MFCC-Based Sound Classification of Honey Bees

Autor:	Urszula Libal, Pawel Biernacki
Jazyk:	angličtina
Rok vydání:	2024
Předmět:	internet of things (iot) smart beekeeping pattern recognition signal processing mel-frequency cepstral coefficients Electrical engineering. Electronics. Nuclear engineering TK1-9971 Telecommunication TK5101-6720
Zdroj:	International Journal of Electronics and Telecommunications, Vol vol. 70, Iss No 4 (2024)
Druh dokumentu:	article
ISSN:	2081-8491 2300-1933
DOI:	10.24425/ijet.2024.152069
Popis:	Abstract—Smart beekeeping is a rapidly developing field. Automated detection and classification of honey bees opens many new opportunities for studies on their behavior. In this paper, we focus on distinguishing between two classes of bees: female workers and male drones. The classification is performed on mel-frequency cepstral coefficients obtained for audio recordings of their flights in a close proximity to an entrance to a beehive. We compare the classification accuracy for several classifiers. We investigate how partitioning of the frequency spectrum influences the classification results. The study involves series of experiments performed for different cepstral representations in the form of 5, 10, 15, 20 and 40 mel-frequency cepstral coefficients.
Databáze:	Directory of Open Access Journals
Externí odkaz:	https://doaj.org/article/a72bec960e194843a52fb5c8bafafc50 Zobrazit plný text záznamu View record in DOAJ