Abstract
As bats are an important indicator for the health of their habitat, projects in multiple countries monitor bat populations by collecting audio recordings of bat calls. Analysing these recordings is however a tedious task and there is a need for systems that accurately and efficiently detect and classify bat calls. While earlier studies focused on detection and classification separately, in this paper we propose a first approach that combines these two tasks. Moreover, we aim to build a multi-label classifier that is able to detect if multiple bat species are present in the same audio recording. One of the challenges we face is that the available data focuses either on detection or single-label classification, but not on the combined task of detection and multi-label classification. We propose to address this by a data augmentation approach, and demonstrate that the resulting approach achieves the objectives of being accurate and efficient.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Armitage, D.W., Ober, H.K.: A comparison of supervised learning techniques in the classification of bat echolocation calls. Eco. Inform. 5, 465–473 (2010)
Barataud, M.: Acoustic ecology of European bats. Species Identification and Studies of Their Habitats and Foraging Behaviour. Biotope Editions (2015)
Bergstra, J., Yamins, D., Cox, D.: Making a science of model search: Hyperparameter optimization in hundreds of dimensions for vision architectures. In: Proceedings of the 30th International Conference on Machine Learning, pp. 115–123 (2013)
Border, J.A., Newson, S.E., White, D.C., Gillings, S.: Predicting the likely impact of urbanisation on bat populations using citizen science data, a case study for Norfolk, UK. Landsc. Urban Plan. 162, 44–55 (2017). https://doi.org/10.1016/j.landurbplan.2017.02.005
Chen, X., Zhao, J., Chen, Y.H., Zhou, W., Hughes, A.C.: Automatic standardized processing and identification of tropical bat calls using deep learning approaches. Biol. Conserv. 241 (2020). https://doi.org/10.1016/j.biocon.2019.108269
Fan, R.E., Lin, C.J.: A study on threshold selection for multi-label classification (2007)
He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 770–778 (2016). https://doi.org/10.1109/CVPR.2016.90
Jones, G., Jacobs, D., Kunz, T., Racey, P.: Carpe noctem: the importance of bats as bioindicators. Endanger. Spec. Res. 8, 93–115 (2009). https://doi.org/10.3354/esr00182
Mac Aodha, O., et al.: Bat detective - deep learning tools for bat acoustic signal detection. PLOS Comput. Biol. (2018). https://doi.org/10.1371/journal.pcbi.1005995
Runkel, V., Gerding, G., Marckmann, U.: The Handbook of Acoustic Bat Detection. Pelagic Publishing (2021). https://doi.org/10.53061/XDDW7329
Rydell, J., Nyman, S., Eklöf, J., Jones, G., Russo, D.: Testing the performances of automated identification of bat echolocation calls: a request for prudence. Ecol. Ind. 78, 416–420 (2017). https://doi.org/10.1016/j.ecolind.2017.03.023
Schwab, E., Pogrebnoj, S., Freund, M., Flossmann, F., Vogl, S., Frommolt, K.H.: Automated bat call classification using deep convolutional neural networks (2021)
Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)
Tabak, M., Murray, K., Lombardi, J., Bay, K.: Automated classification of bat echolocation call recordings with artificial intelligence (2021). https://doi.org/10.1101/2021.06.23.449619
Voigt, C.C., Kingston, T. (eds.): Bats in the Anthropocene: Conservation of Bats in a Changing World. Springer, Cham (2016). https://doi.org/10.1007/978-3-319-25220-9
Zhang, M.-L., Li, Y.-K., Liu, X.-Y., Geng, X.: Binary relevance for multi-label learning: an overview. Front. Comp. Sci. 12, 191–202 (2018). https://doi.org/10.1007/s11704-017-7031-7
Zualkernan, I., Judas, J., Mahbub, T., Bhagwagar, A., Chand, P.: A tiny CNN architecture for identifying bat species from echolocation calls. In: 2020 IEEE/ITU International Conference on Artificial Intelligence for Good (AI4G), pp. 81–86 (2020). https://doi.org/10.1109/AI4G50087.2020.9311084
Acknowledgements
This work was supported by Service Public de Wallonie Recherche under grant n\(^\circ \)2010235 - ARIAC by DIGITALWALLONIA4.AI.
We would like to express our gratitude to Natagora and the Plecotus team for the large amount of labelled bat call recordings they shared with us. We would also like to thank Bat detective for the data they have made available and their detection tool, used as starting point in this work. We thank Olivier Bonaventure for joining discussions on this project.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Dierckx, L., Beauvois, M., Nijssen, S. (2022). Detection and Multi-label Classification of Bats. In: Bouadi, T., Fromont, E., Hüllermeier, E. (eds) Advances in Intelligent Data Analysis XX. IDA 2022. Lecture Notes in Computer Science, vol 13205. Springer, Cham. https://doi.org/10.1007/978-3-031-01333-1_5
Download citation
DOI: https://doi.org/10.1007/978-3-031-01333-1_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-01332-4
Online ISBN: 978-3-031-01333-1
eBook Packages: Computer ScienceComputer Science (R0)