Ласкаво просимо до Інституційного репозитарію Хмельницького національного університету ElarKhNU!

 

Фонди

Виберіть фонд, щоб переглянути його зібрання.

Нові надходження

Документ
Formalization of Fabric Recycling Methods Depending on Raw Material Composition for Intelligent Decision Support Systems
(2026) Zagorodnya, A.; Tymofiiev, I.; Molchanova, M.; Mazurets, O.; Мазурець, Олександр Вікторович
The paper proposes a formalization of fabric recycling methods depending on raw material composition for intelligent decision support systems in textile recycling. The study focuses on combining computer vision, machine learning, and rule-based decision mechanisms to support automated textile waste sorting and processing. The proposed approach includes classification of fabrics into raw material categories, assessment of prediction reliability, and generation of recommendations for further handling, such as reuse, mechanical recycling, chemical recycling, downcycling, or manual inspection. The methodology emphasizes not only fabric recognition but also the intelligent selection of the most appropriate recycling scenario. Experimental results demonstrate that computer vision models can achieve high accuracy in distinguishing natural and synthetic fabrics, creating a practical basis for automated textile recycling systems. The proposed approach can be applied in textile sorting lines, recycling centers, and digital decision support services for sustainable waste management.
Документ
Analysis of Dataset of Textile Materials Macro Images to Detect Data Leaks
(2026) Merezhko, Ye.; Yurchenko, D.; Molchanova, M.; Mazurets, O.; Мазурець, Олександр Вікторович
The paper analyzes a dataset of textile material macro images to detect redundancy-related data leaks that may negatively affect the reliability of neural network classification. The study emphasizes that textile datasets often contain visually similar or near-duplicate images due to repetitive fabric textures and repeated image acquisition conditions, which can lead to inflated evaluation results and reduced model generalization. The proposed approach combines perceptual hashing (pHash) and deep embeddings extracted from a pretrained ResNet18 model to identify and remove redundant images from the dataset. Experimental results demonstrate that dataset cleaning improves classification stability and increases the trustworthiness of CNN-based textile recognition models. The practical significance of the work lies in improving the quality of textile datasets for computer vision tasks, automated fabric classification, and intelligent textile recycling systems.
Документ
Investigation of Augmentation Impact of Fibers Macro-Images Set on the Neural Network Classification Accuracy
(2026) Savenko, B.; Zalutska, O.; Mazurets, O.; Molchanova, M.; Мазурець, Олександр Вікторович
The paper investigates the impact of image augmentation on the accuracy of neural network classification of textile fibers macro-images. The study focuses on improving automated recognition of fiber composition for textile sorting and recycling systems using computer vision and convolutional neural networks. Several augmentation techniques, including rotation, zoom, translation, contrast adjustment, and horizontal flipping, were experimentally analyzed using a MobileNetV2-based classifier trained on a three-class dataset of textile fiber macro-images. The results demonstrated that augmentation can improve classification stability and generalization, although its effect differs between classes and transformations. The study showed that zoom and translation provided the best overall improvement in macro-F1 score, while some transformations negatively affected specific classes. The obtained results confirm that augmentation in texture-based textile classification should be treated as a controlled experimental factor rather than a universal preprocessing operation.
Документ
Intelligence Information System for Transformer-Based Sentiment Analysis
(2026) Mazurets, O.; Kuzmak, K.; Rovinsky, A.; Kadynska, V.; Мазурець, Олександр Вікторович
The paper presents an intelligent information system for transformer-based sentiment analysis focused on detecting gender bias in text classification models. The study emphasizes that transformer architectures may assign different sentiment scores to semantically identical sentences depending on gender-related words, which can negatively affect the fairness and objectivity of NLP systems. The proposed system uses counterfactual text generation by creating male and female versions of the same sentence and comparing the sentiment scores produced by a DistilBERT-based model. The architecture includes modules for text preprocessing, counterfactual generation, sentiment classification, bias detection, and result interpretation. Experimental evaluation demonstrated that the model exhibited gender-related differences in a significant number of analyzed cases, confirming the relevance of fairness auditing in sentiment analysis systems. The developed approach can be applied for ethical evaluation and monitoring of transformer-based NLP models.
Документ
Військові дії в Україні та їх наслідки для довкілля
(Видавництво Львівської політехніки, 2026-05-18) Нестер, Анатолій; Войтишина, Вікторія
Безпека довкілля в Україні в умовах воєнного стану носить глобальну проблему породжену варварськими діями російської держави внаслідок бойових дій на нашій території. Існує серйозна загроза ядерної катастрофи через захоплення Запорізької атомної електростанції та знаходження на її території військовослужбовців російської федерації, озброєння та замінувавши місцевість, а також обстрілюючи з її території міста на іншому березі водосховища - Нікополь і Марганець.