Search

Research in agriculture is a promising field, and crop prediction for particular land areas is especially critical to agriculture. Such prediction depends on the soil, minerals, and environment, the last of which has been short-changed by changing climatic conditions. Consequently, crop prediction for a particular zone presents difficulties for farmers. This is where machine learning (ML) steps in with techniques that are widely applied in agriculture. This work proposes a weighted stacked ensemble (WSE) method for the crop prediction process. It combines two base learners or classifiers to construct the WSE, which is a single predictive ensemble model, using weighted instances. The experimental outcomes show that the proposed WSE outperforms other classification and ensemble techniques in terms of improved crop prediction accuracy. [ABSTRACT FROM AUTHOR]

This paper aims to provide a comprehensive review on Elliptic Curve Cryptography (ECC), a public key cryptographic system and its applications. The paper discusses important mathematical properties and operations of elliptic curves, like point addition and multiplication operations and its implementation in cryptographic methods such as encryption and decryption. This paper provides a detailed workout on important mathematical problems on elliptic curves and ECC which provides insight into working of essential cryptographic techniques in ECC. And the paper also provides a literature review of research works based on ECC in various fields such as Internet of Things (IoT), Cloud computing, Blockchain and Image Security. And the paper further provides insight into the recent applications of ECC in fields like IoT and Blockchain by comprehensively discussing the proposed mechanism for each of the recent applications and also briefly discussing the security of the proposed mechanism. [ABSTRACT FROM AUTHOR]

In this growing world of the internet, most of our daily routine tasks are somehow connected to the internet, from smartphones to internet of things (IoT) devices to cloud networks. Internet users are growing rapidly, and the internet is accessible to everyone from anywhere. Data phishing is a cyber security attack that uses deception to trick internet users to get their content and information. In this attack, malicious users try to steal personal data such as login credentials, credit card details, health care information, etc., of the users on the internet. They exploit users' sensitive information using vulnerabilities. Information stealers are known as phishers. Phishers use different techniques for phishing. One of the most common methods is to direct the users to a false website to enter their login credentials and their details on these phishing sites. Phishing websites look like the original websites. Phishers use these details to get access to the user's accounts and hijack them for monetary purposes. Many internet users fall for this trap of phishing sites and share their personal and sensitive details. In this paper, we will analyze and implement machine learning (ML) techniques to detect phishing attacks. There are different methods to identify phishing attacks, one of them is by checking the uniform resource locator (URL) address using ML. ML is used to teach a machine to differentiate between phishing and original site URLs. There are many different techniques to overcome this attack. This research paper aims to provide accurate and true phishing detection with less time complexity. [ABSTRACT FROM AUTHOR]

Optical character recognition (OCR) is a computer vision technique that enables computers to recognize text from images. Text detection and computer vision have made significant advancements, leading to the development of various OCR technologies. However, selecting the most suitable OCR system for a specific purpose has become a challenging task. This research paper aims to explain the theoretical concepts and mathematical formulas underlying OCR engines, providing a better understanding of their functioning and performance. The analysis covers various aspects, including the theories, algorithms, and techniques employed by OCR engines. This paper presents experiments conducted on five different image categories: vehicle number plates, receipts, handwriting, symbols and plain text images. Evaluation metrics such as Character Error Rate (CER), Word Error Rate (WER), Insertion Error Rate (IER), Deletion Error Rate (DER), End-to-end recognition rate (EEER), Word Error Rate (WER), Recall, Precision, and F1-score were utilized. The findings reveal that OCR systems perform well on plain documents, with recall and F1-score values exceeding 0.85 and 0.8, respectively. However, there are still areas for improvement in OCR, which are discussed in detail in this paper. This research provides valuable insights for researchers, developers, and practitioners interested in employing OCR technology for their commercial projects. [ABSTRACT FROM AUTHOR]

Presents an algorithm for extracting integrated circuit critical areas associated with point defects. Problem of reporting all overlap areas between two sets of rectilinearly-oriented rectangles in the plane; Local layout extraction approach; Definition of critical area for a vertical short as an overlap area of two geometrical objects from two different integrated circuit mask layers.

