AN ADAPTIVE APPROACH TO THE BEE HIVE STATE IDENTIFICATION USING NEURAL NETWORKS AND AUDIO ANALYSIS
DOI:
https://doi.org/10.34185/1991-7848.itmm.2024.01.021Keywords:
neural networks; tensorflow; deep learning; bees; MFCCs; STFT; bees;Abstract
Monitoring the queen bee is crucial for the health and productivity of a bee colony. The queen plays a vital role in reproduction and maintaining the colony's population. Utilizing neural networks, such as CNNs along with sound analysis, can be a valuable tool for monitoring queen bees and assessing their behavior and health within the hive. Finding the best way to preprocess audio data and review it is an important task that, if performed well, will help to track the bee hive population and its health state in general. According to the training and evaluation results, MFCCs-based models have given constant good results, and when used on a limited audio dataset, pre-trained model showed better performance than the one trained from zero.
References
Kremen C., Williams N. M., Thorp R. W. Crop pollination from native bees at risk from agricultural intensification. Proceedings of the National Academy of Sciences. 2002.
Vol. 99, no. 26. P. 16812–16816.
Kirchner W. H. Acoustical communication in honeybees. Apidologie. 1993. Vol. 24,
no. 3. P. 297–307.
Use of LSTM Networks to Identify “Queenlessness” in Honeybee Hives from Audio Signals / S. Ruvinga et al. 2021 17th International Conference on Intelligent Environments (IE), Dubai, United Arab Emirates, 21–24 June 2021. 2021.
Nolasco I., Benetos E. To bee or not to bee: Investigating machine learning approaches to beehive sound recognition. Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE). 2018.
