Journal of Informatics and Control Problems https://icp.az/ en Journal of Informatics and Control Problems DataLife Engine Experimental analysis of an innovative approximate solution method for an integer programming problem https://icp.az/index.php?newsid=411 https://icp.az/index.php?newsid=411 Rayiha Niyazova
Experimental analysis of an innovative approximate solution method for an integer programming problem

The article presents an experimental analysis of an innovative approximate solution method for the integer programming problem, of which the author is a co-author. This method was published in a Web of Science-indexed journal. In that work, a theoretical investigation of the method was provided, and for clarity, the method was explained using a numerical example. However, no experiments were conducted there to determine the effectiveness of the method. Naturally, a more comprehensive conclusion regarding the effectiveness and quality of the method can be drawn after extensive experiments conducted on problems of various dimensions with random coefficients. Therefore, in this work, numerous problems of different dimensions and with random coefficients are solved by applying said method, and conclusions regarding the quality of the method are drawn.

Keywords: Integer programming problem, Innovative approximate solution, Experimental analysis

DOI: https://doi.org/10.54381/icp.2026.1.08]]> Rayiha Niyazova
Experimental analysis of an innovative approximate solution method for an integer programming problem

The article presents an experimental analysis of an innovative approximate solution method for the integer programming problem, of which the author is a co-author. This method was published in a Web of Science-indexed journal. In that work, a theoretical investigation of the method was provided, and for clarity, the method was explained using a numerical example. However, no experiments were conducted there to determine the effectiveness of the method. Naturally, a more comprehensive conclusion regarding the effectiveness and quality of the method can be drawn after extensive experiments conducted on problems of various dimensions with random coefficients. Therefore, in this work, numerous problems of different dimensions and with random coefficients are solved by applying said method, and conclusions regarding the quality of the method are drawn.

Keywords: Integer programming problem, Innovative approximate solution, Experimental analysis

DOI: https://doi.org/10.54381/icp.2026.1.08 ]]> Admin Wed, 01 Apr 2026 17:26:47 +0400 Pichilti – monolingual Azerbaijani distilled Whisper model https://icp.az/index.php?newsid=410 https://icp.az/index.php?newsid=410 Mirakram Aghalarov, Mahammad Mehdi, Javidan Zeynalov, Sabuhi Aghayev
Pichilti – monolingual Azerbaijani distilled Whisper model

The recent saturation in the development of Speech-to-Text (STT) models has been disrupted by the release of multilingual models trained using zero-shot learning. While these models offer powerful and robust capabilities for voice processing in noisy environments, their multilingual nature leads to increased GPU utilization. Moreover, smaller models exhibit poor performance on low-resource languages such as Azerbaijani. This paper introduces a methodology and a large-scale voice dataset designed for training STT models in Azerbaijani. Over 500 hours of speech data have been collected, and knowledge distillation techniques have been applied at various levels. As a result, the distilled Whisper variant (Pichilti-base) outperforms Whisper-large v3 in Azerbaijani for voice recognition tasks. Additionally, specific post-processing methods have been implemented to mitigate hallucination effects in silent recordings.

Keywords: Knowledge Distillation, Speech to Text, Voice Processing, Low Resource Languages

DOI: https://doi.org/10.54381/icp.2026.1.07]]> Mirakram Aghalarov, Mahammad Mehdi, Javidan Zeynalov, Sabuhi Aghayev
Pichilti – monolingual Azerbaijani distilled Whisper model

The recent saturation in the development of Speech-to-Text (STT) models has been disrupted by the release of multilingual models trained using zero-shot learning. While these models offer powerful and robust capabilities for voice processing in noisy environments, their multilingual nature leads to increased GPU utilization. Moreover, smaller models exhibit poor performance on low-resource languages such as Azerbaijani. This paper introduces a methodology and a large-scale voice dataset designed for training STT models in Azerbaijani. Over 500 hours of speech data have been collected, and knowledge distillation techniques have been applied at various levels. As a result, the distilled Whisper variant (Pichilti-base) outperforms Whisper-large v3 in Azerbaijani for voice recognition tasks. Additionally, specific post-processing methods have been implemented to mitigate hallucination effects in silent recordings.

