of Cd, Pb, Hg and As in the vegetables and vegetable products were compared to the maximum levels set by the European Union and the Serbian legislation. The concentration of mercury was less than the limit of detection in each analysed sample. One or multiple measurable toxic metals (Cd, Pb and/or As) were found in 250 samples (54.9%; n = 455). According to the Regulations which were valid until the end of August 2021, the maximum levels of Cd, Pb and As were exceeded in 19 samples (4.2% of the samples of vegetable and vegetable products; n = 455), i.e. in 13 samples of vegetables: Cd in three, Pb in nine and As in one sample and in 6 samples of vegetables products: Cd in three, Pb in one and As in two samples. Regarding the new EU and Serbian legislation which is valid since September 2021 the maximum levels of Cd and Pb for vegetables and vegetable products were exceeded in 118 samples (25.9% of the samples of vegetable and vegetable products; n = 455), i.e. in 95 samples of vegetables: Cd in 67 and Pb in 28 samples and in 23 samples of vegetable products: Cd in 20 and Pb in 3 samples.
The digitization and general industrial development of Montenegro is a great challenge for engineering and science due to its special characteristics. As the accession of Montenegro to the European Union has been an ongoing agenda for over a decade now, and the accession of the country is expected by 2025, adapting the interconnectivity and smart automation of Industry 4.0 plays an essential role in reducing the current gap between Montenegro and EU member states. In this paper, we investigate the present and potential future digitization efforts in the fields of Cooperative Intelligent Transport Systems (C-ITS), agriculture, and healthcare in Montenegro. Our work takes into consideration the characteristics of the country and analyzes the considerations and implications regarding the deployment of state-of-the-art technologies in the investigated fields.
Background: The necessity of setting up high-resolution models is essential to timely forecast dangerous meteorological phenomena. Objective: This study presents a verification of the numerical Weather Research and Forecasting non-hydrostatic Mesoscale Model (WRF NMM) for weather prediction using the High-Performance Computing (HPC) cluster over the complex relief of Montenegro. Methods: Verification was performed comparing WRF NMM predicted values and measured values for temperature, wind and precipitation for six Montenegrin weather stations in a five-year period using statistical parameters. The difficult task of adjusting the model over the complex Montenegrin terrain is caused by a rapid altitude change in in the coastal area, numerous karst fields, basins, river valleys and canyons, large areas of artificial lakes on a relatively small terrain. Results: Based on the obtained verification results, the results of the model vary during time of day, the season of the year, the altitude of the station for which the model results were verified, as well as the surrounding relief for them. The results show the best performance in the central region and show deviations for some metrological measures in some periods of the year. Conclusion: This study can give recommendations on how to adapt a numerical model to a real situation in order to produce better weather forecast for the public.
Institution pages aggregate content on ResearchGate related to an institution. The members listed on this page have self-identified as being affiliated with this institution. Publications listed on this page were identified by our algorithms as relating to this institution. This page was not created or approved by the institution. If you represent an institution and have questions about these pages or wish to report inaccurate content, you can contact us here.
481 members
Selman Repišti
  • Applied Psychology
Tomo Popovic
  • Faculty of Information Systems and Technologies
Jadranka Kaludjerovic
  • Faculty of International Economics, Finance and Business
Aleksandra Martinovic
  • Faculty of Food Safety, Food Technology and Ecology
Marko Simeunović
  • Faculty of Information Systems and Technologies
Information
Address
Oktoih 1, 81000, Podgorica, Montenegro
Head of institution
Prof. Veselin Vukotić
Website
http://www.udg.edu.me/en/
Phone
+382 20-410-777
Fax
+382 20-410-766