RFOS - Repository of Faculty of Organizational Sciences Univ. of Belgrade
Not a member yet
2871 research outputs found
Sort by
On some sharp estimates of toeplitz operator in some spaces of hardy-lizorkin type of analytic functions in the polydisc
No full textWe provide some new sharp assertions on the action of the Toeplitz operator T phi in new F-alpha(p,q) type spaces of analytic functions of several complex variables extending previously known assertions proved by various authors
An AI-based Approach for Grading Students' Collaboration
No full textSoft skills (such as communication and collaboration) are rarely addressed in programming courses, mostly because they are difficult to teach, assess, and grade. A quantitative, modular, AI-based approach for assessing and grading students' collaboration has been examined in this paper. The pedagogical underpinning of the approach includes a pedagogical framework and a quantitative soft skill assessment rubric, which have been adapted and used in an extracurricular Java programming course. The objective was to identify pros and cons of using different AI methods within this approach when it comes to assessing and grading collaboration in group programming projects. More specifically, fuzzy rules and several machine learning methods (ML onward) have been examined to see which one would yield the best results regarding performance, interpretability/explainability of recommendations and feasibility/practicality. The data used for training and testing span four academic years, and the results suggest that almost all of the examined AI methods, when used within the proposed AI-based approach, can provide adequate grading recommendations as long as teachers cover other aspects of the assessment not covered by the rubrics: code quality, plagiarism, and project completion. The fuzzy-rule-based method requires time and effort to be spent on (manual) creation and tuning of fuzzy rules and sets, whereas the examined ML methods require lesser initial investments but do need historical data for training. On the other hand, the fuzzy-rule-based method can provide the best explanations on how the assessment/grading was made - something that proved to be very important to teachers. IEE
Do we Reach Desired Disparate Impact with In-Processing Fairness Techniques?
No full textUsing machine learning algorithms in social environments and systems requires stricter and more detailed control. More specifically, the cost of error in such systems is much higher. Therefore, one should ensure that important decisions, such as whether to convict a person or not based on the previous criminal record, are by the legal requirements and not biased toward a group of people. One can find many many papers in the literature aimed at mitigating or eliminating unwanted bias in machine learning models. A significant part of these efforts add fairness constraint to the mathematical model or adds a regularization term to the loss function. In this paper, we show that optimizing the loss function given the fairness constraint or regularization for unfairness can surprisingly yield unfair solutions. This is due to the linear relaxation of the fairness function. By analyzing the gap between the true value of fairness and the one obtained using linear relaxation, we found that the gap can be as high as around 21% for the COMPAS dataset, and around 35% for the Adult dataset. In addition, we show that the fairness gap is consistent regardless of the strength of the fairness constraint or regularization
Project financing of renewable energy projects a bibliometric analysis and future research agenda
No full textThe effective transition from fossil towards renewable energy sources requires gigantic investments. Simultaneously, financing the transition towards clean energy production is a conundrum for both theory and practice. Renewable energy project finance is seen as an important tool for this transition. The aim of this paper is to overview (i) the scholarly output (authors, journals, citations), (ii) geographical distribution of research, and (iii) most intensively elaborated sub -areas of project financing of renewable energy projects. A bibliometric analysis has been applied to a sample of 73 papers retrieved from the Web of Science database. The results indicate that the interest in this topic among scholars has been steadily growing in the last few decades. In addition, this paper provides a potential direction for future research
Risk assessment of financing renewable energy projects: A case study of financing a small hydropower plant project in Serbia
No full textThis study proposed a novel approach for conducting the credit risk assessment of financing a small hydropower plant (SHPP) project in Serbia via the failure mode and effects analysis (FMEA), which was modified by the Dempster-Shafer Theory (DST). A qualitative analysis of financing the SHPP project was performed to identify and describe the risk events that may cause loan default. To conduct the risk assessment, experts with experience in SHPP project financing in Serbia were required to evaluate the occurrence and severity of the identified risk events and their ability to detect them. Considering the epistemic uncertainty to which they were exposed, the experts assigned multiple ratings and their mass functions according to DST. Thereafter, the proposed FMEA-DST methodology was applied to identify the risk events that required the special attention of credit risk managers. Finally, adequate mitigation strategies that will reduce the credit risk of SHPP project finance in Serbia were proposed for the identified risk events. The research results demonstrated the effectiveness of the proposed approach as a comprehensive framework, which credit risk managers can employ to evaluate project finance requests