Background: Despite effective prevention and control strategies, in countries of the Balkan region, cancers are the second leading cause of mortality, closely following circulatory system diseases., Objective: To describe trends in the burden of breast, cervical, and colon and rectum cancer in the Balkan region and per country between 1990 and 2019, including a forecast to 2030., Methods: We described the 2019 Global Burden of Disease (GBD) estimates for breast, cervical, and colon and rectum cancers in eleven Balkan countries over the period 1990-2019, including incidence, years lived with disability (YLD), years of life lost (YLL), and disability-adjusted life years (DALYs) rates per 100,000 population and accompanied 95% uncertainty interval. With the Autoregressive Integrated Moving Average, we forecasted these rates per country up to 2030., Results: In the Balkan region, the highest incidence and DALYs rates in the study period were for colon and rectum, and breast cancers. Over the study period, the DALYs rates for breast cancer per 100,000 population were the highest in Serbia (reaching 670.84 in 2019) but the lowest in Albania (reaching 271.24 in 2019). In 2019, the highest incidence of breast cancer (85 /100,000) and highest YLD rate (64 /100,000) were observed in Greece. Romania had the highest incidence rates, YLD rates, DALY rates, and YLL rates of cervical cancer, with respective 20.59%, 23.39% 4.00%, and 3.47% increases for the 1990/2019 period, and the highest forecasted burden for cervical cancer in 2030. The highest incidence rates, YLD rates and DALY rates of colon and rectum cancers were continuously recorded in Croatia (an increase of 130.75%, 48.23%, and 63.28%, respectively), while the highest YLL rates were in Bulgaria (an increase of 63.85%). The YLL rates due to colon and rectum cancers are forecasted to progress by 2030 in all Balkan countries., Conclusion: As most of the DALYs burden for breast, cervical, and colon and rectum cancer is due to premature mortality, the numerous country-specific barriers to cancer early detection and quality and care continuum should be a public priority of multi-stakeholder collaboration in the Balkan region., (© 2023. BioMed Central Ltd., part of Springer Nature.)

Background: Introduction of vaccines against COVID-19 has not encountered expected acceptance. The uptake of COVID-19 vaccines in Western Balkans countries is lagging behind the European Union average. The aim of our study was to assess the intention to get vaccinated against COVID-19 in the population of unvaccinated adult citizens of five Western Balkans countries, and to explore factors that influence the vaccination intention., Methods: Cross-sectional study was conducted in the period from July to October 2021. The questionnaire was shared through online social media. Intention to get vaccinated against COVID-19 was measured by a single item assessing the likelihood of getting vaccinated on a 5-points Likert scale. Linear regressions were conducted with socio-demographic characteristics, presence of chronic diseases and attitudes towards COVID-19 vaccination as independent factors., Results: The largest proportion of unvaccinated respondents willing to get vaccinated in the future was observed in Montenegro and Albania (40.4% in each country), while in the Serbian sample, the willingness to get vaccinated was the lowest (22.6%). Socio-demographic characteristics were not significantly associated with the intention to get vaccinated against COVID-19 in most of the countries. In Albania, Bosnia and Herzegovina, North Macedonia and Serbia the strongest determinant of COVID-19 vaccination intention was the higher sense of social responsibility., Conclusions: Vaccination interventions and campaigns aiming to improve the COVID-19 vaccine uptake should be focussed on specific set of factors in each country, appealing to social responsibility as most prevalent determinant of vaccination intention in Western Balkans., (© The Author(s) 2023. Published by Oxford University Press on behalf of the European Public Health Association.)

The negative effects of men's excessive alcohol consumption on family members are well known. However, less is known about how men's alcohol dependence is associated with the mental health of their female spouses residing with them. Therefore, the aim of this study was to investigate the prevalence and factors associated with depression, anxiety, and intimate partner violence against women (IPVAW) whose male spouses are undergoing treatment for alcohol dependence. We hypothesize that men with alcohol dependency, who are also violent, present a serious threat to women's mental health. We conducted a cross-sectional study among 104 women whose male partners had been admitted for inpatient treatment for alcohol dependence. Women's depression was measured by the Beck Depression Inventory (BDI-II); anxiety was measured by the Beck Anxiety Inventory (BAI), and exposure to physical and sexual IPVAW was measured by the Conflict Tactics Scale (CTS-2). Multinomial logistic regression analyses were conducted in order to analyze factors associated with depression and anxiety. The prevalence of moderate/severe depression and anxiety among the women was 34.6% and 25.2%, respectively, while almost half (48.1%) experienced IPV during the past 12 months. After adjustments for age, exposure to IPV increased the chances of experiencing moderate/severe depression by 37.5 times (95% CI 7.91-177.76), and 8.15 times for moderate/severe anxiety (95% CI 2.45-27.14). The mental health of women whose partners have alcohol dependence is significantly threatened and should be considered, especially when it is associated with exposure to spousal violence., (© The Author(s), under exclusive licence to Springer Science+Business Media, LLC part of Springer Nature 2021.)

