EnBeeMo
Multicriterial Hyperparameter Optimization of the EnBeeMo’s BeeCount-Algorithm
Development of a cloud-based environment for optimising neural networks for tracking bees. An interdisciplinary team of students at Munich University of Applied Sciences led by Professor Herbert Palm has taken on this challenge. But what is this all about? Quite simply, it's about ecological agriculture, which can only work if the needs of bees, humans and nature are taken into account in the long term. To this end, it is important to find suitable ways to count the number of bees in a colony without interfering with their natural habitat.
In this way, conclusions can be drawn about certain location factors and events that may have an influence on the development of the respective bee colony. One proposed solution, which was developed as part of the DTLab Challenge at Munich University of Applied Sciences, is a system called "EnBeeMo", which uses an infrared camera in front of the hive to record videos of the bees flying in and out. The resulting images are then evaluated using a machine learning algorithm.
Staff:
- Matthias Wick
Project partners:
- Micron (Bereich Graphics Memory)
- Amazon Web Services (AWS)
