Dejan Đukić

12th International Conference on Applied Internet and Information Technologies (AIIT 2022)

Neural networks and their application in object recognition

Popovic, Stefan; Kopanja, Lazar; Popovic, Sonja Djukic; Djukic, Dejan

/

This paper discusses in a concise way the importance and the manner of using neural networks in object recognition. Although the neural network model has been proposed in the middle of the twentieth century, it has experienced its full expansion only today at the end of the first quarter of the twenty-first century. Neural networks are used both in complex security systems and industrial plants and in improving the quality of life through applications that almost the entire population uses in everyday life. Starting from the theoretical foundations for understanding the neural network, we come to their practical application in object recognition.

Neural networks, object recognition, perceptron

Конференцијски рад

eNergetics 2022

Preliminary Research on the Application of Neural Networks to the Combustion Control of Boilers with Automatic Firing

Popović, Stefan; Djukic, Dejan; Popović, Sonja Đukić; Kopanja, Lazar

/

This paper deals with the importance and application of neural networks for improving the operation of boilers with automatic firing. Although the neural network model was illustrated in the middle of the twentieth century, it is experiencing its full expansion only today. Neural networks have a very wide application, both in complex security systems, improving the quality of life through applications used in everyday life, and in industrial plants. The paper starts from the theoretical foundations for understanding neural networks and provides an overview of research conducted on boilers with automatic firing. The conclusion of the work is that this area is insufficiently researched and that a greater application of neural networks in this area would be of great importance for improving combustion, and thus would lead to significant fuel savings and reduction of environmental pollution.

neural networks, boilers with automatic firing, environmental protection

Конференцијски рад

eNergetics 2023

Neural Networks in Pellet Combustion Control-an Overview of the Group’s Research Work in 2022/2023

Popović, Stefan; Djukic, Dejan; Popović, Sonja Djukić; Gligorijević, Milan

/

The problems of pollution and global warming have plagued the planet for more than a century, and are the result of excessive consumption of fossil fuels. The last decades have brought innovations in the heating of smaller buildings, heating fuel oil and coal are being shut down, and boilers with automatic gas and biomass heating are being introduced. This significantly reduces pollution, but not enough. Hence the need for greater application of artificial intelligence and machine learning in combustion control in boilers with automatic firing. This paper presents a description of the experimental application of artificial intelligence, machine learning and neural networks to the ATI Terming Ozone 55 boiler and a brief summary of the results obtained.

boilers with automatic firing, neural networks, environmental protection

Конференцијски рад

Glasnik za društvene nauke (GDN)

A REFINEMENT OF THE FISHER'S EQUATION

Dejan Djukic

https://www.gdn.rs/index.php/GDN/article/download/100/62

Fisher's equation, or the equation of exchange, relates the money supply to the price levels, the monetary dynamics, and the economic activity. This equation, in its most cited form, shows imprecisions when it comes to the dimensional analysis of the quantities it relates. A need for clarifying the interpretation of these quantities and for facilitating the application of this equation has motivated this endeavour. In this work, first the Fisher's equation has been analysed dimensionally, and certain difficulties for its correct interpretation have been shown... With some well justified simplification, a refined form of the Fisher's equation has been produced. A facilitated application of the equation in its new form has been shown through a brief analysis of the phenomenon of monetary inflation, and the influence of the money supply on prices and overall economic activity.

quantity of money, Fisher's equation, monetary economics.

M53

AIIT 2024 - International conference on applied internet and information technologies

Artificial intelligence in electrical engineering

Djukic, Dejan; Popovic, Stefan

/

In this work, an application of Artificial intelligence (AI) to problems of electrical engineering has been presented. In particular, a method for deriving a symbolic equivalent resistance of an arbitrary number of resistors connected in series or in parallel has been designed. The supporting environment for performing symbolic computations is Prolog programming language... the principal parts of the created Prolog code, and the results of its execution on examples of resistor networks have been presented.

Artificial intelligence, logic programming, Prolog programming language, symbolic computation, electrical engineering, electrical circuits, resistor networks

Конференцијски рад

AIIT 2024 - International conference on applied internet and information technologies

Neural networks in pellet combustion control - research report for OZONE 55

Popovic, Stefan; Djukic, Dejan; Djukic Popovic, Sonja; Denic, Nebojsa; Viduka, Dejan

/

The rapid development of technologies and a faster way of life introduce artificial intelligence and machine learning into all aspects of life... This paper presents a description of the experimental application of artificial intelligence, machine learning and neural networks to the ATI Terming Ozone 55 boiler and a brief summary of the results obtained.

neural networks, machine learning, boilers, pellet

Конференцијски рад

Alfatech 2024 - International Scientific and Professional Conference “ALFATECH” Smart Cities and modern technologies

