VSVitalii Serdechnyi

Vitalii Serdechnyi

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Vitalii Serdechnyi has a total of 13 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    COMPUTER VISION-BASED CONTACTLESS CONTROL INTERFACE FOR EDUCATIONAL ENVIRONMENTS

    by Olesia Barkovska, Artem Bakulin, Volodymyr Mytiai, Oleksandr Yankovskyi, Ihor Novoseltsev, Vitalii Serdechnyi

    The relevance of this study is determined by the growing role of distance learning systems and the need to expand interaction modalities with them, particularly in situations of limited access to traditional input devices or within the context of inclusive education. The aim of this study is to design and assess the practical feasibility of a computer vision-based contactless interface for LMS control through operating-system input events, considering robustness under varying lighting, distance, viewpoint, and resolution and comparison with conventional mouse-and-keyboard interaction. To achieve this aim, the following tasks were formulated: to develop a model of a gesture-based LMS control method; to implement both a single-hand gesture mode and a bimanual interaction mode for different control scenarios; to conduct a series of experiments evaluating the accuracy and robustness of gesture recognition under varying recording conditions; and to perform a comparative analysis of the effectiveness of gesture-based control versus the classical “mouse and keyboard” interface. The research methods include computer vision techniques based on hand landmark detection, algorithmic interpretation of gestures using geometric and dynamic features, as well as experimental measurements of recognition accuracy, task execution time, and the number of interaction errors. The evaluation involved five static hand poses, 30 repetitions per pose, and three representative interaction scenarios. The results demonstrate that the proposed system provides stable recognition of large static hand poses across a wide range of lighting conditions and camera distances. Changes in hand orientation were identified as the most critical factor affecting recognition accuracy. All three scenarios were successfully completed in the baseline trials at a resolution of 1280×720, with no critical interaction errors recorded. The practical feasibility of gesture-based control was demonstrated through its integration with a real learning management system, dl.nure.ua, via operating system–level input events. The practical significance lies in its applicability for controlling educational web platforms in distance learning environments, during presentations, and in inclusive education scenarios.

  • The impact of the number representation format in parameterized text queries on the accuracy of 3D model generation

    by Olesia Barkovska, Liubov Bukharova, Igor Ruban, Oleksii Liashenko, Andriy Kovalenko, Vitalii Serdechnyi

    The subject matter of the article is the analysis of the artificial intelligence models for generating 3D objects based on a text query with different formats for representing numerical parameters. The goal of the work is to evaluate and compare the effectiveness of the Hunyuan3D 2.0, Michelangelo and SDFusion models depending on the format of the text input queries using the following metrics: generation time, CLIP-Similarity and Chamfer Distance. The tasks to be solved are: 1) to conduct a systematic review of modern generative 3D models regarding their ability to process queries with numerical parameters presented in different formats (decimals, verbal representations, fractions); 2) to conduct a quantitative and qualitative evaluation of generative 3D models using the metrics of generation time, CLIP-Similarity and Chamfer Distance, taking into account the visual similarity to text descriptions and geometric similarity to Ground Truth objects; 3) to analyse the obtained results of generative text-to-3D models evaluation for parameterized 3D objects generation tasks for further implementation in user interface applications. The methods used in this work are machine learning methods, methods of vector representation of text and images, statistical methods of evaluating results, and a heuristic method of forming text queries. The results show that there is no universal generative 3D model that is capable of creating objects that fully correspond to a parameterised text query. The proposed methodology enables the formation of input text sequences containing such numerical representations, including decimals, verbal representations or fractions, for further analysis of the accuracy of object generation. Conclusions. Similar efficiency of training 3D generative models in the joint latent space of text features containing numerical parameters and using datasets with precisely defined geometric characteristics of objects was confirmed. The results show that the Hunuyan3D-2.0 model is suitable for further research and modification to adapt the used methods to create personalised 3D objects with given numerical parameters, such as a prosthetic cover.