Sustainable Energy Consumption Model for Textile Industry Using Fully Intuitionistic Fuzzy Optimization Approach
No full textConsumption of renewable energy is on the rise because new technologies have made it cheaper and easier to meet the needs of a long-term energy source. In the present study, the idea of optimal usage of sustainable energy is discussed, taking into consideration the environmental and economic conditions that exist in Pakistan's textile manufacturing industry. By taking into account the regional potential for the application of renewable energy resources, solar energy generators are taken into consideration, and a fully intuitionistic fuzzy (FIF) textile energy model is constructed. Using the FIF model to determine the optimal distribution of solar energy units resulted in a tolerable number of unused energy units. These units may be returned to the central power supply station, which would save both money and energy
A conceptual model of procurement management for new products in the automotive industry
No full textThe automotive industry is one of the most dynamic and challenging business areas in the European Union (EU) and wider. It implies a complex supply chain with a turnover of 7% of EU GDP (gross domestic product) and 6.1% of total EU employment and has an important multiplier effect on the economy. Given the apparent impact of automotive companies on the economy, they are under constant pressure to review and improve their production processes, business activities, and market position. It can be said that each process that supports the creation of new value in the automotive industry is of equal importance. The focal point of this paper is the procurement management process for new products. Considered procurement is related to the components of the products purchased for the first time. These procurements have a direct impact on business expenses. Therefore, the paper proposes a conceptual model to improve the procurement of new products components. The model is developed following modern control theory and based on the feedback loop principle. All elements of a feedback loop (reference, system, sensor, comparator, and controller) are described. The model development is based on a case of a large company from the automotive industry in the Republic of Serbia
Redesigning the composite index of sharing economy: issues and perspectives
No full textThe sharing economy has significantly influenced changes in consumer behaviour and attitudes. As a consequence, it altered business models and transactions with a vast number of organizations around the globe accommodating their business operations and algorithms according to the uprising demand for sharing economy services. Furthermore, many countries, regions and/or cities whose economic prosperity depends on the tourism industry are forced to adhere to such global trends strategically and on time. An objective of this study is to propose the usage of composite index methodology in the evaluation of the availability of countries’/cities’ sharing economy services. The evaluated LATAM Sharing Economy Index 2021 evaluates and ranks the 44 biggest cities in Latin America. The index consists of a few main indicators describing the overall level of availability of crucial sharing economy services such as flat-sharing, e-scooters, car-sharing applications, gym sharing, and ride-hailing services. The paper will shed additional light on the methodological challenges when building composite indexes for sharing economy
The Outcomes of Lean Implementation in High-Mix/Low-Volume Industry – Literature Review
No full textMany companies in the world have used lean to achieve significant improvements in both efficiency and effectiveness. However, most evidence of lean implementation stem from manufacturing environment similar to one lean was developed in, i.e. product-focused and to-stock Low-Mix/High-Volume (LMHV) manufacturing. High-Mix/Low-Volume (HMLV) industry, on the other hand, is usually process-focused, with to-order manufacturing, and as such it comes with specific set of goals and priorities, and possibly different set of lean implementation outcomes. This paper aims at investigating the outcomes of lean implementation with a specific focus on High-Mix/Low-Volume. For this purpose, a systematic literature review procedure was conducted, in order to analyze implementation reports from state-of-the-art literature. The results show that HMLV companies mostly report efficiency related, easily quantifiable outcomes, stressing the positive side of lean. What literature lacks to report are intermediary outcomes (e.g. better understanding of processes, teamwork and collaboration, problem solving abilities), as well as results regarding customer satisfaction. In addition, reports also lack the issue of outcomes sustainability, as most papers show evidence from short-term case studies.DOI: 10.1007/978-3-030-97947-8_3