GENETIC ALGORITHMS AND MACHINE LEARNING AS THE BASIS OF ALL IMPLEMENTED SOLUTIONS IN SMART CITIES

Popovic, Stefan; Djukic Popovic, Sonja; Djukic, Dejan; Milan, Gligorijevic

/

The significance of the development of genetic algorithms and machine learning is inevitable today. All engineering solutions used in the construction of smart cities must contain an artificial intelligence component in their software part. The work deals with the needs of designers during the development of smart cities and the current opportunities offered by the market.

genetic algorithms, machine learning, artificial intelligence, smart cities, neural networks

Конференцијски рад

Alfatech 2024 - International Scientific and Professional Conference “ALFATECH” Smart Cities and modern technologies

Bilateral exponential as sigmoid in multilayered neuronal networks

Djukić, Dejan; Popović, Stefan

/

The significance of the development of genetic algorithms and machine learning is inevitable today. All engineering solutions used in the construction of smart cities must contain an artificial intelligence component in their software part. The work deals with the needs of designers during the development of smart cities and the current opportunities offered by the market.

genetic algorithms, machine learning, artificial intelligence, smart cities, neural networks

Конференцијски рад

PaKSoM 2024

Innovations in Risk Management - Integration of Neural Networks in Boilers with Automatic Firing

Popović, Stefan; Denić, Nebojša; Stojanović, Jelena; Djukic, Dejan; Popović, Đukić Sonja

/

Already at the beginning of the first quarter of the twenty-first century, we are witnessing the increasing application of artificial intelligence in all stages of life. The paper you are reading highlights the importance of implementing neural networks on boilers with automatic firing and is the result of a project that is entering its fifth year of experimental verification... Artificial intelligence systems applied to boiler systems can reduce the harmful effects of the systems themselves, but also prevent accidents that can threaten people's health and safety, as well as cause material damage.

neural networks, risk management, automatic boilers.

Конференцијски рад

Alfatech 2025 - International Scientific and Professional Conference “ALFATECH” Smart Cities and modern technologies

Global location coding (Universal Geographical Indicator System)

DJUKIC, Dejan; POPOVIC, Stefan; OCOKOLJIC, Snezana

/

In today's globalised society, where more and more of the goods and services are being routed automatically, there is a growing necessity to use a global location coding system... E.g. a twelve digit sequence indicates an area of about 50 m in diameter. Using such global coding system for geographic locations may substantially simplify the delivery of goods and services, direct and focus a remedial effort in emergencies, or be used advantageously for planning and improvement of city management.

location coding, geographic information system, smart city area numbers, smart city, mail delivery routing, goods and services delivery, land monitoring

Конференцијски рад

Alfatech 2025 - International Scientific and Professional Conference “ALFATECH” Smart Cities and modern technologies

Syntactic and morphological data-base and algorithms for NLP of the Serbian language

Tomic, Mirjana; Djukic, Dejan

/

In this work, a method for automated generating grammatically correct sentences in Serbian language has been presented... The applications of the method presented here are numerous: from educational use, e.g. in language training, to more general research tools in the domain of natural language processing (NLP), not only for the Serbian language, but for a wider family of languages following complex grammatical rules, such as highly inflected, and morphologically complex languages.

Natural language processing, NLP, automated natural language generation, NLG, Serbian language, data-base design, language and text synthesis, education, programming methodology

Конференцијски рад

Journal of Soft Computing and Decision Analytics (vol. 3, br. 1)

Risk Management Innovations through Neural Network Integration in Automated Boiler Combustion Systems

Popovic, Stefan; Djukic Popovic, Sonja; Denic, Nebojsa; Djukic, Dejan; Stojanovic, Jelena

/

In the early decades of the twenty-first century, the application of artificial intelligence has been expanding across all sectors of society, including industrial energy systems... The application of AI-based solutions in boiler control not only contributes to the reduction of environmental impact but also enhances operational safety by preventing accidents that may endanger human health and cause material losses.

Neural networks, Risk management, Automatic boilers, Combustion optimization.

/

Electronics, Volume 14, Issue 3

Optimization of Artificial Intelligence Algorithm Selection: PIPRECIA-S Model and Multi-Criteria Analysis

Поповић, Стефан; Dejan Viduka; Basic, Ana; Dimić, Violeta; Djukic, Dejan; Nikolic, Vojkan R; Stokic, Aleksandar

/

In the age of digitization and the ever-present use of artificial intelligence (AI), it is essential to develop methodologies that enable the systematic evaluation and ranking of different AI algorithms... This approach not only advances the understanding of AI algorithms but also contributes to the development of strategies for their implementation in various industries.

PIPRECIA-S model; artificial intelligence; multi-criteria analysis; algorithm ranking; strategic planning

M22

PaKSoM 2025

Multi-dimensional Hamming Coding for Data Safety

Djukic, Dejan

/

As physical devices serving for data storage age, the stored data suffer gradual degradation, which is a process colloquially called the bit-rot... For this, trials have been made with data arranged in three dimensions, encoded by three-dimensional Hamming code, and the results issuing from the trials have been presented and discussed.

error correction code, Hamming code, data safety, bit-rot, data quality, information coding

Конференцијски рад