Acoustic Signal Detection of Search-Phase Echolocation Bat Calls with CNN
Keywords:
Bioindicator, Convolutional Neural Networks, Fourier Transform, STFT, Non-Max Suppression, BatAbstract
Bats are one of the most diverse species on earth. Not only do they provide highly beneficial services to nature such as pollination and pest control, they provide useful insights on the changes occurring to the ecosystem as a result of anthropogenic change. Therefore, bat tracking helps in the conservation of endangered bat species and also to measure trends in biodiversity. Bats play a vital role in our ecosystem, however, they are least studied and marred with myths. Hence it is necessary to study and monitor their population dynamics to get an insight on roost size, mortality rate, migration pattern, breeding season, etc. Insectivorous bats use “Echolocation” to communicate with each other, to find roosts, to detect prey and obstacles while navigating in flight. This paper proposes a Convolution Neural Network (CNN) based pipeline for automatically detecting search-phase calls produced by echolocating bats in noisy, real-world recordings. Audio files are first converted into spectrogram or time-frequency representation and then denoised. The performance results of this model were compared with other existing models on different evaluation metrics like precision, recall, Receiver Operating Characteristic (ROC) curves, and Precision Recall (PR) curves. The model performed better than the existing systems on three different acoustic datasets. Around 500 more bat calls were detected across all 3 datasets compared to that of the existing systems, with a significant increase in recall of the proposed model, as high as 11%. The proposed detection system proved to be capable of detecting echolocation bat calls reliably.
Downloads
References
Fenton MB, Simmons NB. Bats: A World of Science and Mystery. USA: University of Chicago Press, Chicago.
Bates PJJ, Harrison DL. Bats of the Indian Subcontinent. UK: Harrison Zoological Museum; 1997
Korad V, Yardi K, Raut R. Diversity and distribution of bats in the Western Ghats of India. Zoo’s Print Journal. 2007 July 21:22(7):2752-2758. doi: 10.11609/JoTT.ZPJ.1563.2752-8.
Frick WF, Kingston T, Flanders J. A review of the major threats and challenges to global bat conservation. Ann N Y Acad Sci. 2020 Jun;1469(1):5-25. doi: 10.1111/nyas.14045.
Kunz TH, Braun de Torrez E, Bauer D, Lobova T, Fleming TH. Ecosystem services provided by bats. Ann N Y Acad Sci. 2011 Mar;1223:1-38. doi: 10.1111/j.1749-6632.2011.06004.x.
Boyles JG, Sole CL, Cryan PM, McCracken GF. On Estimating the Economic Value of Insectivorous Bats: Prospects and Priorities for Biologists. Bat Evolution, Ecology, and Conservation. Springer, ed. Adams R, Pedersen S, pp. 501–515, New York, 2013.
Danilo R, Christian CV. The use of automated identification of bat echolocation calls in acoustic monitoring: A cautionary note for a sound. Ecological Indicators, 2016 July,66:598-602. doi: 10.1016/j.ecolind.2016.02.036.
Russo D, Salinas-Ramos VB, Cistrone L, Smeraldo S, Bosso L, Ancillotto L. Do We Need to Use Bats as Bioindicators? Biology (Basel). 2021 Jul 21;10(8):693. doi: 10.3390/biology10080693.
Jones G, Jacobs DS, Kunz TH, Willig MR, Racey PA. Carpe noctem: the importance of bats as bioindicators. Endang Species Res. 2009;8:93-115. doi: 10.3354/esr00182.
Santini L, González-Suárez M, Russo D, Gonzalez-Voyer A, von Hardenberg A, Ancillotto L. One strategy does not fit all: determinants of urban adaptation in mammals. Ecology Letters. 2018 Dec 20;22(2):365-376. doi: 10.1111/ele.13199.
Walters CL, Collen A, Lucas T, Mroz K, Sayer CA, Jones KE. Challenges of Using Bioacoustics to Globally Monitor Bats. Bat Evolution, Ecology, and Conservation. Springer, ed. Adams R, Pedersen S, pp. 479–499, New York, 2013. doi: 10.1007/978-1-4614-7397-8_23.
Russo D, Ancillotto L, Jones G. Bats are still not birds in the digital era: echolocation call variation and why it matters for bat species identification. Canadian Journal of Zoology. 2018;96(2):63-78. doi: 10.1139/cjz-2017-0089.
Mac Aodha O, Gibb R, Barlow KE, Browning E, Firman M, Freeman R, Harder B, Kinsey L, Mead GR, Newson SE, Pandourski I, Parsons S, Russ J, Szodoray-Paradi A, Szodoray-Paradi F, Tilova E, Girolami M, Brostow G, Jones KE. Bat detective-Deep learning tools for bat acoustic signal detection. PLoS Comput Biol. 2018 Mar 8;14(3):e1005995. doi: 10.1371/journal.pcbi.1005995.
Roche N, Langton S, Aughney T, Russ JM, Marnell F, Lynn D, Catto C. A car-based monitoring method reveals new information on bat populations and distributions in Ireland. Animal Conservation. 2011 June 21.14(6):642-651. doi: 10.1111/j.1469-1795.2011.00470.x.
Ruiz AT, Equihua J, Martínez S, Robredo E, Palm G, Schwenker F. Detection of Bat Acoustics Signals Using Voice Activity Detection Techniques with Random Forests Classification. Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. Springer, ed. Vera-Rodriguez R, Fierrez J, Morales A, pp. 253-261, Madrid, 2019.
Ruiz AT, Jung K, Tschapka M, Schwenker F, Palm G. Automated identification method for detection and classification of neotropical bats. In 8th International Conference of Pattern Recognition Systems, pp. 1-6, Madrid, 2017.
Schwab E, Pogrebnoj S, Freund M, Flossmann F, Vogl S, Frommolt KH. Automated bat call classification using deep convolutional neural networks. Bioacoustics. 2022 Mar 20:1-6. doi: 10.1080/09524622.2022.2050816.
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.
Hu J, Huang W, Su Y, Liu Y, Xiao P. BatNet++: A Robust Deep Learning-Based Predicting Models for Calls Recognition. In 2020 5th International Conference on Smart Grid and Electrical Automation (ICSGEA), pp. 260-263, 2020.
Nuñez GB, Lemus G, Wolf MM, Rodales AL, González EM, Crisci C. The first artificial intelligence algorithm for identification of bat species in Uruguay. Ecological Informatics. 2018 Jul 1;46:97-102. doi: 10.1016/j.ecoinf.2018.05.005.
Bat Detective - Deep Learning Tools for Bat Acoustic Signal Detection, 2018, [online] Available: http://visual.cs.ucl.ac.uk/pubs/batDetective/
Müller Meinard, Fundamentals of Music Processing: Using python and Jupyter Notebooks, 2nd ed. Springer, 2021.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
