Date of Award:


Document Type:


Degree Name:

Doctor of Philosophy (PhD)


Computer Science

Committee Chair(s)

Vladimir A. Kulyukin


Vladimir A. Kulyukin


Xiaojun Qi


Jacob Gunther


Nicholas Flann


Haitao Wang


In recent years, a widespread decline has been seen in honey bee population and this is widely attributed to colony collapse disorder. Hence, it is of utmost importance that a system is designed to gather relevant information. This will allow for a deeper understanding of the possible reasons behind the above phenomenon to aid in the design of suitable countermeasures.

Electronic Beehive Monitoring is one such way of gathering critical information regarding a colony’s health and behavior without invasive beehive inspections. In this dissertation, we have presented an electronic beehive monitoring system called BeePi that can be placed on top of a super and requires no structural modifications to a standard beehive (Langstroth or Dadant beehive), thereby preserving the sacredness of the bee space without disturbing the natural beehive cycles. The system is capable of capturing videos of forager traffic through a camera placed over the landing pad. Audio of bee buzzing is also recorded through microphones attached outside just above the landing pad. The above sensors are connected to a low-cost raspberry pi computer, and the data is saved on the raspberry pi itself or an external hard drive.

In this dissertation, we have developed an algorithm that analyzes those video recordings and returns the number of bees that have moved in each video. The algorithm is also able to distinguish between incoming, outgoing, and lateral bee movements. We believe this would help commercial and amateur beekeepers or even citizen scientists to observe the bee traffic near their respective hives to identify the state of the corresponding bee colonies. This information helps those mentioned above because it is believed that honeybee traffic carries information on colony behavior and phenology.

Next, we analyzed the audio recordings and presented a system that can classify those recordings into bee buzzing, cricket chirping, and ambient noise. We later saw how a long–term analysis of the intensity of bee buzzing could help us understand the hive’s development through an entire beekeeping season.

We also investigated the effect of local weather conditions using 21 different meteorological variables on the forager traffic. We collected the meteorological data from a weather station located on the campus of Utah State University. Through our study, we were able to show that without the use of additional costly intrusive hardware to count the bees, we can use our bee motion counting algorithm to calculate the bee motions and then use the counts to investigate the relationship between foraging activity and local weather.

To ensure that our findings and algorithms can be reproduced, we have made our datasets and source codes public for interested research and citizen science communities.