RFOS - Repository of Faculty of Organizational Sciences Univ. of Belgrade
Not a member yet
2871 research outputs found
Sort by
Integrated sustainable transportation modelling approaches for electronic passenger vehicle in the context of industry 5.0
No full textGlobally, governments are contributing to the four main concerns of this century, namely, boosting urban air quality, halting climate change, ensuring energy security and mitigating human health issues associated with air pollution. These concerns are primarily driven by the transportation industry 5.0. Sustainable transportation in the context of Industry 5.0 considers three factors, namely, economic, environmental and social developments, one of which is a conversion to electric vehicles (EVs) as a mode of transportation industry 5.0. Therefore, significant efforts are being exerted to integrate sustainable transportation modelling approaches (ISTMA) for electronic passenger vehicle (EPV) supportive industry 5.0. Selecting the most sustainable ISTMA for EPV in the context of Industry 5.0 is a crucial decision in sustainable transportation industry 5.0 and fell under the multi-criteria decision-making (MCDM) problem due to the five fundamental issues, namely, multiple evaluation criteria, the varying priorities of these criteria, the presence of several levels of criteria diminishes the weight of criteria with sub-criteria, criteria trade-offs and data variation. In this paper, a novel ISTMAs for EPV benchmarking that integrates probabilistic hesitant fuzzy set-fuzzy-weighted zero-inconsistency (P-H-FWZIC) and multiplicative multi-objective Optimisation by ratio analysis (MULTIMOORA) methods are proposed on the basis of the established scoring decision matrix. The proposed integrated methods are used in the first stage to establish decision matrices based on the intersection of the sub-levels of criteria with ISTMAs for EPV using feed-forward data presentation and backward scoring process (BSP) procedures, on this basis, a scoring decision matrix based on intersection between the sustainability in the context of Industry 5.0 and other main criteria with ISTMAs for EPV is established. P-H-FWZIC method is used to accomplish multiple functions, including the evaluation of market share (MS) criterion and weighting the criteria. MULTIMOORA method is used to accomplish multiple functions, including the establishing of scoring decision matrix and the benchmarking of ISTMAs for EPV. A total of ISTMAs for EPV are evaluated and benchmarked on the basis of the identified main criteria with respect to sub levels of criteria. According to the P-H-FWZIC results, the Sus (Sustainability) criterion receives the highest priority with weight value of (0.4722), followed by the SS (Supply Side) and DS (Demand Side) criteria with weight values of (0.3667), and (0.1612), respectively. The MULTIMOORA results reveal that ISTMA1, ISTMA7 and ISTMA2 are the top three sustainable approaches for EPV in the context of Industry 5.0. Lastly, the reliability of the integrated MCDM methods is validated and evaluated using sensitivity analysis and the Spearman correlation coefficient test as well as comparison analysis
A Methodological Approach For Converting Relational To Graph Databases
No full textGraph databases are better for data containing many relationships, and are most common with social networks and similar information systems. Many systems that would benefit from using graph databases do not utilize them. This paper aims to increase their adoption rate by streamlining the migration process.
The main question answered in this paper is which steps should be taken to reliably and consistently transfer data from a relational DBMS (DataBase Management System) to a graph DBMS. A demonstration of the transfer is provided, along with a comparison between queries in the two environments.
