Tetiana Nosenko

Dr. Tetiana Nosenko


Research Focus & Metrics

Academic Career Length

9Years (2018-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2021
Verified
Book
Closed access
VAVadym Abramov
Vadym Abramov
MAMariia Astafieva
Mariia Astafieva
MBMariia Boiko
Mariia Boiko
DBDmytro Bodnenko
Dmytro Bodnenko
ABAleksandr Bushma
Aleksandr Bushma
VYVladyslav Yaskevych
Vladyslav Yaskevych
The monograph highlights the results of the scientific topic "Theoretical and practical aspects of the use of mathematical methods and information technology in education and science" (registration number 0116U004625) by the Department of Computer Science and Mathematics, Faculty of Information Technology and Management, Borys Hrinchenko University of Kyiv (deadline: March 2016 - March 2021). The main scientific and practical results in the following areas are presented: mathematical and computer modeling, hardware and software of automated control systems, application of digital technologies in the educational process. For scientific and pedagogical, scientific and pedagogical workers who are interested in modern problems of application of mathematical methods and digital technologies in education and science.

26 June 2025 in Cybersecurity: Education, Science, Technique
Verified
Journal Article
Open access
PDF file
Iryna MashkinaIryna Mashkina
Iryna Mashkina
TNTetiana Nosenko
Tetiana Nosenko
OHOksana Hlushak
Oksana Hlushak
SSSvitlana Spivak
Svitlana Spivak
VBVladyslav Bilous
Vladyslav Bilous
ВБВладислав Білоус
Владислав Білоус
This article researches the effectiveness of implementing AI chatbots to optimize customer support (Customer Support) using the example of a waste collection business. The classification of chatbots is considered, and examples of popular AI solutions, such as Zendesk Answer Bot and LivePerson, are provided for analyzing ready-made systems in customer service. The key areas of project implementation for developing a chatbot for a waste collection company are described in detail, including data collection and analysis, optimization of garbage collection routes, and management of the vehicle fleet. The work highlights the intelligent technologies used to create the chatbot, particularly machine learning for data analysis and forecasting, natural language processing (NLP) for understanding queries, and GPS integration for logistics optimization. The main stages of chatbot development and training are considered, and the importance of its integration with CRM and other corporate systems to ensure seamless data exchange and improve service quality is emphasized. The advantages of using AI chatbots are analyzed, including improved customer interaction, optimization of logistics processes, and reduction of negative environmental impact. The specifics of the developed chatbot for the waste collection company are outlined: goals and tasks were defined, the Microsoft Bot Framework platform was chosen, and the architecture, user interface, and knowledge base were developed. Training and testing of the system were carried out, and its integration with CRM for accessing customer data and updating information, with a GPS monitoring system for tracking garbage trucks and informing customers, as well as with notification and waste accounting systems, is envisaged. Currently, the project is at the stage of implementation and monitoring, which includes integration into the real environment and analysis of effectiveness. Prospects for further research are identified, in particular, forecasting waste volumes, developing more complex interaction scenarios, and studying ethical aspects.

1 January 2025 in Cybersecurity: Education, Science, Technique
Verified
Journal Article
Open access
PDF file
TNTetiana Nosenko
Tetiana Nosenko
Iryna MashkinaIryna Mashkina
Iryna Mashkina
IMIryna Melnyk
Iryna Melnyk
ІМІрина Машкіна
Ірина Машкіна
ІМІрина Мельник
Ірина Мельник
The paper addresses the urgent problem of automated detection of low-activity moving sources of ionizing radiation in dynamic radiation monitoring systems. The limitations of classical threshold-based signal processing algorithms, characterized by low sensitivity and high false alarm rates under low signal-to-noise ratio conditions, are analyzed. A novel method for identifying radiation anomalies based on a One-Dimensional Convolutional Neural Network (1D CNN) is proposed. A mathematical model and software algorithm for generating synthetic time series of a scintillation detector have been developed, taking into account the stochastic nature of radiation detection (Poisson statistics), vehicle passage geometry, and shielding effects. The developed neural network model was trained and tested on the generated datasets. The effectiveness of the proposed approach has been experimentally confirmed: the classification accuracy for medium-activity sources reached 98.5%, and for extremely weak signals visually indistinguishable from noise, it remained at 83.5%. The obtained results demonstrate the potential of applying deep learning methods to enhance the reliability of radiation security systems.

