https://icsfti-proc.kpi.ua/ <p>The conference is organized by KPI named after Igor Sikorskyi and is dedicated to the memory of the outstanding scientist, teacher of the Department of Computing, Professor Shirochyn. Co-organizers of the conference on behalf of the university are the Faculty of Informatics and Computer Engineering, the Faculty of Applied Mathematics. The purpose of the conference is to discuss scientific results and exchange experience between scientists conducting research in the field of computer engineering, software engineering and technical education.</p> en-US The International Conference on Security, Fault Tolerance, Intelligence https://icsfti-proc.kpi.ua/article/view/328424 <p>This paper presents the NASCA method, which combines convolutional neural networks (CNN) and convolutional variational autoencoders (CVAE) to enhance the classification of lung auscultation sounds under limited and imbalanced data conditions. The method integrates data preprocessing, synthetic augmentation, and robust deep learning classification with strict control against data leakage. Experiments conducted on the ICBHI dataset achieved an F1-score of 98.45% in multi-class classification. The results confirm the potential of NASCA for improving early respiratory disease detection.</p> Denis Panaskin Copyright (c) 2025 2025-04-29 2025-04-29 1 16