The prediction of swarming in honeybee colonies using vibrational spectra

Abstract

in this work, we disclose a non-invasive method for the monitoring and predicting of the swarming process within honeybee colonies, using vibro-acoustic information. two machine learning algorithms are presented for the prediction of swarming, based on vibration data recorded using accelerometers placed in the heart of honeybee hives. Both algorithms successfully discriminate between colonies intending and not intending to swarm with a high degree of accuracy, over 90% for each method, with successful swarming prediction up to 30 days prior to the event. We show that instantaneous vibrational spectra predict the swarming within the swarming season only, and that this limitation can be lifted provided that the history of the evolution of the spectra is accounted for. We also disclose queen toots and quacks, showing statistics of the occurrence of queen pipes over the entire swarming season. From this we were able to determine that (1) tooting always precedes quacking, (2) under natural conditions there is a 4 to 7 day period without queen tooting following the exit of the primary swarm, and (3) human intervention, such as queen clipping and the opening of a hive, causes strong interferences with important mechanisms for the prevention of simultaneous rival queen emergence.

On the Importance of the Sound Emitted by Honey Bee Hives

“…A simple analysis of recorded sound is performed by means of a Fourier transform. One of the most recent contributions in this field is from Ramsey et al [61]. In this work, the authors improve the results of their previous work [43].…”

“…Swarming detection and swarming prediction. [61] (a) 2. Different microphones and accelerometers placement inside the colonies, based on different approaches.…”

“…( g ) from [ 54 ] shows a custom brood frame. Finally, ( h ) from [ 61 ] shows accelerometers positioning similar to the one proposed in [ 43 ].…”

Comparison of Feature Extraction Methods for Sound-Based Classification of Honey Bee Activity

“…Spectral analysis has also been used for studying and monitoring the so called "waggle dance" of bees [10]: in fact, authors explain that there is a correlation between bee dance and the presence of harmonics near 320 Hz in the recorded signals, showing that it is possible to generate signals at which bees react. On [37], authors use accelerometers to acquire the bees sound inside the colony, and then by means of multidimensional FFT and discriminant functions, swarming events have been predicted. In [38], machine learning methods are proposed capable of distinguishing bee buzzing from cricket chirping and ambient noise.…”

The effect of a lack of uncapped brood on social interactions between honey bee workers and the queen

“…The vibro-acoustic signals were mostly studied with the use of microphones (Wenner 1962a, b, Wenner et al 1967Ohtani and Kamada 1980;Michelsen et al 1986aMichelsen et al , b, 1987Pratt et al 1996;Seeley and Tautz 2001) and less often using laser vibrometers (Michelsen et al 1986a, b;Hrncir et al 2008) or accelerometers (Ramsey et al 2017(Ramsey et al , 2020. However, our previous research (Łopuch and Tofilski 2017a(Łopuch and Tofilski , b, 2019(Łopuch and Tofilski , 2020 proved that recording honey bee behaviour with a high-speed camera is a simple and useful alternative.…”