Abstract
dc:descriptionThe aim of this work is to develop a monitoring system for bee pests that can detect small hive beetles and alert the beekeeper. Various Internet of Things architectures can be used to implement such systems, including cloud, edge, and fog computing. The most economical and optimal solution is the fog architecture, which enables data processing closer to the beehives. Convolutional neural networks can be applied for pest detection, and their architectures are typically categorized into one-stage, two-stage, and transformer-based models. One-stage models offer the best balance between accuracy and computational resource efficiency. Creating a dataset of bee pests is a challenging task due to the limited amount of publicly available material and the need to account for varying lighting conditions. A prototype of the system was developed, demonstrating that such a system is feasible and can be extended with additional functionalities in the future. The purpose of the system is to provide beekeepers an easy way to manage their hives and receive notifications when pests are detected.
Degree
thesis:*- Grantor dc:publisher
- Institutional Repository of Vilnius University
- Year dc:date
- 2025
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- Grinkevičius, Tedas,
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:ELABAETD239030336&prefLang=en_US