Microsoft Access is used to manage the relational database, while Neo4j and the Cypher query language are used for the graph database. The approach can be used by institutions and companies to make their information systems better suited to their work areas
Development of a Quality-Based Model for Software Architecture Optimization: A Case Study of Monolith and Microservice Architectures
No full textVarious architectures can be applied in software design. The aim of this research is to examine a typical implementation of Jakarta EE monolithic and microservice software architectures in the context of software quality attributes. Software quality standards are used to define quality models, as well as quality characteristics and sub-characteristics, i.e., software quality attributes. This paper evaluates monolithic and microservice architectures in the context of Coupling, Testability, Security, Complexity, Deployability, and Availability quality attributes. The performed examinations yielded a quality-based mixed integer goal programming mathematical model for software architecture optimization. The model incorporates various software metrics and considers their maximal, minimal or targeted values, as well as upper and lower deviations. The objective is the sum of all deviations, which should be minimal. Considering the presented model, a solution which incorporated multiple monoliths and microservices was defined. This way, the internal structure of the software is defined in a consistent and symmetrical context, while the external software behavior remains unchanged. In addition, an intersection point of monolithic and microservice software architectures, where software metrics obtain the same values, was introduced. Within the intersection point, either one of the architectures can be applied. With the exception of some metrics, an increase in the number of features leads to a value increase of software metrics in microservice software architecture, whilst these values are constant in monolithic software architecture. An increase in the number of features indicated a quality attribute's importance for the software system should be examined and an appropriate architecture should be selected accordingly. Finally, practical recommendations regarding software architectures in terms of software quality were given. Since each software system needs to meet non-functional in addition to functional requirements, a quality-driven software engineering can be established
Generic compliance of industrial PPE by using deep learning techniques
No full textInability of safety managers to timely detect misuse of Personal protective equipment (PPE) causes a number of injuries and financial losses. Considering sizes of industry halls and number of workers, there is an increasing demand for computerized tools that could help companies to enhance the implementation of strictinging workplace safety standards. As a solution, we propose a procedure that: 1) reduces the problem of PPE compliance to the binary classification, and 2) enables compliance of arbitrary type and number of PPE that could be mounted on various body parts. To prove this hypothesis, we studied 18 different PPE types used across various industries for protecting 5 physiological body parts/functions. The HigherHRNet pose estimator was used for defining the PPE regions of interest, while six different image classification architectures were assessed for the compliance/classification of the considered regions. All classifiers were pretrained on the ImageNet data set and fine-tuned using the dedicated data set developed during this study. Top-performing models were MobileNetV2, Dense-Net, and ResNet, while the MobileNetV2 was recommended as the most optimal choice considering its lower computation demands. Compared to previous studies, the proposed approach demonstrated competing performances with unique ability to be easily adopted for performing compliance of various PPE by slight editing of the predefined lists of PPE types and corresponding body parts. Considering the present data/privacy/ computational constraints, the procedure is recommended as suited for the digitalization of PPE compliance in: 1) self-check points, and 2) safety-critical workplaces
Revealing the regulation of learning strategies of MOOC retakers: A learning analytic study
No full textMassive Open Online Courses (MOOCs) have already shown a great potential to be used as an alternative model for teacher professional development (TPD). Not only do MOOCs offer relevant content and activities, but they also provide opportunities for strengthening the skills for self regulated learning of teachers as life-long learners. In this study, we focused on a unique subgroup of MOOC learners - retakers who take the same TPD MOOC multiple times. In the empirical study reported in this paper, we examined what learning strategies they choose when taking a TPD MOOC and the extent to which they are able to adapt their learning strategies to improve their performance in the subsequent attempts. By using learning analytic methods, we detected five learning strategies and eight major forms of strategy change adapted by MOOC retakers. We found that two strategy changes (from Content-Oriented Strategy to Intensive-Thorough Strategy or Balanced Strategy) with associated with significantly higher performance in the subsequent attempts compared to no change in strategy. Our findings have implications for MOOC instructors and providers about the ways they can support MOOC retakers. Our findings also suggest that MOOCs are not only valuable TPD resources for teachers, but they also have unique opportunities for strengthening the self-regulation skills of teacher learners as the "by-products of learning"
A Machine Learning Approach for Learning Temporal Point Process
No full textDespite a vast application of temporal point processes in infectious disease diffusion forecasting, ecommerce, traffic prediction, preventive maintenance, etc, there is no significant development in improving the simulation and prediction of temporal point processes in real-world environments. With this problem at hand, we propose a novel methodology for learning temporal point processes based on one-dimensional numerical integration techniques. These techniques are used for linearising the negative maximum likelihood (neML) function and enabling backpropagation of the neML derivatives. Our approach is tested on two real-life datasets. Firstly, on high frequency point process data, (prediction of highway traffic) and secondly, on a very low frequency point processes dataset, (prediction of ski injuries in ski resorts). Four different point process baseline models were compared: second-order Polynomial inhomogeneous process, Hawkes process with exponential kernel, Gaussian process, and Poisson process. The results show the ability of the proposed methodology to generalize on different datasets and illustrate how different numerical integration techniques and mathematical models influence the quality of the obtained models. The presented methodology is not limited to these datasets and can be further used to optimize and predict other processes that are based on temporal point processes
