Jerzy Tchórzewski
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jerzy Tchórzewski has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Dariusz Ruciński
University of Siedlce Faculty of Exact and Natural Sciences Institute of Computer Science ul. 3 Maja 54, 08-110 Siedlce, Poland
3 shared publications - Radosław Marlęga
Instytut Techniki Górniczej KOMAG, Instytut Badawczy
3 shared publications - Wojciech Nabiałek
University of Siedlce
3 shared publications Adam Szaniawski
GENBIT - Student Branch of Computer Science, Department of Computer Science, Faculty of Sciences, Siedlce University of Natural Sciences and Humanities, Siedlce, Poland
1 shared publicationArkadiusz Ozioro
GENBIT Student Branch of Computer Science, Faculty of Science Siedlce, University of Natural Sciences and Humanities, Siedlce, Poland
1 shared publicationDariusz Rucilski
Faculty of Sciences, Siedlce University of Natural Sciences and Humanities, Computer Science Institute, Siedlce, Poland
1 shared publication
Latest Publications
- Open Access
- 29 April 2026
- Published by MDPI AG in Electronics
- Vol. 15 (9) , 1880
Study of the National Power System in the Context of Intelligent Systems Under Conditions of Increasing Renewable Energy Production and Electricity Savings
In power engineering, various mathematical models are used, for example, to study stability, forecasting, etc., obtained using analytical methods, machine learning, and artificial intelligence. The present authors pursue a novel direction in modeling the development of the power system as an intelligent control system using data from 1990–2024 under conditions including a growing level of renewable energy production and an increased level of electrical energy saving. As a result of the modeling carried out in the MATLAB and Simulink environment, two types of highly accurate development models were obtained: a regression machine learning ARX model and a multilayer perceptron (MLP) neural network. For the neural model, MAPE errors ranged from 0.73% to 3.37%, and the coefficient of determination R2 ranged from 0.9478 to 0.9868. The accuracy of the ARX models was close to 100%. Using an ARX model converted into a state-space (SS) model, it was observed that the subsystems of conventional electricity production and renewable energy were observable and controllable. The presented methodology is modern, enabling the study of large development systems using development models in terms of control and systems theory and artificial intelligence methods.
- 29 April 2026
- Published by MDPI AG in Electronics
- Vol. 15 (9) , 1880
Open AccessStudy of the National Power System in the Context of Intelligent Systems Under Conditions of Increasing Renewable Energy Production and Electricity Savings
In power engineering, various mathematical models are used, for example, to study stability, forecasting, etc., obtained using analytical methods, machine learning, and artificial intelligence. The present authors pursue a novel direction in modeling the development of the power system as an intelligent control system using data from 1990–2024 under conditions including a growing level of renewable energy production and an increased level of electrical energy saving. As a result of the modeling carried out in the MATLAB and Simulink environment, two types of highly accurate development models were obtained: a regression machine learning ARX model and a multilayer perceptron (MLP) neural network. For the neural model, MAPE errors ranged from 0.73% to 3.37%, and the coefficient of determination R2 ranged from 0.9478 to 0.9868. The accuracy of the ARX models was close to 100%. Using an ARX model converted into a state-space (SS) model, it was observed that the subsystems of conventional electricity production and renewable energy were observable and controllable. The presented methodology is modern, enabling the study of large development systems using development models in terms of control and systems theory and artificial intelligence methods.
- Open Access
- 8 November 2025
- Published by Siedlce University of Natural Sciences and Humanities in Studia Informatica. System and information technology
- Vol. 32 (1) , 77-91
Modeling the National Power System Using Artificial Neural Networks
The purpose of this paper is to investigate and demonstrate the potential of modeling the National Power System (NPS) in Poland. The paper presents the results of research modeling of the NPS system using three different models based on Artificial Neural Networks. Data characterizing the NPS were implemented to build the models. The results measured by Mean Squared Error and determination coefficient were presented and analyzed. The research results and conclusions are presented in the summary.
