Institutional Repository of Vilnius University
Urbanistinių garsų klasifikavimas naudojant dirbtinius neuroninius tinklus /
Abstract
dc:descriptionIn this thesis the main goal was to compare artificial neural network classification capabilities in the context of urban sound classification. In this work, theoretical analysis related to artificial intelligence, machine learning, neural networks is provided. Also, you may find information as to how is sound processed, what sound features (characteristics) are used when trying to classify sounds. In this thesis, 2 types of artificial neural networks were implemented - deep as well as convolutional neural networks. There were 12 neural network models created - 6 deep, 6 convolutional. When comparing the results we've decided that convolutional neural networks are better suited for environmental sound classification, due to the better results that were received.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2019
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Gilys, Tomas,
- Contributors dc:contributor
-
- Kybartas, Rimantas
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:ELABAETD81919056&prefLang=en_US