1 January 2025 in OPEN EDUCATIONAL E-ENVIRONMENT OF MODERN UNIVERSITY
Verified
Journal Article
Open access
PDF file
ВВВікторія Павлівна Вембер
Вікторія Павлівна Вембер
Iryna MashkinaIryna Mashkina
Iryna Mashkina
TNTetiana Nosenko
Tetiana Nosenko
VYVladyslav Yaskevych
Vladyslav Yaskevych
ІМІрина Вікторівна Машкіна
Ірина Вікторівна Машкіна
ВЯВладислав Олександрович Яскевич
Владислав Олександрович Яскевич
The article explores the opportunities and challenges of using artificial intelligence (AI) in teaching professional disciplines to students majoring in "Computer Science" and "Software Engineering." It analyzes modern approaches to defining AI, international and national regulatory initiatives, as well as research findings on the integration of AI into the educational process. Practical examples of AI application are examined, including automated assessment, personalized learning, algorithm visualization, and programming support. The article also analyzes how AI can contribute to improving the learning process and enhancing the quality of education, while addressing ethical and practical aspects of its use. The main focus is on identifying the role of AI in teaching and learning, analyzing AI tools and technologies, discussing the limitations and challenges of AI, and providing recommendations for its effective implementation. The article aims to provide educators and students with an understanding of the potential and limitations of AI in education and to suggest ways to use these technologies effectively to improve the educational process. It identifies problems related to academic integrity, the quality of prompts, student dependence on automated solutions, and the risk of declining critical thinking skills. Pedagogical approaches for effective AI use are proposed, including the "flipped classroom" model and Bloom's taxonomy. Recommendations are also provided for adapting learning tasks and reinforcing individual project defenses. It is concluded that combining traditional teaching methods with AI capabilities can improve the quality of education, but requires careful planning, ethical consideration, and a responsible stance from educators and educational institutions.

6 November 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
TNTetiana Nosenko
Tetiana Nosenko
Iryna MashkinaIryna Mashkina
Iryna Mashkina
This study explores the application of Artificial Intelligence (AI) algorithms for detecting hazardous substance discharges into water bodies and modeling their distribution. River pollution remains a major environmental concern, while traditional monitoring methods are labor-intensive, costly, and lack operational efficiency. The paper analyzes key water quality parameters and modern Internet of Things (IoT) systems that enable real-time data collection on indicators such as pH, dissolved oxygen, temperature, and turbidity. Emphasis is placed on Machine Learning (ML) algorithms for anomaly detection and pollution forecasting. Methods including linear regression, decision trees, neural networks, and clustering are compared, with particular attention to ensemble models such as Random Forest (RF) and XGBoost. Using open environmental data on Ukrainian surface waters for 2022, RF and XGBoost were found to effectively predict nitrogen and dissolved oxygen concentrations and identify anomalies linked to anthropogenic pollution sources, including municipal sewage and agricultural runoff. The integration of AI and IoT technologies significantly improves the accuracy, speed, and efficiency of water quality monitoring, supporting early warning systems and sustainable water management while highlighting ongoing challenges related to data quality and implementation costs.

1 January 2025 in Cybersecurity: Education, Science, Technique
Verified
Journal Article
Open access
TNTetiana Nosenko
Tetiana Nosenko
Iryna MashkinaIryna Mashkina
Iryna Mashkina
In the context of increasing technogenic risks and the need for rapid response to radiation-related emergencies, mobile environmental monitoring systems are becoming a critical component of national safety and public health protection. This article presents a comprehensive approach to modeling the processing of spatially distributed environmental data collected by unmanned aerial vehicles (UAVs) equipped with IoT-based radiation sensors. The proposed system architecture is based on a three-tier client-server model that separates data acquisition, processing, and visualization tasks. The UAV platform integrates lightweight, energy-efficient IoT sensors capable of real-time data transmission, including geolocation and radiation dose measurements. The core contribution of this research lies in the development of a data processing algorithm tailored for dynamic, irregularly spaced measurements. The algorithm includes noise filtering, temporal and spatial aggregation, and spatial interpolation using the Inverse Distance Weighting (IDW) method. The IDW technique was selected for its simplicity, transparency, and high sensitivity to local variations, making it suitable for generating detailed heatmaps of radioactive contamination. The modeling process demonstrates the algorithm’s ability to transform raw sensor data into continuous contamination surfaces, enabling intuitive interpretation and decision-making. Additionally, the article outlines the integration of the algorithm into a mobile application interface, which provides users with interactive access to processed data layers. The application retrieves pre-rendered heatmap tiles from the server based on the user’s viewport and zoom level, ensuring fast and responsive visualization. The system’s modular design allows for scalability and adaptation to various environmental monitoring scenarios. The research highlights the importance of combining UAV mobility, IoT sensor intelligence, and spatial modeling to overcome limitations of traditional monitoring systems. It also identifies future directions for enhancing interpolation accuracy through machine learning methods and expanding the system’s applicability to other types of environmental hazards.