Keywords: Knowledge Distillation, Speech to Text, Voice Processing, Low Resource Languages

DOI: https://doi.org/10.54381/icp.2026.1.07 ]]> Admin Wed, 01 Apr 2026 17:26:41 +0400 Qualitative analysis of two destroying each other reproducing populations dynamics https://icp.az/index.php?newsid=409 https://icp.az/index.php?newsid=409 Volodymyr G. Skobelev, Volodymyr V. Skobelev
Qualitative analysis of two destroying each other reproducing populations dynamics

In this paper, a parametric linear continuous-time model that describes the dynamics of a conflict between two populations is constructed. It is assumed that individuals of each population destroy individuals of the other population at given rates, and individuals of each population can be reproduced at given rates with new individuals immediately entering into conflict. The paper contains a qualitative (i.e., mathematical) analysis of the proposed model. The relevance of this problem is due to the fact that, in essence, the entire class of similar problems is considered from a single point of view. Besides, the obtained results outline some strong base for developing algorithms (and, consequently, software) for automatic analysis of systems in this class.

Keywords: System Dynamics, Linear continuous-time models, Lanchester models, Ordinary differential equations, Qualitative analysis

DOI: https://doi.org/10.54381/icp.2026.1.06]]> Volodymyr G. Skobelev, Volodymyr V. Skobelev
Qualitative analysis of two destroying each other reproducing populations dynamics

In this paper, a parametric linear continuous-time model that describes the dynamics of a conflict between two populations is constructed. It is assumed that individuals of each population destroy individuals of the other population at given rates, and individuals of each population can be reproduced at given rates with new individuals immediately entering into conflict. The paper contains a qualitative (i.e., mathematical) analysis of the proposed model. The relevance of this problem is due to the fact that, in essence, the entire class of similar problems is considered from a single point of view. Besides, the obtained results outline some strong base for developing algorithms (and, consequently, software) for automatic analysis of systems in this class.

Keywords: System Dynamics, Linear continuous-time models, Lanchester models, Ordinary differential equations, Qualitative analysis

DOI: https://doi.org/10.54381/icp.2026.1.06 ]]> Admin Wed, 01 Apr 2026 17:26:33 +0400 Generalized synergistic edge-guided graph reasoning network for biomedical image segmentation https://icp.az/index.php?newsid=408 https://icp.az/index.php?newsid=408 Di Zhao, Yi Tang, Dmitry Pertsau, Alevtina Gourinovitch
Generalized synergistic edge-guided graph reasoning network for biomedical image segmentation

Biomedical image segmentation plays a vital role in computer-aided diagnosis and treatment planning. However, existing methods often struggle with modeling complex anatomical structures and capturing long-range dependencies. To address these limitations, we propose a generalized Synergistic Edge-Guided Graph Reasoning Network (SEGRNet) that integrates convolutional feature extraction with graph-based global reasoning. The model projects pixel-level region and edge features into a graph domain, enabling adaptive interaction between local and global features via a graph convolutional network. After reasoning, enhanced features are mapped back for refined segmentation. Experiments conducted on three public datasets including BUSI, LGG and CHAOS outperforms state-of-the-art models in terms of dice coefficient, mean intersection over union and structural similarity. These results confirm the effectiveness and generalization ability of the proposed method across various medical imaging scenarios, making it suitable for future clinical applications.

Keywords: Medical image segmentation, Graph reasoning, Graph convolutional network, MRI, CT

DOI: https://doi.org/10.54381/icp.2026.1.05]]> Di Zhao, Yi Tang, Dmitry Pertsau, Alevtina Gourinovitch
Generalized synergistic edge-guided graph reasoning network for biomedical image segmentation

Biomedical image segmentation plays a vital role in computer-aided diagnosis and treatment planning. However, existing methods often struggle with modeling complex anatomical structures and capturing long-range dependencies. To address these limitations, we propose a generalized Synergistic Edge-Guided Graph Reasoning Network (SEGRNet) that integrates convolutional feature extraction with graph-based global reasoning. The model projects pixel-level region and edge features into a graph domain, enabling adaptive interaction between local and global features via a graph convolutional network. After reasoning, enhanced features are mapped back for refined segmentation. Experiments conducted on three public datasets including BUSI, LGG and CHAOS outperforms state-of-the-art models in terms of dice coefficient, mean intersection over union and structural similarity. These results confirm the effectiveness and generalization ability of the proposed method across various medical imaging scenarios, making it suitable for future clinical applications.

Keywords: Medical image segmentation, Graph reasoning, Graph convolutional network, MRI, CT

DOI: https://doi.org/10.54381/icp.2026.1.05 ]]> Admin Wed, 01 Apr 2026 17:26:25 +0400 Operating algorithms for the intelligent control controller of a sucker rod pumping unit https://icp.az/index.php?newsid=407 https://icp.az/index.php?newsid=407 Mahammad Rezvan
Operating algorithms for the intelligent control controller of a sucker rod pumping unit

The article examines the operating algorithms of modernized intelligent monitoring and control well controllers (IWC) located at oil wells operated by SRPU, using the capabilities of modern information technology science and new microprocessors. A general block diagram of the modernized IWC is provided, and the MODBUS protocol used during information exchange between the IWC and external devices is formed according to the purpose of each request. The algorithms for the initial parameter determination service of the given block diagram, the units checking for the presence of a request from external devices to the controller, checking the request validity, and the request service blocks are provided, and the operating mechanism of these algorithms is explained extensively.