Objectives: The aim of this study was to assess the validity and reliability of the Serbian versions of the Copenhagen Burnout Inventory (CBI) and the Study Burnout Inventory (SBI) among fifth-year medical students at 5 universities in Serbia., Material and Methods: The study included 573 fifthyear medical students at 5 universities in Serbia. The research instrument consisted of SBI and CBI. The reliability of these instruments was assessed using an internal consistency measure (Cronbach's α), an intra-class coefficient (ICC) and factor analysis., Results: Cronbach's α for SBI was 0.83, including for exhaustion 0.73, for cynicism 0.70, and for inadequacy 0.48. The test-retest reliability (ICC) was 0.75. Cronbach's α for personal burnout on CBI was 0.89, for the faculty-related burnout 0.86, and for the faculty-members-related burnout 0.92. Cronbach's α for CBI was 0.93. The factor analysis for SBI showed 2 factors and for CBI 3 factors., Conclusions: This study revealed that the Serbian versions of both SBI and CBI could be used for the assessment of burnout in this population. Int J Occup Med Environ Health. 2021;34(6):737-45., (This work is available in Open Access model and licensed under a CC BY-NC 3.0 PL license.)

Introduction: The outbreak of the disease caused by the novel coronavirus, SARS-CoV-2 named COVID-19 has spread throughout the world. The number of registered cases is increasing and almost no country or territory worldwide has been without any COVID-19 patient. The aim of this study was to examine the level of knowledge on the SARS-COv-2 and COVID-19 among medical students and to explore the differences in attitudes, practices and fear of COVID-19 among students with sufficient and students with insufficient knowledge., Methodology: The cross-sectional study among the 1,722 medical students was conducted through an online platform of the Faculty of Medicine, University of Belgrade. The instrument used was a questionnaire with sections on socio-demographic characteristics, knowledge, attitudes and practices towards COVID-19 and the Fear of COVID-19 scale., Results: Total of 1576 (91.50%) students were in the sufficient knowledge group. The multivariate logistic regression analysis showed that there was a significant association between the sufficient knowledge on COVID-19 and female sex (OR = 1.70, 95% CI = 1.18-2.45), age (OR = 1.10, 95% CI = 1.02-1.18), considering the preventive measures enforced in Serbia as good (OR = 2.57, 95% CI = 1.18-5.56), wearing the surgical mask outside of the household in the past 14 days (OR = 1.87, 95% CI = 1.22-2.87) and score on Fear of COVID-19 scale (OR = 0.94, 95% CI = 0.91-0.98)., Conclusions: Medical students showed good knowledge of COVID-19 and could be a part of the promotion of health education messages as a part of preventive measures., Competing Interests: No Conflict of Interest is declared, (Copyright (c) 2021 Zorica Terzic-Supic, Jovana Todorovic, Milos Bajcetic, Janko Jankovic, Milena Santric-Milicevic, Zeljka Stamenkovic, Bosiljka Djikanovic, Stefan Mandic-Rajcevic, Pavle Piperac, Aleksandra Jovic-Vranes, Bojana Matejic.)

This paper presents an overview of semiconductor materials used in gas sensors, their technology, design, and application. Semiconductor materials include metal oxides, conducting polymers, carbon nanotubes, and 2D materials. Metal oxides are most often the first choice due to their ease of fabrication, low cost, high sensitivity, and stability. Some of their disadvantages are low selectivity and high operating temperature. Conducting polymers have the advantage of a low operating temperature and can detect many organic vapors. They are flexible but affected by humidity. Carbon nanotubes are chemically and mechanically stable and are sensitive towards NO and NH 3 , but need dopants or modifications to sense other gases. Graphene, transition metal chalcogenides, boron nitride, transition metal carbides/nitrides, metal organic frameworks, and metal oxide nanosheets as 2D materials represent gas-sensing materials of the future, especially in medical devices, such as breath sensing. This overview covers the most used semiconducting materials in gas sensing, their synthesis methods and morphology, especially oxide nanostructures, heterostructures, and 2D materials, as well as sensor technology and design, application in advance electronic circuits and systems, and research challenges from the perspective of emerging technologies.

