The Determination of the Developments of Beehives via Artificial Neural Networks

• Published in: Tehnički vjesnik Vol. 25; no. 2; pp. 553 - 557
• Main Authors: Bayir, Raif, Albayrak, Ahmet
• Format: Journal Article Web Resource
• Language: English
• Published: Slavonski Baod University of Osijek 01.04.2018; Josipa Jurja Strossmayer University of Osijek; Strojarski fakultet u Slavonskom Brodu; Fakultet elektrotehnike, računarstva i informacijskih tehnologija Osijek; Građevinski i arhitektonski fakultet Osijek; Faculty of Mechanical Engineering in Slavonski Brod, Faculty of Electrical Engineering in Osijek, Faculty of Civil Engineering in Osijek
• Subjects: Analysis; Artificial intelligence; Artificial neural networks; backpropagation; Beekeeping; Embedded systems; European honeybee; Food; Honey; intelligent systems; Model accuracy; Neural networks; Weight
• ISSN: 1330-3651; 1848-6339
• DOI: 10.17559/TV-20160419130812

Honeybees provide great benefits for people both with the foods they produce and as a pollinator. It is known that they pass the whole year with the foods they collect in spring and summer months. Beekeepers also benefit from the honey produced in these periods. Whether a beehive works adequately or not and its status of development can be understood through the observations by beekeepers. In this study, an Arduino-supported neural network model was developed in order to obtain information about the general situations of beehives. The three-input and three-output neural networks were embedded in a board after the training and testing stage. While temperature, humidity, and weight refer to inputs, good situation, stable situation, and bad situation represent outputs. The real-time model has an accuracy of 99.84%.