Keywords: Well controller, Analog-to-Digital Converter, MODBUS protocol, Microprocessor, Cyclic Redundancy Check, Dynamometer chart, Radio communication

DOI: https://doi.org/10.54381/icp.2026.1.04]]> Mahammad Rezvan
Operating algorithms for the intelligent control controller of a sucker rod pumping unit

The article examines the operating algorithms of modernized intelligent monitoring and control well controllers (IWC) located at oil wells operated by SRPU, using the capabilities of modern information technology science and new microprocessors. A general block diagram of the modernized IWC is provided, and the MODBUS protocol used during information exchange between the IWC and external devices is formed according to the purpose of each request. The algorithms for the initial parameter determination service of the given block diagram, the units checking for the presence of a request from external devices to the controller, checking the request validity, and the request service blocks are provided, and the operating mechanism of these algorithms is explained extensively.

Keywords: Well controller, Analog-to-Digital Converter, MODBUS protocol, Microprocessor, Cyclic Redundancy Check, Dynamometer chart, Radio communication

DOI: https://doi.org/10.54381/icp.2026.1.04 ]]> Admin Wed, 01 Apr 2026 17:26:16 +0400 Theoretical foundations for measuring and determining the flow rate of water delivered from reservoirs and canals to users https://icp.az/index.php?newsid=406 https://icp.az/index.php?newsid=406 Asif Rzayev, Maryam Mammadli
Theoretical foundations for measuring and determining the flow rate of water delivered from reservoirs and canals to users

An analysis of the structures of water conduits for reservoirs and irrigation canals is conducted. Existing methods for measuring and determining the flow rate during water release from such structures are analyzed, and ways to implement these methods based on modern information-measurement and telecommunication technologies are investigated. In accordance with the goals and priority directions of the National Water Strategy of the Republic of Azerbaijan, the theoretical foundations for creating operational flow rate control systems in reservoirs and irrigation canals are developed on the basis of modern measurement and information-communication technologies. A structural diagram and components of a remote flow rate control and management system for distributed water supply networks supplied by reservoirs are proposed. Hydraulic processes in the water conduit structures of reservoirs and canals are analyzed, including variants of liquid discharge from thin-walled orifices into the atmosphere and under the water level, as well as local resistances causing additional pressure losses in the reservoir outlet tunnels. For more accurate calculation of the flow rate, it is proposed to determine the total resistance coefficient of the system by identifying practical losses for each specific case.

Keywords: Reservoirs, Water conduits, Irrigation canals, Water flow rate, Measurement, Local resistances, Remote control

DOI: https://doi.org/10.54381/icp.2026.1.03]]> Asif Rzayev, Maryam Mammadli
Theoretical foundations for measuring and determining the flow rate of water delivered from reservoirs and canals to users

An analysis of the structures of water conduits for reservoirs and irrigation canals is conducted. Existing methods for measuring and determining the flow rate during water release from such structures are analyzed, and ways to implement these methods based on modern information-measurement and telecommunication technologies are investigated. In accordance with the goals and priority directions of the National Water Strategy of the Republic of Azerbaijan, the theoretical foundations for creating operational flow rate control systems in reservoirs and irrigation canals are developed on the basis of modern measurement and information-communication technologies. A structural diagram and components of a remote flow rate control and management system for distributed water supply networks supplied by reservoirs are proposed. Hydraulic processes in the water conduit structures of reservoirs and canals are analyzed, including variants of liquid discharge from thin-walled orifices into the atmosphere and under the water level, as well as local resistances causing additional pressure losses in the reservoir outlet tunnels. For more accurate calculation of the flow rate, it is proposed to determine the total resistance coefficient of the system by identifying practical losses for each specific case.

