RFOS - Repository of Faculty of Organizational Sciences Univ. of Belgrade
Not a member yet
2871 research outputs found
Sort by
Structured prediction of sparse dependent variables for traffic state estimation in large-scale networks
No full textCurrently, one of the biggest challenges in modern traffic engineering is related to traffic state estimation (TSE). Although many machine learning and domain models can be used for TSE, they do not consider the sparsity and spatial dependence of traffic state variables. In this paper, we propose a hybrid soft computing model of two Gaussian conditional random field (GCRF) models for the inference of traffic speed, which is a relevant variable for TSE and travel information systems. The proposed model can infer the traffic state variables in large-scale networks whose nodes are geographically dispersed. Moreover, by combining a Gaussian conditional random field binary classification model (GCRFBC), which classifies traffic regimes as free-flow or potentially congested, and a regression GCRF model for the prediction of traffic speed in potentially congested traffic regimes, the model addresses two specifics of the problem: sparsity in traffic data, and the fact that observations are not independent. The proposed model was tested on two large-scale real-world networks in Serbia, namely an arterial E70-E75 335 km long highway stretch and the major ski resort Kopaonik with 55 km of ski slopes. In addition, the proposed model showed better prediction performance than several other unstructured and structured models
Algorithm for Energy Resource Selection Using Priority Degree-Based Aggregation Operators with Generalized Orthopair Fuzzy Information and Aczel–Alsina Aggregation Operators
No full textMany aggregation operators are studied to deal with multi-criteria group decision-making problems. Whenever information has two aspects, intuitionistic fuzzy sets and Pythagorean fuzzy sets are employed to handle the information. However, q-rung orthopair fuzzy sets are more flexible and suitable because they cover information widely. The current paper primarily focuses on the multi-criteria group decision-making technique based on prioritization and two robust aggregation operators based on Aczel–Alsina t-norm and t-conorm. This paper suggests two new aggregation operators based on q-rung orthopair fuzzy information and Aczel–Alsina t-norm and t-conorm, respectively. Firstly, novel q-rung orthopair fuzzy prioritized Aczel–Alsina averaging and q-rung orthopair fuzzy prioritized Aczel–Alsina geometric operators are proposed, involving priority weights of the information. Several related results of the proposed aggregation operators are investigated to see their diversity. A multi-criteria group decision-making algorithm based on newly established aggregation operators is developed, and a comprehensive numerical example for the selection of the most suitable energy resource is carried out. The proposed aggregation operators are compared with other operators to see some advantages of the proposed work. The proposed aggregation operators have a wider range for handling information, with priority degrees, and are based on novel Aczel–Alsina t-norm and t-conorm
Mathematical analysis of generative adversarial networks based on complex picture fuzzy soft information
No full textGenerative Adversarial Networks (GANs) are the models that generate data samples from the statistical distribution of the data. It is one of the most well-known branches of machine learning and deep learning. Different techniques are involved in the processing and production of visual data, which sometimes gives rise to misperception uncertainties. Bearing this issue in mind, we define some solid mathematical concepts to model and resolve the stated problem named complex picture fuzzy soft relations (CPFSRs) which is defined by the Cartesian product (CP) of two complex picture fuzzy soft sets (CPFSSs). The major objective of this study is to develop some innovative and useful notions that may be used to handle difficult and inconsistent information in practical situations. The proposed notion is foremost and superior to the prevailing ideas, where the presented idea is the improved technique of two different theories, named picture fuzzy set (PFS) and soft set (SS). Additionally, it presents the picture fuzzy soft set (PFSS) in professional decision-making by reducing complexions. The evaluated CPFSRs are the improved versions of soft relations, fuzzy relations, complex soft relations, and complex fuzzy relations. Therefore, this paper provides modeling methodologies based on CPFSRs which are used for the analysis of electing the best GAN for effective working. In the process, the score functions are also formulated and analyzed. Finally, a comparative study of existing techniques has been done to show the validity of the proposed work
Evaluation of Metaverse traffic safety implementations using fuzzy Einstein based logarithmic methodology of additive weights and TOPSIS method
No full textAs the Metaverse's popularity grows, its effect on everyday problems is beginning to be discussed. The upcoming Metaverse world will influence the transportation system as cross-border lines blur due to rapid globalization. The purpose of this paper is to investigate the capabilities of the Metaverse and its alternatives to traffic safety, as well as to prioritize its advantages. The case study is based on a densely populated metropolis with an extensive education system. The city's decision-makers will have to weigh the pros and cons of the Metaverse's effect on traffic safety. To illustrate the complex forces that drive the decision-making process in traffic safety, we create a case study with four alternatives to Metaverse's integration into the traffic system. Alternatives are evaluated using twelve criteria that reflect the decision problem's rules and regulations, technology, socioeconomic, and traffic aspects. In this study, fuzzy Einstein based logarithmic methodology of additive weights (LMAW) is applied to calculate the weights of the criteria. We present a new framework that combines Einstein norms and the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) method to rank the alternatives. The findings of this study show that public transportation is the most appropriate area for implementing the Metaverse into traffic safety because of its practical opportunities and broad usage area
Enhancing e-learning effectiveness: analyzing extrinsic and intrinsic factors influencing students’ use, learning, and performance in higher education
