Addressing RFID misreadings to better infer bee hive activity

This paper proposes a method to address misreadings and consequent inadequacy of Radio- Frequency Identification (RFID) data for social insect monitoring. Six months worth of field experiment data were collected to demonstrate the application of the method. The data is transformed into a linear combination of Gaussian model and curve-fitted using evolutionary algorithm. The results show that the proposed method allows us to improve the quality of data that infer honey bee behaviour at the colony level.