A New Type-3 Fuzzy PID for Energy Management in Microgrids
No full textMore recently, type-3 (T3) fuzzy logic systems (FLSs) with better learning ability and uncertainty modeling have been presented. On other hand, the proportional-integral-derivative (PID) is commonly employed in most industrial control systems, because of its simplicity and efficiency. The measurement errors, nonlinearities, and uncertainties degrade the performance of conventional PIDs. In this study, for the first time, a new T3-FLS-based PID scheme with deep learning approach is introduced. In addition to rules, the parameters of fuzzy sets are also tuned such that a fast regulation efficiency is obtained. Unlike the most conventional approaches, the suggested tuning approach is done in an online scheme. Also, a nonsingleton fuzzification is suggested to reduce the effect of sensor errors. The proposed scheme is examined on a case-study microgrid (MG), and its good frequency stabilization performance is demonstrated in various hard conditions such as variable load, unknown dynamics, and variation in renewable energy (RE) sources
Defining Software Architecture Modalities Based on Event Sourcing Architecture Pattern
No full textThe main focus of this paper is the development of data-intensive systems. One of the key issues is maintaining consistency while being able to promptly process frequent data requests. The central premise is that CQRS (Command Query Responsibility Segregation) and Event sourcing concepts can be utilized for addressing these challenges. To ensure the development of a system that would be capable of executing the immense number of required operations, yet at the same time provide the desired reliability, a software architecture (combining CQRS, Event sourcing, and the Service Fabric) is proposed based on a real-life project. Furthermore, several modalities of the architecture are defined to be used in different scenarios, depending on the volume of data that is to be processed. The presented modalities of the described software architecture were then implemented as a part of the information system that supports the organization and grading of exams for an immense number of candidates. Consequently, a large volume of data is generated, and the proposed architecture has proven best suited for reporting purposes which will be described in this paper
Approach to multi-attribute decision-making problems based on neutrality aggregation operators of T-spherical fuzzy information
No full textIn the process of decision-making, uncertain information is always challenging to deal with. T-spherical fuzzy set (TSFS) operates vagueness of data by analysing three independent functions, namely membership, non-membership, and abstinence function. The TSFS provides us robust scheme with parameter q >= 1 to handle the countless opportunities. Hence, this set proves its superiority over the existing picture fuzzy set (PFS) and spherical fuzzy set (SFS). Now a day, decision-makers usually assign impartial values throughout the assessment. This manuscript demonstrates some new operational laws by fusing the neutral characteristics of the degrees of membership and using the probability sum (PS) function. Meanwhile, we determine several aggregation operators (AOs) including weighted averaging neutral, ordered weighed neutral, and hybrid averaging neutral AOs to aggregate the data under T-spherical fuzzy (TSF) environment. As it came to the notice that weighted neutral averaging aggregation operators of the Pythagorean fuzzy set (PyFS), single-valued neutrosophic fuzzy set (SVNFS), and q-rung orthopair fuzzy set (q-ROFS) have some restrictions during the decision-making problems. So, to overcome this, we introduce a new multi-attribute group decision-making method (MAGDM) based on proposed AOs. Lastly, we provide various numerical instances to explain the method and exhibit its supremacy. Furthermore, a comparative analysis is conducted to compare the potential of proposed AOs with some other existing methods
Value relevance of accounting earnings and cash flows in a transition economy: the case of Serbia
No full textPurpose The purpose of the study is to investigate the association of earnings and cash flows with stock prices and returns, and the impact of regulatory changes on the value relevance of accounting numbers. Design/methodology/approach The authors examine a sample of non-financial firms listed on the Belgrade Stock Exchange from 2005 to 2018 and use three regression models - price, return and differenced. Findings The authors find evidence that accounting earnings are more value relevant than cash flows. The authors also find negative relation of earnings changes with stock returns and argue that this is due to the lower persistence of negative earnings levels and changes. Finally, the authors find that the value relevance of accounting information in Serbia increases after the improvements in capital market regulation. Research limitations/implications Given the empirical focus on a transition economy, the widespread applicability of the study is limited. The findings, however, call for more research on transition economies to better understand the functioning of capital markets and the way information from financial statements is incorporated into stock prices. Practical implications The results imply that policymakers in transition economies should improve the accounting and capital market regulation to provide better investor protection and to improve the capital market conditions. Originality/value The authors add to knowledge about the value relevance of accounting information in emerging and transition economies. The results could be of interest to standard setters in their efforts to better understand and improve the quality of accounting information in emerging and transition economies