Background: Regular physical activity supports healthy behavior and contributes to the reduction of preventable diseases. Students in their social transition period are the ideal groups for interventions. The higher education period, associated with demanding changes and poor time management, results in a low level of physical activity. In this age, social media usually are a suitable channel of communication and multicomponent interventions are the most desirable. It has not been sufficiently investigated how effective a Web-based approach is among university students when it comes to physical activity in the long-term period. We combined a Web-based approach with motivational interviews and tested these two interventions together and separate to assess their impact on improving the physical activity of medical students 1 year after the intervention., Methods: All 514 first-year students at the Faculty of Medicine in Belgrade were invited to fill in a baseline questionnaire. Also, they underwent measurement of weight, height and waist circumference. After that, students selected a 6 months intervention according to their preference: Intervention through social media (Facebook) (Group 1) or combined with a motivational interview (Group 2). Group 3 consisted of students without any intervention. One year after completion of the 6 months intervention period, all students were invited to a second comprehensive assessment. Analyses were performed employing a wide range of statistical testing, including direct logistic regression, to identify determinants of increased physical activity measured by an average change of Metabolic Equivalent of Task (MET). This outcome measure was defined as the difference between the values at baseline and one year after completion of the 6 months intervention period., Results: Due to a large number of potential determinants of the change of MET, three logistic regression models considered three groups of independent variables: basic socio-demographic and anthropometric data, intervention and willingness for change, and health status with life choices. The only significant model comprised parameters related to the interventions ( p < 0.001). It accurately classified 73.5% of cases. There is a highly significant overall effect for type of intervention (Wald = 19.5, df = 2, p < 0.001) with high odds for the increase of physical activity. Significant relationship between time and type of intervention also existed ( F = 7.33, p < 0.001, partial η 2 = 0.091). The influence of both factors (time and interventions) led to a change (increase) in the dependent variable MET., Conclusion: Our study confirmed the presence of low-level physical activity among students of medicine and showed that multicomponent interventions have significant potential for positive change. The desirable effects of the Web-based intervention are higher if an additional booster is involved, such as a motivational interview., Competing Interests: The authors declare that they have no competing interests., (© 2020 Mandic et al.)

Background: Exclusive breastfeeding is essential for early childhood development, although the use of adaptive milk formulas instead of breastfeeding is widespread nowadays. This study aimed to examine the prevalence of exclusively breastfed infants under the age of 6 months in non-Roma and Roma population and factors associated with this practice. Materials and Methods: This study is a secondary analysis of the Serbian Multiple Indicator Cluster Survey investigating non-Roma and Roma infants under the age of 6 months. The study included mothers of 321 non-Roma and 164 Roma infants younger than 6 months. Univariate and multivariate logistic regression served to analyze factors associated with the practice of exclusive breastfeeding in both populations. Results: The prevalence of exclusive breastfeeding was almost the same among mothers in both non-Roma and Roma population (13.3 vs. 13%, p = 0.910). Exclusive breastfeeding was significantly more often ( p < 0.001) among wealthier women, women whose newborns were over 2,500 g on birth, multipara, and women who had not established menstrual cycle among both populations. Living outside the capital significantly diminishes the chance for exclusively breastfed infants in the non-Roma community (Vojvodina: OR 0.16, CI 95% 0.03-0.92; eastern Serbia: OR 0.02, CI 95% 0.01-0.35) as well as living in the rural area (urban: OR 10.35, CI 95% 1.94-55.28). Unexpectedly, in the non-Roma population, not staying in the same room with the newborn in the maternity ward increases the chance for the baby to be exclusively breastfed (OR 7.19, CI 95% 1.80-28.68). The same pattern has been observed in Roma population. Non-Roma mothers multipara are more likely to exclusively breastfeed their children than primipara (OR 7.78, CI 95% 1.09-20.93), while among Roma mothers, the inverse association has been found although not significant (OR 0.42, CI 95% 0.14-1.23). Attending a childbirth preparation program more than 18 times increases the chances of infants being exclusively breastfed (OR 18.65, CI 95% 1.34-53.67). In the Roma population, there was no single woman that attended a childbirth preparation program. Conclusion: The pattern of exclusive breastfeeding significantly differs between non-Roma and Roma populations. Preventive work should have focus on strengthening support to mothers and medical staff in maternity wards., (Copyright © 2020 Stamenkovic, Matejic, Djikanovic and Bjegovic-Mikanovic.)

