Back to search
Institutional Repository of Vilnius University
Comparison of cnn and svm ensemble methods for acoustic drone recognition /
Abstract
dc:descriptionThis thesis explores combining SVM and CNN (ResNet) models for acoustic drone detection. When tested on known drones, the hybrid ResNet+SVM ensemble with product rule fusion achieved a perfect F1 of 1.0, outperforming standalone SVM (0.984) and CNN (0.963). On unseen drones, a CNN-only ensemble led with F1 of 0.907, with the hybrid ensemble close behind at 0.892. Ensembles of different machine learning models proved useful but not revolutionary.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2026
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Žilinskas, Mantas,
Subjects
dc:subject × 1Rights
dc:rights- Statement dc:rights
-
- info:eu-repo/semantics/openAccess
- Language dc:language
- eng
Identifiers
dc:identifier.*- Repository record dc:identifier
- https://repository.vu.lt/VU:ELABAETD308339392&prefLang=en_US