- 8 November 2025
- Published by Siedlce University of Natural Sciences and Humanities in Studia Informatica. System and information technology
- Vol. 32 (1) , 77-91
Open AccessModeling the National Power System Using Artificial Neural Networks
The purpose of this paper is to investigate and demonstrate the potential of modeling the National Power System (NPS) in Poland. The paper presents the results of research modeling of the NPS system using three different models based on Artificial Neural Networks. Data characterizing the NPS were implemented to build the models. The results measured by Mean Squared Error and determination coefficient were presented and analyzed. The research results and conclusions are presented in the summary.
- Open Access
- 8 November 2025
- Published by Siedlce University of Natural Sciences and Humanities in Studia Informatica. System and information technology
- Vol. 32 (1) , 47-60
Functioning of an Intelligent System on the Example of the National Power Demand System
This publication includes a concept and research results regarding the search for regularity in the functioning of an intelligent system using the example of a system for forecasting national power demand. The research employs the ARX regression machine learning method to derive models of the functioning of the electricity forecasting system. The study uses actual values of electricity generated by both uniform and non-uniform domestic electricity systems as input quantities, and forecasted national power demand as the output values from January 2023. The main aim of the research was to obtain several hourly models and several monthly models to demonstrate changes in selected system parameters and to show whether, and what changes occur in the direction of increasing the system’s independence, enhancing the system control level, etc. The research methodology also employs, in addition to the machine learning method, the method of control theory and systems. At the same time, an example of obtaining a model of the national system demand for electric power using the ARX machine learning method, which was transformed into state space model, whose matrix elements were used to interpret the correctness of changes in the intelligent system.
- 8 November 2025
- Published by Siedlce University of Natural Sciences and Humanities in Studia Informatica. System and information technology
- Vol. 32 (1) , 47-60
Open AccessFunctioning of an Intelligent System on the Example of the National Power Demand System
This publication includes a concept and research results regarding the search for regularity in the functioning of an intelligent system using the example of a system for forecasting national power demand. The research employs the ARX regression machine learning method to derive models of the functioning of the electricity forecasting system. The study uses actual values of electricity generated by both uniform and non-uniform domestic electricity systems as input quantities, and forecasted national power demand as the output values from January 2023. The main aim of the research was to obtain several hourly models and several monthly models to demonstrate changes in selected system parameters and to show whether, and what changes occur in the direction of increasing the system’s independence, enhancing the system control level, etc. The research methodology also employs, in addition to the machine learning method, the method of control theory and systems. At the same time, an example of obtaining a model of the national system demand for electric power using the ARX machine learning method, which was transformed into state space model, whose matrix elements were used to interpret the correctness of changes in the intelligent system.
- Open Access
- 8 November 2025
- Published by Siedlce University of Natural Sciences and Humanities in Studia Informatica. System and information technology
- Vol. 32 (1) , 93-111
Searching form the Model of Human Facial Expressions and its Implementation inMATLAB and Simulink Environments
The publication contains selected research results on the creation of a neural model of human facial expressions along with its implementation in the MATLAB and Simulink environments using the library called Deep Learning Toolbox. The model was generated as an object to recognize selected human faces and emotional states based on visual data recorded on the human face in real time. The study was placed against the background of available literature on the analysis of facial expressions and emotion classification methods. In addition to the concept of the original solution, the assumptions of the research experiment were given, a method for measuring facial expressions was selected for the experimental conditions, and a set of data was developed for training a neural model of the facial expression system with their preparation for ANN learning. Ultimately, various artificial neural networks were trained to model the facial expression system and sensitivity and comparative tests were performed in Simulink to, among others: assess the quality of the model in relation to real data. Very high results of ANN training of the facial expression system model were obtained (MSE on the order of 10−14, R close to 1), as well as relatively high model quality relative the facial expression system, measured, among others, average relative error, the value of which was several percent. However, in terms of prediction effectiveness, because of the obtained results, which are not very high for the assumed high measurement accuracies, the research that has been started is continued.
