Welcome to the InfoSci Platform
Behavior Classification of Egyptian Fruit Bat (Rousettus aegyptiacus) From Calls With Deep Learning

Behavior Classification of Egyptian Fruit Bat (Rousettus aegyptiacus) From Calls With Deep Learning

Batuhan Yılmaz, Melih Sen, Engin Masazade, Vedat Beskardes
Copyright: © 2022 |Pages: 39
ISBN13: 9781799886860|ISBN10: 1799886867|EISBN13: 9781799886877
DOI: 10.4018/978-1-7998-8686-0.ch004
Cite Chapter Cite Chapter

MLA

Yılmaz, Batuhan, et al. "Behavior Classification of Egyptian Fruit Bat (Rousettus aegyptiacus) From Calls With Deep Learning." Handbook of Research on New Investigations in Artificial Life, AI, and Machine Learning, edited by Maki K. Habib, IGI Global, 2022, pp. 60-98. https://doi.org/10.4018/978-1-7998-8686-0.ch004

APA

Yılmaz, B., Sen, M., Masazade, E., & Beskardes, V. (2022). Behavior Classification of Egyptian Fruit Bat (Rousettus aegyptiacus) From Calls With Deep Learning. In M. Habib (Ed.), Handbook of Research on New Investigations in Artificial Life, AI, and Machine Learning (pp. 60-98). IGI Global. https://doi.org/10.4018/978-1-7998-8686-0.ch004

Chicago

Yılmaz, Batuhan, et al. "Behavior Classification of Egyptian Fruit Bat (Rousettus aegyptiacus) From Calls With Deep Learning." In Handbook of Research on New Investigations in Artificial Life, AI, and Machine Learning, edited by Maki K. Habib, 60-98. Hershey, PA: IGI Global, 2022. https://doi.org/10.4018/978-1-7998-8686-0.ch004

Export Reference

Mendeley
Favorite

Abstract

Sensing the environment with passive acoustic sensors has been used as a very useful tool to monitor and quantify the status and changes on biodiversity. In this chapter, the authors aim to classify the social calls (biting, feeding, fighting, isolation, mating protest, and sleeping) of a certain bat species, Egyptian fruit bat, which lives in colonies with thousands of others. Therefore, classification of their calls not only helps us to understand the population dynamics but also helps us to offer distinct environmental management procedures. In this work, the authors use the database previously presented in Prat et al. and present the social call classification results under both classical machine learning techniques and a convolutional neural network (CNN). The numerical results show that CNN improves the classification performance up to 20% as compared to the traditional machine learning approaches when all the call classes are considered. It has also been shown that the classes of aggressive calls, which can sound quite close to each other, can be distinguished with CNN.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.