No full textAs a result of the pandemic, but also of the rapid advancement of technology in general, e-learning has emerged as a popular method of education, providing students with flexibility and accessibility. Understanding the factors that influence students’ levels of learning and accomplishment in this digital learning environment is therefore critical for teachers and institutions seeking to increase the effectiveness of teaching and knowledge transfer via e-learning platforms. A number of variables that might improve or impair student use, learning, and performance affect how successful e-learning actually is. In order to maximize the benefits of e-learning and guarantee successful student results, educators and policymakers must have a thorough understanding of these elements. The purpose of this study is to investigate the impact of extrinsic and intrinsic factors on students’ use, learning level, and performance in the setting of e-learning in higher education in two countries. This study evaluates the impact of extrinsic elements such as course content, e-learning system quality, institutional and teacher support, as well as intrinsic aspects such as personal innovativeness, self-efficacy, and information sharing in two countries. The study takes a quantitative approach, and the analysis was carried out using the structural equations method to examine the combined influence of numerous extrinsic and intrinsic elements on the use of e-learning, as well as learning level and performance.The research results show that the course content and e-learning system, personal innovativeness, self-efficacy, and knowledge sharing have a positive influence on the intention to use e-learning. Also, the intention of using an e-learning system will increase the actual use of e-learning technologies, which will ultimately result in better learning performance. The findings of this study will help educators, policymakers, and e-learning platform developers create effective ways for optimizing student experiences and promoting good learning outcomes in higher education settings.https://rdcu.be/dnja
Leveraging Open Banking: Challenges and Opportunities
No full textThe main goal of this research is to examine the application of innovative open banking models and services through the lens of the end users. Many countries have already started the process of writing regulations for open banking and its assorted services. These regulations are often written before the technology is entirely embraced by its intended users, and for this reason acceptance studies are of crucial importance in ascertaining the user expectations and the intended scope of their use. For this purpose, we present an UTAUT-2 based acceptance study which deals with user acceptance of open banking coupled with other notable technologies such as blockchain. By enabling open banking through the blockchain, many benefits could be achieved, primarily when dealing with trust and privacy of user data. These benefits are expected to play an influential part in raising the acceptance levels of open banking as a whole. Through the analysis of the model, we have identified several notable influential factors that can play a large part in the behavioral intention of users, and as such can be used as a guideline for the development of new and innovative open banking services
Blockchain-based C2C Business Models in a Smart City
No full textThis article discusses the potential of C2C business models in a smart city. The goal is to analyze the benefits of implementing blockchain technology in collision with IoT by increasing safety and transparency of collected information. In the article, creation of blockchain and smart city infrastructure as a platform for future development of various services is proposed. This way, businesses would be able to develop specific solutions that promote sharing economy with less difficulty. This article proposes an extended business model covering multiple aspects specific for the case of smart cities. Lastly, the results and conclusions of the short survey of our target group, regarding preliminary readiness assessment, are presented
Navigating Project Success - A Deep Dive Into The Influence Of MS Project
No full textThe pursuit of identifying critical factors for project success persists due to the evolving global business landscape. Concurrently, studies have substantiated that Project Management software tools enhance project success rates. This article investigates the impact of Microsoft Project, on project success factors. 14 semi-structured interviews were conducted with industry and academic experts. Respondents employed the Analytic Hierarchy Process (AHP) to assess 12 success factors. Results yielded ranked lists of factors and categories, each with calculated weights. Microsoft Project was found to significantly enhance team communication and realistic planning of time, resources, and costs. However, its impact on stakeholder communication and team competence development was modest. Notably, it predominantly contributes to project management, while its role in portfolio management is minor. These findings offer valuable insights for companies, showcasing a direct correlation between MS Project use and organizational success, potentially boosting project success rates
THE INFLUENCE OF CIRCULAR ECONOMY ON SUSTAINABLE DEVELOPMENT: EUROPEAN AND SERBIAN EXPERIENCE
No full textThe paper analyzes the influence of circular economy indicators on economic growth and the creation of new jobs, with a special focus on green jobs. In the last decade, circular economy has received rising attention worldwide as a way to replace the current production and consumption model based on a linear economy. By promoting closing the loop by applying the 6Rs (rethink, refuse, reduce, reuse, recycle and repair) with a particular emphasis on municipal waste, the circular economy aims to achieve better harmony between the environment, economy and well-being of society. EU member states have implemented various policies and initiatives, such as the Circular Economy Package, which aims to increase recycling rates, reduce landfilling and promote eco-design. Additionally, circular economy plays a central role in the new European Green Deal in its aim to tackle climate change. The Republic of Serbia has also recognized the importance of sustainable development and has developed its National Sustainable Development Strategy, which aims to promote economic, social and environmental sustainability. Using European Statistical Office (Eurostat) data from 27 European countries pertaining to the years between 2014 and 2021, this paper aims to examine the relationship between the circular economy, economic growth and job creation. Based on the cluster analysis, EU members are divided into several groups. Also, the results obtained from the regression analysis for EU member states were compared with the current state of application of the circular economy in Serbia, using data from the Statistical Office of the Republic of Serbia. Although the implementation of the circular economy in Serbia lags behind the EU average, there is untapped potential for further progress, especially in the field of energy. The results suggest that a circular economy provides opportunities to create competitive advantages and promote sustainable economic growth, which can be beneficial to decision-makers
Testing, assessment and evaluation in an online environment: a case study of tertiary ESP courses
No full textModern technologies have irreversibly changed the educational process. Numerous virtual learning environments (VLEs), learning management systems (LMSs), communication platforms and other software tools not only enable easier communication and content sharing, but can also be used in measuring students’ achievement at almost all levels of education. This paper presents the use of software tools and platforms for testing, assessing and evaluating students’ knowledge and language skills in several courses in English for Specific Purposes (ESP) at a business-oriented university. The tools presented include Moodle LMS, MS Forms, MS Teams, Socrative, Mentimeter, and Kahoot!. After listing the functionalities of these platforms and tools and presenting their advantages and drawbacks, the paper compares testing, assessment and evaluation done in the traditional classroom environment with the ones conducted online, focusing on the benefits and limitations of each enviroment