- 8 November 2025
- Published by Siedlce University of Natural Sciences and Humanities in Studia Informatica. System and information technology
- Vol. 32 (1) , 93-111
Open AccessSearching form the Model of Human Facial Expressions and its Implementation inMATLAB and Simulink Environments
The publication contains selected research results on the creation of a neural model of human facial expressions along with its implementation in the MATLAB and Simulink environments using the library called Deep Learning Toolbox. The model was generated as an object to recognize selected human faces and emotional states based on visual data recorded on the human face in real time. The study was placed against the background of available literature on the analysis of facial expressions and emotion classification methods. In addition to the concept of the original solution, the assumptions of the research experiment were given, a method for measuring facial expressions was selected for the experimental conditions, and a set of data was developed for training a neural model of the facial expression system with their preparation for ANN learning. Ultimately, various artificial neural networks were trained to model the facial expression system and sensitivity and comparative tests were performed in Simulink to, among others: assess the quality of the model in relation to real data. Very high results of ANN training of the facial expression system model were obtained (MSE on the order of 10−14, R close to 1), as well as relatively high model quality relative the facial expression system, measured, among others, average relative error, the value of which was several percent. However, in terms of prediction effectiveness, because of the obtained results, which are not very high for the assumed high measurement accuracies, the research that has been started is continued.
- 23 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Regression Machine Learning of an Hourly Model of National Electric Power Demand System
The article shows that it is possible to use the regression machine learning method arx to obtain a parametric ARX model of the National Electric Power Demand System with high quality and accuracy, and on this basis also to obtain models of SS state variables, which required, among others: designing a method of using available data, performing machine learning on selected examples, transforming models from ARX models to SS state variable models, evaluating the obtained models using simulation models, attempting to interpret the obtained research results, etc. The research was carried out in the MATLAB and Simulink environment using real values related to the production and consumption of electricity of the National Power System.
- 23 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Regression Machine Learning of an Hourly Model of National Electric Power Demand System
The article shows that it is possible to use the regression machine learning method arx to obtain a parametric ARX model of the National Electric Power Demand System with high quality and accuracy, and on this basis also to obtain models of SS state variables, which required, among others: designing a method of using available data, performing machine learning on selected examples, transforming models from ARX models to SS state variable models, evaluating the obtained models using simulation models, attempting to interpret the obtained research results, etc. The research was carried out in the MATLAB and Simulink environment using real values related to the production and consumption of electricity of the National Power System.
- Open Access
- 31 March 2025
- Published by Siedlce University of Natural Sciences and Humanities in Studia Informatica. System and information technology
- Vol. 31 (2) , 87-102
Analysis of the Possibilities of the Evolutionary Algorithm to Improve the Neural Model of the TGE S.A. Day Ahead Market System Using Selected Programming Environments
The article contains selected research results regarding the analysis of the possibility of using the Evolutionary Algorithm to improve neural models of intelligent systems using selected programming environments. Choosing an appropriate programming language is one of the basic activities in the process of implementing complex algorithms, which include methods of artificial neural networks and evolutionary algorithms. Due to the fact that the object of the researchwas an intelligent Day Ahead Market system operating on the Polish Power Exchange and the modeling methods were artificial neural networks and evolutionary algorithms, it was decided to use very high-level programming languages such as Python, Matlab and C# for implementation and associated development environments. It turned out, among other things, that each of these languages and programming environments has its advantages and disadvantages, but all of them are very useful due to their useful syntax and rich included libraries. A thorough analysis of the implementation shows, among other things, that the choice of programming language affects the efficiency, speed and quality of the obtained implementations of system models. Against this background, the advantages and disadvantages of individual programming languages are shown, especially in the context of implementing evolutionary algorithms. The research results indicate directions for selecting an appropriate programming language and the associated programming environment for system modeling using artificial neural networks and evolutionary algorithms. In addition, the method of analysis, as well as the method of modeling and implementation was shown on the example of a specific system, which was the Day Ahead Market system of TGES.A.
