Institutional Repository of Vilnius University
Anestezijos gylio klasifikavimas pagal neapdorotus elektroencefalogramos signalus naudojant konvoliucinius neuroninius tinklus /
Abstract
dc:descriptionThis work analyzed the application of convolutional neural networks (CNNs) for classifying anesthesia depth based on raw electroencephalogram (EEG) signals collected during surgical operations. CNN models were utilized for binary (one-vs-one and one-vs-all) and multiclass classification tasks, with their classification metrics evaluated. To enhance the recognition of less frequent classes, a loss function balancing strategy was implemented. Additionally, hyperparameter optimization was carried out for the multiclass CNN model, yielding a model that demonstrated the highest accuracy and F1 score among all models evaluated in this work. The results suggest that CNN models have potential for application in anesthesia depth assessment systems, but their deployment requires further research and optimization.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2025
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Valiulis, Mantas,
Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- lit
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD231295023&prefLang=en_US