Use of LSTM neural networks to identify 'queenlessness' in honeybee hives from audio signals

Ruvinga, Stenford, Hunter, Gordon J.A., Duran, Olga and Nebel, Jean-Christophe (2021) Use of LSTM neural networks to identify 'queenlessness' in honeybee hives from audio signals. In: 17th International Conference on Intelligent Environments; 21 - 24 Jun 2021, Dubai, United Arab Emirates (held online).

Abstract

Honeybees are of vital importance to both agriculture and ecology, but honeybee populations have been in serious decline over recent years. The queen bee is of crucial importance to the success of a colony. In this paper, we make a contribution to addressing these problems by employing LSTM, Multi-Layer Perceptron Neural Networks and Logistic Regression approaches applied to audio data recorded from “queen-less” and “queen-right” hives to provide a method of prompt detection of a hive lacking a healthy queen. The initial results – particularly from the LSTM - are highly encouraging.

Actions (Repository Editors)

Item Control Page Item Control Page