Edge Computing for Bee Monitoring: Queen Absence Detection via Audio Analysis

• Jorge F. Ramos Bezerra IFCE
• Sandy F. da Costa Bezerra UFC
• Ícaro de Lima Rodrigues UFC
• Elias Teodoro da Silva Jr. IFCE
• Danielo G. Gomes UFC
• Antonio Rafael Braga IFCE

DOI: https://doi.org/10.5753/wcama.2025.9205

Abstract

The preservation of bees is essential for biodiversity, and the presence of the queen bee is crucial for the organization of the hive. Using cutting-edge computing, this work proposes a method to detect its absence through the analysis of hive audio in a fast, feasible and accessible way. The recordings were processed, extracting relevant acoustic features, used in the classification by Naive Bayes, KNN, MLP and Random Forest. These algorithms achieved accuracies ranging from 87.66% to 97.54%. MLP was chosen for implementation in a microcontroller, where it achieved 88.50% accuracy with an average inference time of 109 ms.

References

Abdul, Z. K. and Al-Talabani, A. K. (2022). Mel frequency cepstral coefficient and its applications: A review. IEEE Access, 10:122136–122158.

Braga, R., A., G. Gomes, D., Rogers, R., E. Hassler, E., M. Freitas, B., and A. Cazier, J. (2020). A method for mining combined data from in-hive sensors, weather and apiary inspections to forecast the health status of honey bee colonies. Computers and Electronics in Agriculture, 169:105161.

Danieli, P. P., Addeo, N. F., Lazzari, F., Manganello, F., and Bovera, F. (2024). Precision beekeeping systems: State of the art, pros and cons, and their application as tools for advancing the beekeeping sector. Animals, 14(1).

Giannakopoulos, T. (2015). pyaudioanalysis: An open-source python library for audio signal analysis. GitHub repository, [link].

Kanelis, D., Liolios, V., Papadopoulou, F., Rodopoulou, M.-A., Kampelopoulos, D., Siozios, K., and Tananaki, C. (2023). Decoding the behavior of a queenless colony using sound signals. Biology, 12(11).

Lai, L., Suda, N., and Chandra, V. (2018). Cmsis-nn: Efficient neural network kernels for arm cortex-m cpus. arXiv preprint arXiv:1801.06601.

Lu, Y., Hong, W., Fang, Y., Wang, Y., Liu, Z., Wang, H., Lu, C., Xu, B., and Liu, S. (2024). Continuous monitoring the queen loss of honey bee colonies. Biosystems Engineering, 244:67–76.

Otesbelgue, A., Rodrigues, I., dos Santos, C., Gomes, D., and Blochtein, B. (2025). The missing queen: a non-invasive method to identify queenless stingless bee hives. In Apidologie. Springer.

Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., and Duchesnay, E. (2011). scikit-learn: Machine learning in Python.

Pires, C. S. S., Pereira, F. d. M., Lopes, M. T. d. R., Nocelli, R. C. F., Malaspina, O., Pettis, J. S., and Teixeira, E. W. (2016). Enfraquecimento e perda de colônias de abelhas no brasil: há casos de ccd? Pesquisa Agropecuária Brasileira, 51(5):422–442.

Rodrigues, I., Melo, D., and Gomes, D. (2024). Bioacoustic dataset of sudden queen loss in an apis mellifera l. honeybee colony. In Anais do XV Workshop de Computação Aplicada à Gestão do Meio Ambiente e Recursos Naturais, pages 215–218, Porto Alegre, RS, Brasil. SBC.

Rodrigues, I., Melo, D., Silva, D., Rybarczyk, Y., and Gomes, D. (2022). Padrões bioacústicos como identificadores precisos da presença de rainha em colmeias de abelhas melíferas. In Anais do XIII Workshop de Computação Aplicada à Gestão do Meio Ambiente e Recursos Naturais, pages 11–20, Porto Alegre, RS, Brasil. SBC.

Santos, I. R. d., Araújo, F. H. D. d., and Magalhães, D. M. V. (2025). Análise comparativa de modelos de classificação de áudio de colmeias de abelhas em dispositivos portáteis android com onnxruntime. Brazilian Journal of Development, 11(2):e78007.

Schwartzbach, C. (2015). A transformada de fourier e o processamento eletrônico dos sinais.

Shlens, J. (2014). A tutorial on principal component analysis. arXiv preprint arXiv:1404.1100.