Real-time swarming detection in honeybees: Leveraging audio signal processing and machine learning techniques

Abstract

Acoustical signals play a significant role in honey bee communication across various behavioral contexts. One notable example is queen piping, which refers to the acoustic signals emitted by young queens during the swarming process. Specifically, emerged virgin queens emit a distinct acoustic signal known as “tooting.” Tooting signals typically consist of one or two pulses lasting approximately one second, characterized by an initial rise in both amplitude and frequency. Recognizing these signals is of utmost importance for beekeepers as it enables them to identify an imminent swarm, effectively manage the swarming process, and safeguard the colony. This paper proposes a novel method for online swarming detection in honey bees, leveraging audio signal collection, acoustical signal processing, and machine learning techniques. The experimental results demonstrate the effectiveness of the proposed system in accurately detecting swarming at its early stages. Notably, the system maintains a high level of accuracy even when confronted with environmental noise and other unfamiliar audio signals that could potentially corrupt the audio signal acquired from the beehive.