Background: The objective of this study was to examine predictors of prenatal smoking, and attempted smoking cessation during pregnancy among Romani women., Methods: A community-based, cross-sectional study (November 2012 to February 2013) of 410 Romani women in Roma settlements in Serbia and Macedonia was conducted. Logistic regression was used to identify predictors of prenatal smoking and attempted smoking cessation during pregnancy., Results: Romani women older than 30 years and those who were living with a man were over twice as likely (adjusted odds ratio (aOR) 2.48, 95% confidence interval (CI) 1.12-5.46; aOR 2.09, 95% CI 1.27-3.43) to smoke during pregnancy, compared to women <20 and married women, respectively. An inverse relationship between education and prenatal smoking was observed (for primary education versus no education, aOR 0.56, 95% CI 0.32-0.98; for secondary or higher education versus no education, aOR 0.38, 95% CI 0.16-0.90). Having a husband/partner who smokes was associated with significantly increased likelihood of prenatal smoking (aOR 3.71, 95% CI 2.20-6.25) and decreased likelihood of attempting to quit (aOR 0.51, 95% CI 0.24-1.06)., Conclusions: Culturally sensitive and comprehensive prevention strategies and intervention programs are needed to reduce smoking during pregnancy among Romani women, including interventions targeting male partners., (© The Author 2016. Published by Oxford University Press on behalf of Faculty of Public Health. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com)

Background Roma are Europe's largest minority population. Serbia and Macedonia have the greatest proportion of Roma outside of the European Union. Our objective was to examine women's agency and how it related to desired timing of pregnancy among Romani women in Macedonia and Serbia. Methods We surveyed 410 Romani women who had given birth in the last 2 years between November 2012-February 2013 in Serbia and Macedonia using purposeful snowball sampling. Log-Poisson models were used to examine the association between women's inclusion in healthcare decision- making and desired timing of pregnancy. Results Romani women in Macedonia and Serbia were excluded from the labor market, with over 80% being unemployed, approximately 30% had no schooling, and 17% were not included in healthcare decisions. Romani women who were sole decision-makers in relation to their health were 1.4 times more likely to desire the timing of their most recent pregnancy [RRR = 1.4, CI (1.1, 1.8)]. Conclusions Romani women who have great involvement in their own healthcare decisions were more likely to desire the timing of their current pregnancy. Women's inclusion in such important decisions is important and empowerment programs that address gender inequity are needed in Romani communities, particularly for control of timing of pregnancy.

Objectives: The aims of this study were to estimate the level of knowledge, attitudes, and intentions about human papillomavirus (HPV) infection and HPV vaccine among gynecologists and to explore predictors of gynecologists' intention to recommend the HPV vaccine., Method: This research was conducted between April and June 2014 among all gynecologists working at women's health departments in all primary health centers in Belgrade, the capital of Serbia, using a specially designed questionnaire., Results: The response rate was 88.2%. The knowledge of gynecologists was estimated as average. The most frequently reported obstacles to HPV vaccination was the financial concern (59.8%). More than two thirds of the gynecologists were willing to recommend the vaccine (68.4%). The factors associated with the gynecologists' intention to recommend the vaccine included their positive attitudes toward boys' vaccination (odds ratio [OR], 8.96; 95% confidence interval [CI], 2.85-28.16), negative attitudes toward frequent changes the recommendations (OR, 0.31; 95% CI, 0.10-0.93), and beliefs that the vaccine application would decrease condom usage (OR, 0.31; 95% CI, 0.06-0.68)., Conclusions: The findings provide an important insight into the current point of view of the gynecologists, which confirms that the better the knowledge of HPV and vaccine, the higher the likelihood of recommending it.

Objective: The present study aimed to identify the role of mother's education in the nutritional status of children aged 2-5 years in Serbia., Design: Nationally representative population-based study. Age- and gender-specific BMI percentiles of children were analysed. In accordance with the WHO growth reference, children with BMI less than the 5th percentile were considered undernourished. Logistic regression was used to calculate the association between mother's education and other socio-economic determinants as possible confounders., Setting: UNICEF's fourth Multiple Indicator Cluster Survey, conducted in both Roma and non-Roma settlements in Serbia., Subjects: Children (n 2603) aged 2-5 years (mean age 3·05 years)., Results: Less than 5 % of children aged 2-5 years were undernourished. There were significantly more undernourished children among the Roma population, in the capital of Serbia and among those whose mothers were less educated. There were statistically significant differences according to mother's education in all socio-economic characteristics (ethnicity, area, region of living and wealth index). Mother's level of education proved to be the most important factor for child's nutritional status; place of living (region) was also associated., Conclusions: Mother's education is the most significant predictor of children's undernutrition. It confirms that investment in females' education will bring benefits and progress not only for women and their children, but also for society as a whole.