Прегледај по Аутор "Stojčić, Mirko"
Сада се приказује 1 - 7 од 7
Резултати по страници
Опције сортирања
- СтавкаAdaptive Modeling of Prediction of Telecommunications Network Throughput Performances in the Domain of Motorway Coverage(MDPI, 2021) Banjanin, Milorad K.; Stojčić, Mirko; Drajić, Dejan; Ćurguz, Zoran; Milanović, Zoran; Stjepanović, AleksandarThe main goal of this paper is to create an adaptive model based on multilayer perceptron (MLP) for prediction of average downlink (DL) data throughput per user and average DL data throughput per cell within an LTE network technology and in a geo-space that includes a segment of the Motorway 9th January with the access roads. The accuracy of model prediction is estimated based on relative error (RE). With multiple trainings and testing of 30 different variants of the MLP model, with different metaparameters the final model was chosen whose average accuracy for the Cell Downlink Average Throughput variable is 89.6% (RE = 0.104), while for the Average User Downlink Throughput variable the average accuracy is 88% (RE = 0.120). If the coefficient of determination is observed, the results showed that the accuracy of the best selected prediction model for the first variable is 1.4% higher than the accuracy of the prediction of the selected model for the second dependent variable. In addition, the results showed that the performance of the MLP model expressed over R2 was significantly better compared to the reference multiple linear regression (MLR) model used.
- СтавкаANFIS MODEL FOR THE PREDICTION OF GENERA TED ELECTRICITY OF PHOTO VOLTAIC MODULES(2019) Stojčić, Mirko; Stjepanović, Aleksandar; Stjepanović, ĐorđeThe fact that conventional energy sources are exhaustive and limited are increasingly encouraging research in the field of alternative and renewable energy sources. The electricity generated by solar photovoltaic modules and panels occupies an ever greater percentage in total electricity production, so it is clear that photovoltaic systems are increasingly integrating with the existing electricity network into one system or functioning as autonomous systems. The aim of the research is to create a model based on the principles of the fuzzy logic and artificial neural networks that will perform the task of predicting the maximum energy of photovoltaic modules as accurately as possible. The prediction should facilitate work in planning production and consumption, system management, economic analysis. The most important methods used in the research are modeling and simulation. Input and output variables are selected and in the ANFIS (Adaptive Neuro Fuzzy Inference System) model a set of their values is presented. Based on them it comes to the function of dependency. The prediction rating of the created model was performed on a separate data set for testing and a model with the lowest average test error value was selected. The performance of the model was compared with the mathematical model through sensitivity analysis, which led to the conclusion that the ANFIS model gives more accurate results.
- СтавкаApplication of MCDM Methods in Sustainability Engineering: A Literature Review 2008–2018(MDPI, 2019) Stojčić, Mirko; Kazimieras Zavadskas, Edmundas; Pamučar, Dragan; Stević, Željko; Mardani, AbbasSustainability is one of the main challenges of the recent decades. In this regard, several prior studies have used different techniques and approaches for solving this problem in the field of sustainability engineering. Multiple criteria decision making (MCDM) is an important technique that presents a systematic approach for helping decisionmakers in this field. The main goal of this paper is to review the literature concerning the application of MCDM methods in the field of sustainable engineering. The Web of Science (WoS) Core Collection Database was chosen to identify 108 papers in the period of 2008–2018. The selected papers were classified into five categories, including construction and infrastructure, supply chains, transport and logistics, energy, and other. In addition, the articles were classified based on author, year, application area, study objective and problem, applied methods, number of published papers, and name of the journal. The results of this paper show that sustainable engineering is an area that is quite suitable for the use of MCDM. It can be concluded that most of the methods used in sustainable engineering are based on traditional approaches with a noticeable trend towards applying the theory of uncertainty, such as fuzzy, grey, rough, and neutrosophic theory.