  • Open Access

    Research on machine learning methods for detecting objects in difficult shooting conditions

    by Vitalii Serdechnyi, Olesia Barkovska, Andriy Kovalenko, Anton Havrashenko, Vitalii Martovytskyi

    The subject matter of the article is research into machine learning methods for object detection in images and videos under complex urban conditions, particularly under poor lighting, the presence of precipitation, high scene complexity, and limited computational resources. The goal of this research is to identify the most effective deep learning models based on convolutional neural networks for object detection tasks under challenging imaging conditions, considering the practical requirements for accuracy and processing speed. The tasks to be solved are: analysis of object detectors (YOLO v8–11, DETR, SSD, Mask R-CNN, Faster R-CNN, RetinaNet); preparation of a dataset with real weather conditions and pedestrian environments in Ukraine; experimental evaluation of selected detectors using the metrics mAP@0.5, mAP@.5:.95, Recall, Precision, IoU, FPS, and F1-Score; and analysis of the obtained results. The methods used are: convolutional neural networks, automated image annotation, comparative analysis of quality metrics (F1-score, mAP@0.5:.95, Precision, Recall, IoU, FPS), and manual correction of annotations. The following results were obtained: the YOLOv10-m and YOLOv11-m models demonstrated the best quality indicators under conditions of limited visibility and varying lighting. The YOLOv11-m model was the most balanced in terms of accuracy and speed across all tested conditions - snow, rain, and sunshine. YOLOv11-m is recommended as the baseline model for implementation in real-time systems, particularly in intelligent assistants for people with visual impairments. Conclusions: The scientific novelty of the results obtained is as follows: 1) a comprehensive evaluation of modern deep learning architectures for object detection (YOLOv8–v11, Faster R-CNN, SSD, Mask R-CNN, DETR, RetinaNet) was carried out under non-laboratory conditions, including real weather scenarios such as snow, rain, and poor lighting, which are typical for urban environments in Eastern Europe; 2) the software tool for automated model evaluation was developed, allowing simultaneous testing of multiple architectures and visualization of performance metrics (F1-score, mAP@0.5, mAP@.5:.95, IoU, Precision, Recall, FPS) with support for manual annotation correction and comparative model analysis; 3) it was experimentally established that the YOLOv11-m model demonstrates the best balance of accuracy and inference speed across various complex imaging conditions, justifying its recommendation as a baseline model for real-time vision-based assistive systems.

  • Open Access

    Analysis of the impact of the contextual embeddings usage on the text classification accuracy

    by Olesia Barkovska, Anton Havrashenko, Vitalii Serdechnyi, Vladyslav Kholiev, Patrik Rusnak

    Analysis of the impact of the contextual embeddings usage on the text classification accuracy


  • Open Access

    Intelligent assistance system for people with visual impairments

    by Olessia Barkovska, Vitalii Serdechnyi

    Subject of the Research: The creation of an intelligent assistance system for people with visual impairments. Nowadays, the task of developing effective intelligent assistance systems that allow people with vision problems to achieve maximum independence is important and relevant, as existing systems have a number of drawbacks, such as limited autonomy, limited integration with other devices and systems, limited analysis of dynamic obstacles, and limited user feedback capabilities, which in most cases are restricted to voice guidance. Objective: The objective of this work is to create a generalized functional model of an intelligent assistance system for people with visual impairments, which has enhanced autonomy, integration with other devices and systems, the ability to analyze dynamic objects and predict their movement trajectory, and provide diverse feedback to the user. Tasks: To achieve the set objective, the following tasks were accomplished: a generalized functional model of the proposed intelligent assistance system for people with visual impairments was created; the functional dependencies of the components of the developed model were substantiated; a review of the basic modules of the proposed system model was conducted. Methods: The methods used include functional modeling methods and system analysis methods. Results: The following results were obtained: a functional model of an intelligent assistance system for people with visual impairments was proposed. This system surpasses existing analogs in a number of functional capabilities: detection of static and dynamic obstacles with prediction of dynamic obstacles’ movement trajectory, the ability to operate in various conditions (indoors, outdoors, in light or dark, in different weather conditions), support for integration with other systems and devices, and a high level of autonomy. Conclusions: The developed system model has enhanced autonomy, integration with other devices and systems, the ability to analyze dynamic objects and predict their movement trajectory, and provides diverse feedback to the user.