Keywords: Reservoirs, Water conduits, Irrigation canals, Water flow rate, Measurement, Local resistances, Remote control

DOI: https://doi.org/10.54381/icp.2026.1.03 ]]> Admin Wed, 01 Apr 2026 17:26:08 +0400 The application of machine learning methods for risk analysis of investment projects https://icp.az/index.php?newsid=405 https://icp.az/index.php?newsid=405 Dilan Özcan Yaylalı, İman Askerzade
The application of machine learning methods for risk analysis of investment projects

The evaluation of investment projects is the centerpiece of all investment activities. Given the substantial financial losses that can result from various risk variables and uncertainty, risk analysis of investment projects is particularly important. Most frequently, investment appraisals employ cost-benefit metrics to guide investment decisions. Aiming at the risk analysis of the investment projects, we examined an application and compared several machine learning methods including deep learning techniques, to build a risk assessment model for investment projects and analyze investment risks scientifically and effectively. The suggested deep learning approach, which combines long short-term memory and convolutional networks, yielded the best performance. The study proves that using machine learning techniques for the risk analysis of investment projects enables businesses to detect and manage investment risks.

Keywords: Machine learning, Risk analysis, Investment projects

DOI: https://doi.org/10.54381/icp.2026.1.02]]> Dilan Özcan Yaylalı, İman Askerzade
The application of machine learning methods for risk analysis of investment projects

The evaluation of investment projects is the centerpiece of all investment activities. Given the substantial financial losses that can result from various risk variables and uncertainty, risk analysis of investment projects is particularly important. Most frequently, investment appraisals employ cost-benefit metrics to guide investment decisions. Aiming at the risk analysis of the investment projects, we examined an application and compared several machine learning methods including deep learning techniques, to build a risk assessment model for investment projects and analyze investment risks scientifically and effectively. The suggested deep learning approach, which combines long short-term memory and convolutional networks, yielded the best performance. The study proves that using machine learning techniques for the risk analysis of investment projects enables businesses to detect and manage investment risks.

Keywords: Machine learning, Risk analysis, Investment projects

DOI: https://doi.org/10.54381/icp.2026.1.02 ]]> Admin Wed, 01 Apr 2026 17:25:59 +0400 Conceptual framework of an intelligent feed grain warehouse in Industries 4.0 and 5.0 https://icp.az/index.php?newsid=404 https://icp.az/index.php?newsid=404 Velizara Pencheva, Asen Asenov
Conceptual framework of an intelligent feed grain warehouse in Industries 4.0 and 5.0

The research aims to describe the conceptual framework of intelligent feed grain warehouses in livestock breeding, which are closely related to the development of Industries 4.0 and 5.0. The main components of a smart warehouse are reviewed: cyber physical system (CPS); cloud and peripheral computing services; Internet of Things (IoT); automated management platforms; warehouse management systems (WMS); and collaborative robots (“cobots”) and drones, Through an expert evaluation using Delphi (Delphi) with the application of factor analysis, statistical processing and correction after each cycle of processing the results, the barriers faced by companies in the construction of intelligent feed grain warehouses in animal husbandry were assessed.

Keywords: Smart warehouse, Barrier, Industry 4.0, Industry 5.0, Delphi method

DOI: https://doi.org/10.54381/icp.2026.1.01]]> Velizara Pencheva, Asen Asenov
Conceptual framework of an intelligent feed grain warehouse in Industries 4.0 and 5.0

The research aims to describe the conceptual framework of intelligent feed grain warehouses in livestock breeding, which are closely related to the development of Industries 4.0 and 5.0. The main components of a smart warehouse are reviewed: cyber physical system (CPS); cloud and peripheral computing services; Internet of Things (IoT); automated management platforms; warehouse management systems (WMS); and collaborative robots (“cobots”) and drones, Through an expert evaluation using Delphi (Delphi) with the application of factor analysis, statistical processing and correction after each cycle of processing the results, the barriers faced by companies in the construction of intelligent feed grain warehouses in animal husbandry were assessed.

Keywords: Smart warehouse, Barrier, Industry 4.0, Industry 5.0, Delphi method

DOI: https://doi.org/10.54381/icp.2026.1.01 ]]> Admin Wed, 01 Apr 2026 17:25:51 +0400 2026 VOLUME 46 - No. 1 https://icp.az/index.php?newsid=60 https://icp.az/index.php?newsid=60 2026 VOLUME 46 - No. 1

CONTENTS:

