2016 •
Application of neural networks for honey bee colony state identification
Authors:
Armands Kviesis, Aleksejs Zacepins
Abstract:
During the honey bee colony's life cycle different colony states can be observed. At certain situations some of the states can negatively impact colony's development (broodless state, swarming) resulting in possible colony's death and increase of beekeepers costs. On the other hand, when honey bee colony is in active brood rearing stage (at the preferable period) it is a sign that the colony is capable of reproduction. By knowing in which state the bee colony are at a specific moment, without opening the hive, beekeeper can improve his apiary m (...)
During the honey bee colony's life cycle different colony states can be observed. At certain situations some of the states can negatively impact colony's development (broodless state, swarming) resulting in possible colony's death and increase of beekeepers costs. On the other hand, when honey bee colony is in active brood rearing stage (at the preferable period) it is a sign that the colony is capable of reproduction. By knowing in which state the bee colony are at a specific moment, without opening the hive, beekeeper can improve his apiary management, e.g., timely prepare for further actions. Within the “Application of Information Technologies in Precision Apiculture” (ITAPIC) project, colony monitoring was performed using one temperature sensor per honey bee hive. This gives enough data to examine temperature dynamics and allows to determine the patterns of the given honey bee colony states. Based on these data, it is possible to develop a honey bee colony state identification process. This can be achieved by inspecting the temperature data and developing algorithms for each honey bee colony state or by applying neural networks. Neural networks are widely used for various tasks, including tasks related to classification and data processing. In this paper authors propose a method for honey bee colony state (commencement of brood rearing period and swarming) detection using neural networks with supervised learning. (Read More)
2016 17th International Carpathian Control Conference (ICCC) ·
2016
Artificial intelligence |
Machine learning |
We have placed cookies on your device to help make this website and the services we offer better. By using this site, you agree to the use of cookies. Learn more