https://journals.uran.ua/eejet/issue/feed 2024-11-14T13:54:20+02:00 Frolova Liliia eejet@entc.com.ua Open Journal Systems <p><span lang="EN-US">Terminology used in the title of the «Eastern-European Journal of Enterprise Technologies» - «enterprise technologies» should be read as «industrial technologies». <strong>«Eastern-European Journal of Enterprise Technologies»</strong> publishes all those best ideas from the science, which can be introduced in the industry. Since, obtaining the high-quality, competitive industrial products is based on introducing high technologies from various independent spheres of scientific researches, but united by a common end result - a finished high-technology product. </span>Among these scientific spheres, there are information technologies and control systems, engineering, energy and energy saving. Publishing scientific papers in these directions are the main development «vectors» of the «Eastern-European Journal of Enterprise Technologies». Since, these are those directions of scientific researches, the results of which can be directly used in modern industrial production: space and aircraft industry, instrument-making industry, mechanical engineering, power engineering, chemical industry and metallurgy.</p> <p><span lang="EN-US">Therefore, the scientists, associated with modern production, have the opportunity to participate in <strong>technology transfer to industry</strong>, publishing the results of their applied scientific researches. Industrialists, in turn, can draw scientific and practical information from the journal - each in their direction:</span></p> <ul> <li>specialists in management and computer science - from volumes «Applied Information Technologies and Control Systems», «Mathematics and Cybernetics - Applied Aspects»;</li> <li>mechanical and design engineers - from the volume «Applied Mechanics»;</li> <li>production engineers - from volumes «Mechanical Engineering Technology», «Applied Physics», «Materials Science», «Technology of organic and inorganic substances and the Ecology»;</li> <li>production and power engineers - from the volume «Energy-saving technology and equipment».</li> </ul> <p><span lang="EN-US"><strong>The goal of the journal</strong> is to eliminate the gap, which occurs between the rapidly emerging new scientific knowledge and their introduction in the industry, which requires much more time. Industrial enterprises are active subscribers to the «Eastern-European Journal of Enterprise Technologies», and production engineers check the practical value of those scientific and technological ideas, which are recommended for implementation by scientists-authors of the ''Eastern-European Journal of Enterprise Technologies».</span></p> <p><span lang="EN-US"><strong>The objective of the journal</strong> in achieving the goal is <strong>forming a «scientific component» of modern technologies transfer</strong> from science to industry. Therefore, in the papers, published in the journal, the emphasis is placed on both scientific novelty, and practical value.</span></p> https://journals.uran.ua/eejet/article/view/314845 2024-11-08T21:39:33+02:00 Aigerim Bolshibayeva kakim-aigerim@mail.ru Sabina Rakhmetulayeva ssrakhmetulayeva@gmail.com Baubek Ukibassov ukibas.b@gmail.com Zhandos Zhanabekov zzhanabekov@gmail.com

<p>This research focuses on developing a novel hybrid deep learning architecture designed for real-time analysis of ultrasound heart images. The object of the study is the diagnostic accuracy and efficiency in detecting heart pathologies such as atrial septal defect (ASD) and aortic stenosis (AS) from ultrasound data.</p> <p>The problem is the insufficient accuracy and generalizability of existing models in real-time cardiac image analysis, which limits their practical clinical application. To solve this, the convolutional neural networks (CNNs), combining local feature extraction was integrated with global contextual understanding of cardiac structures. Additionally, a YOLOv7 for precise segmentation and detection was utilized.</p> <p>The results demonstrate that the hybrid model achieves an overall diagnostic accuracy of 92 % for ASD detection and 90 % for AS detection, representing a 7 % improvement over the standard YOLOv7 model. These improvements are attributed to the hybrid architecture's ability to simultaneously capture fine-grained anatomical details and broader structural relationships, enhancing the detection of subtle cardiac anomalies.</p> <p>The findings suggest that combination of CNNs enhances pattern recognition and contextual analysis, leading to better detection of cardiac anomalies. The key features contributing to solving the problem include the hybrid architecture's ability to capture detailed local features and broader structural context simultaneously.</p> <p>In practical terms, the model can be applied in clinical settings that require real-time cardiac assessment using standard medical imaging equipment. Its computational efficiency and high accuracy make it suitable even in resource-constrained environments, reducing analysis time for clinicians, supporting personalized treatment plans, and potentially improving patient outcomes in cardiology</p>

2024-11-14T00:00:00+02:00 Copyright (c) 2024 Aigerim Bolshibayeva, Sabina Rakhmetulayeva, Baubek Ukibassov, Zhandos Zhanabekov