INFORMATION TECHNOLOGY AND SYSTEMS
Velizara Pencheva, Asen Asenov. Conceptual framework of an intelligent feed grain warehouse in Industries 4.0 and 5.0
Dilan Özcan Yaylalı, İman Askerzade. The application of machine learning methods for risk analysis of investment projects
Asif Rzayev, Maryam Mammadli. Theoretical foundations for measuring and determining the flow rate of water delivered from reservoirs and canals to users
Mahammad Rezvan. Operating algorithms for the intelligent control controller of a sucker rod pumping unit
MODELING AND IDENTIFICATION
Di Zhao, Yi Tang, Dmitry Pertsau, Alevtina Gourinovitch. Generalized synergistic edge-guided graph reasoning network for biomedical image segmentation
Volodymyr G. Skobelev, Volodymyr V. Skobelev. Qualitative analysis of two destroying each other reproducing populations dynamics
Mirakram Aghalarov, Mahammad Mehdi, Javidan Zeynalov, Sabuhi Aghayev. Pichilti – monolingual Azerbaijani distilled Whisper model
THEORY OF CONTROL
Rayiha Niyazova. Experimental analysis of an innovative approximate solution method for an integer programming problem
]]> 2026 VOLUME 46 - No. 1

CONTENTS:

INFORMATION TECHNOLOGY AND SYSTEMS
Velizara Pencheva, Asen Asenov. Conceptual framework of an intelligent feed grain warehouse in Industries 4.0 and 5.0
Dilan Özcan Yaylalı, İman Askerzade. The application of machine learning methods for risk analysis of investment projects
Asif Rzayev, Maryam Mammadli. Theoretical foundations for measuring and determining the flow rate of water delivered from reservoirs and canals to users
Mahammad Rezvan. Operating algorithms for the intelligent control controller of a sucker rod pumping unit
MODELING AND IDENTIFICATION
Di Zhao, Yi Tang, Dmitry Pertsau, Alevtina Gourinovitch. Generalized synergistic edge-guided graph reasoning network for biomedical image segmentation
Volodymyr G. Skobelev, Volodymyr V. Skobelev. Qualitative analysis of two destroying each other reproducing populations dynamics
Mirakram Aghalarov, Mahammad Mehdi, Javidan Zeynalov, Sabuhi Aghayev. Pichilti – monolingual Azerbaijani distilled Whisper model
THEORY OF CONTROL
Rayiha Niyazova. Experimental analysis of an innovative approximate solution method for an integer programming problem
]]> Bosh Wed, 01 Apr 2026 17:16:52 +0400 Environmental safety control in water reservoirs https://icp.az/index.php?newsid=403 https://icp.az/index.php?newsid=403 Sayyara Gidayatzada
Environmental safety control in water reservoirs

The ecological safety of drinking water in the Jeyranbatan Water Reservoir is shaped by the interaction of natural processes, anthropogenic impacts, and temporal variations in environmental conditions. Ensuring the stability of quality indicators requires continuous monitoring of key parameters, systematic data processing, and scientifically grounded management decisions based on regulatory requirements. The article integrates real-time water quality measurements with an extensive normative database covering national and international standards. Taking the time factor into account, periodic fluctuations, long-term trends, and irregular deviations caused by external influences are distinguished within the indicators. The obtained results provide a basis for the early identification of undesirable changes in water quality and support corrective measures aimed at reducing ecological risks. Comparison with normative values enables assessment of the current state and more accurate forecasting of potential hazards. As a result, aligning reliable measurement data with standardized criteria increases the reliability of management decisions, reduces uncertainty, and strengthens the overall level of ecological safety. The proposed approach can serve as a scientific foundation for advancing the monitoring of drinking water resources.

Keywords: Ecological safety, Drinking water, Potable water, Normative database, Current database, Functional model, Conceptual model

DOI: https://doi.org/10.54381/icp.2025.2.10]]> Sayyara Gidayatzada
Environmental safety control in water reservoirs

The ecological safety of drinking water in the Jeyranbatan Water Reservoir is shaped by the interaction of natural processes, anthropogenic impacts, and temporal variations in environmental conditions. Ensuring the stability of quality indicators requires continuous monitoring of key parameters, systematic data processing, and scientifically grounded management decisions based on regulatory requirements. The article integrates real-time water quality measurements with an extensive normative database covering national and international standards. Taking the time factor into account, periodic fluctuations, long-term trends, and irregular deviations caused by external influences are distinguished within the indicators. The obtained results provide a basis for the early identification of undesirable changes in water quality and support corrective measures aimed at reducing ecological risks. Comparison with normative values enables assessment of the current state and more accurate forecasting of potential hazards. As a result, aligning reliable measurement data with standardized criteria increases the reliability of management decisions, reduces uncertainty, and strengthens the overall level of ecological safety. The proposed approach can serve as a scientific foundation for advancing the monitoring of drinking water resources.

Keywords: Ecological safety, Drinking water, Potable water, Normative database, Current database, Functional model, Conceptual model

DOI: https://doi.org/10.54381/icp.2025.2.10 ]]> Admin Tue, 23 Dec 2025 11:15:00 +0400