- СтавкаAPPLICATION OF THE ANFIS MODEL IN ROAD TRAFFIC AND TRANSPORT ATION : A LITERATURE REVIEW FROM 1993 TO 2018(2018) Stojčić, MirkoThe paper’s focus is on researching the application of the ANFIS (Adaptive Neuro Fuzzy Inference System) model in traffic and transport through a review of relevant papers. The ANFIS, as an element of artificial intelligence, is widely used in intelligent transport systems. All collected papers are divided into 7 sub-areas, namely: 1) vehicle routing, 2) traffic control at intersections with light signaling, 3) vehicle steering and control, 4) safety, 5) modeling of fuel consumption, engine performance and exhaust emissions, 6) traffic congestion prediction, and 7) other applications. For each sub-area, the analysis of the proposed models is performed with a tabular overview of respective input and output variables, while in the third section the discussion of the results is given. It is found that the steering and control of vehicles represent a sub-area with the highest percentage in the total number of examined papers, while the security applications take second place
- СтавкаDevelopment of an ANFIS Model for the Optimization of a Queuing System in Warehouses(MDPI, 2018) Stojčić, Mirko; Pamučar, Dragan; Mahmutagić, Eldina; Stević, ŽeljkoQueuing systems (QS) represent everyday life in all business and economic systems. On the one hand, and there is a tendency for their time and cost optimization, but on the other hand, they have not been sufficiently explored. This especially applies to logistics systems, where a large number of transportation and storage units appear. Therefore, the aim of this paper is to develop an ANFIS (Adaptive neuro-fuzzy inference system) model in a warehouse system with two servers for defining QS optimization parameters. The research was conducted in a company for the manufacturing of brown paper located in the territory of Bosnia and Herzegovina, which represents a significant share of the total export production of the country. In this paper, the optimization criterion is the time spent in the system, which is important both from the aspect of all customers of the system, and from that of the owner of the company. The time criterion directly affects the efficiency of the system, but also the overall costs that this system causes. The developed ANFIS model was compared with a mathematical model through a sensitivity analysis. The mathematical model showed outstanding results, which justifies its development and application.
- СтавкаMULTIFACTOR INFLUENCES ON THE QUALITY OF EXPERIENCE SERVICE USERS OF TELECOMMUNICATION PROVIDERS IN THE REPUBLIC OF SRPSKA, BOSNIA AND HERZEGOVINA(University of Montenegro, 2023) Banjanin, Milorad K.; Maričić, Goran; Stojčić, MirkoThe paper investigates multidisciplinary factors influencing the quality of experience (QoE) of service users of telecommunication provider as an open-structured stock-company of people who are creators of services and applications and/or proactive service users. The quality of user experience QoE is created and improved over time under multifactorial influences. The aim of this paper is to analyze legal-regulatory, socio-contextual, technological-process and stock-company ,factors as input independent variables and subjective-user factors as transition variables of influence on motivation, behavior and user satisfaction in the Model of influences factors (MIF). The output from MIF is dependent variable QoE. MIF was created on a perceptual and reference path with interactively related factors of all influences on QoE through subjective-user assessment. The quality of MIF was verified by statistical significance analysis among variables of paired factors influencing QoE using SPSS technology, regression analysis, and the Boosted Desedions Tree technique of machine learning method.
- СтавкаPredictive Modeling of Delay in an LTE Network by Optimizing the Number of Predictors Using Dimensionality Reduction Techniques(MDPI, 2023) Stojčić, Mirko; Banjanin, Milorad K.; Vasiljević, Milan; Nedić, Dragana; Stjepanović, Aleksandar; Danilović, Dejan; Puzić, GoranDelay in data transmission is one of the key performance indicators (KPIs) of a network. The planning and design value of delay in network management is of crucial importance for the optimal allocation of network resources and their performance focuses. To create optimal solutions, predictive models, which are currently most often based on machine learning (ML), are used. This paper aims to investigate the training, testing and selection of the best predictive delay model for a VoIP service in a Long Term Evolution (LTE) network using three ML techniques: Multilayer Perceptron (MLP), Support Vector Machines (SVM) and k-Nearest Neighbors (k-NN). The space of model input variables is optimized by dimensionality reduction techniques: RReliefF algorithm, Backward selection via the recursive feature elimination algorithm and the Pareto 80/20 rule. A three-segment road in the geo-space between the cities of Banja Luka (BL) and Doboj (Db) in the Republic of Srpska (RS), Bosnia and Herzegovina (BiH), covered by the cellular network (LTE) of the M:tel BL operator was chosen for the case study. The results show that the k-NN model has been selected as the best solution in all three optimization approaches. For the RReliefF optimization algorithm, the best model has six inputs and the minimum relative error (RE) RE = 0.109. For the Backward selection via the recursive feature elimination algorithm, the best model has four inputs and RE = 0.041. Finally, for the Pareto 80/20 rule, the best model has 11 inputs and RE = 0.049. The comparative analysis of the results concludes that, according to observed criteria for the selection of the final model, the best solution is an approach to optimizing the number of predictors based on the Backward selection via the recursive feature elimination algorithm.