- 31 March 2025
- Published by Siedlce University of Natural Sciences and Humanities in Studia Informatica. System and information technology
- Vol. 31 (2) , 87-102
Open AccessAnalysis of the Possibilities of the Evolutionary Algorithm to Improve the Neural Model of the TGE S.A. Day Ahead Market System Using Selected Programming Environments
The article contains selected research results regarding the analysis of the possibility of using the Evolutionary Algorithm to improve neural models of intelligent systems using selected programming environments. Choosing an appropriate programming language is one of the basic activities in the process of implementing complex algorithms, which include methods of artificial neural networks and evolutionary algorithms. Due to the fact that the object of the researchwas an intelligent Day Ahead Market system operating on the Polish Power Exchange and the modeling methods were artificial neural networks and evolutionary algorithms, it was decided to use very high-level programming languages such as Python, Matlab and C# for implementation and associated development environments. It turned out, among other things, that each of these languages and programming environments has its advantages and disadvantages, but all of them are very useful due to their useful syntax and rich included libraries. A thorough analysis of the implementation shows, among other things, that the choice of programming language affects the efficiency, speed and quality of the obtained implementations of system models. Against this background, the advantages and disadvantages of individual programming languages are shown, especially in the context of implementing evolutionary algorithms. The research results indicate directions for selecting an appropriate programming language and the associated programming environment for system modeling using artificial neural networks and evolutionary algorithms. In addition, the method of analysis, as well as the method of modeling and implementation was shown on the example of a specific system, which was the Day Ahead Market system of TGES.A.
- Open Access
- 31 March 2025
- Published by Siedlce University of Natural Sciences and Humanities in Studia Informatica. System and information technology
- Vol. 31 (2) , 15-33
Quantum Inspired Evolutionary Algorithm based on Day Ahead Market of the Polish Electricity Power Exchange
The paper discusses the essence of the method and selected results of the quantum-inspired implementation of the so-called System Evolutionary Algorithm on the example of the neural model of the Day-Ahead Market of the Polish Electricity Exchange Market S.A. First, the appropriate Perceptron Artificial Neural Network was designed and implemented in the MATLAB and Simulink environment, in which the Day-Ahead Market model was taught. Then it was assumed that the obtained parameters of the neural model, i.e. weights and biases, are quantum-encoded numbers, the values of whichwere corrected by the quantum-inspired Evolutionary Algorithm. Finally, a hybrid model was obtained in the form of an Artificial Neural Network with weights and biases corrected by a quantum inspired Evolutionary Algorithm. As a result of the conducted research, the relative error improvement was obtained from the level for different hours of the day from -0.11% ÷ 0.12% to the level from 0.04% ÷ 0.05%, i.e. by an order of magnitude. Moreover, the improvement of the quantum-inspired evolutionary algorithm measured by the fitness metric formulated as MSE error was achieved from a value of 0.990366 to a value of 0.990375.
- 31 March 2025
- Published by Siedlce University of Natural Sciences and Humanities in Studia Informatica. System and information technology
- Vol. 31 (2) , 15-33
Open AccessQuantum Inspired Evolutionary Algorithm based on Day Ahead Market of the Polish Electricity Power Exchange
The paper discusses the essence of the method and selected results of the quantum-inspired implementation of the so-called System Evolutionary Algorithm on the example of the neural model of the Day-Ahead Market of the Polish Electricity Exchange Market S.A. First, the appropriate Perceptron Artificial Neural Network was designed and implemented in the MATLAB and Simulink environment, in which the Day-Ahead Market model was taught. Then it was assumed that the obtained parameters of the neural model, i.e. weights and biases, are quantum-encoded numbers, the values of whichwere corrected by the quantum-inspired Evolutionary Algorithm. Finally, a hybrid model was obtained in the form of an Artificial Neural Network with weights and biases corrected by a quantum inspired Evolutionary Algorithm. As a result of the conducted research, the relative error improvement was obtained from the level for different hours of the day from -0.11% ÷ 0.12% to the level from 0.04% ÷ 0.05%, i.e. by an order of magnitude. Moreover, the improvement of the quantum-inspired evolutionary algorithm measured by the fitness metric formulated as MSE error was achieved from a value of 0.990366 to a value of 0.990375.