Cargando…

Applicability of VGGish embedding in bee colony monitoring: comparison with MFCC in colony sound classification

BACKGROUND: Bee colony sound is a continuous, low-frequency buzzing sound that varies with the environment or the colony’s behavior and is considered meaningful. Bees use sounds to communicate within the hive, and bee colony sounds investigation can reveal helpful information about the circumstances...

Descripción completa

Detalles Bibliográficos
Autores principales: Di, Nayan, Sharif, Muhammad Zahid, Hu, Zongwen, Xue, Renjie, Yu, Baizhong
Formato: Online Artículo Texto
Lenguaje:English
Publicado: PeerJ Inc. 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9884476/
https://www.ncbi.nlm.nih.gov/pubmed/36721779
http://dx.doi.org/10.7717/peerj.14696
_version_ 1784879725918814208
author Di, Nayan
Sharif, Muhammad Zahid
Hu, Zongwen
Xue, Renjie
Yu, Baizhong
author_facet Di, Nayan
Sharif, Muhammad Zahid
Hu, Zongwen
Xue, Renjie
Yu, Baizhong
author_sort Di, Nayan
collection PubMed
description BACKGROUND: Bee colony sound is a continuous, low-frequency buzzing sound that varies with the environment or the colony’s behavior and is considered meaningful. Bees use sounds to communicate within the hive, and bee colony sounds investigation can reveal helpful information about the circumstances in the colony. Therefore, one crucial step in analyzing bee colony sounds is to extract appropriate acoustic feature. METHODS: This article uses VGGish (a visual geometry group—like audio classification model) embedding and Mel-frequency Cepstral Coefficient (MFCC) generated from three bee colony sound datasets, to train four machine learning algorithms to determine which acoustic feature performs better in bee colony sound recognition. RESULTS: The results showed that VGGish embedding performs better than or on par with MFCC in all three datasets.
format Online
Article
Text
id pubmed-9884476
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher PeerJ Inc.
record_format MEDLINE/PubMed
spelling pubmed-98844762023-01-30 Applicability of VGGish embedding in bee colony monitoring: comparison with MFCC in colony sound classification Di, Nayan Sharif, Muhammad Zahid Hu, Zongwen Xue, Renjie Yu, Baizhong PeerJ Agricultural Science BACKGROUND: Bee colony sound is a continuous, low-frequency buzzing sound that varies with the environment or the colony’s behavior and is considered meaningful. Bees use sounds to communicate within the hive, and bee colony sounds investigation can reveal helpful information about the circumstances in the colony. Therefore, one crucial step in analyzing bee colony sounds is to extract appropriate acoustic feature. METHODS: This article uses VGGish (a visual geometry group—like audio classification model) embedding and Mel-frequency Cepstral Coefficient (MFCC) generated from three bee colony sound datasets, to train four machine learning algorithms to determine which acoustic feature performs better in bee colony sound recognition. RESULTS: The results showed that VGGish embedding performs better than or on par with MFCC in all three datasets. PeerJ Inc. 2023-01-26 /pmc/articles/PMC9884476/ /pubmed/36721779 http://dx.doi.org/10.7717/peerj.14696 Text en ©2023 Di et al. https://creativecommons.org/licenses/by/4.0/This is an open access article distributed under the terms of the Creative Commons Attribution License (https://creativecommons.org/licenses/by/4.0/) , which permits unrestricted use, distribution, reproduction and adaptation in any medium and for any purpose provided that it is properly attributed. For attribution, the original author(s), title, publication source (PeerJ) and either DOI or URL of the article must be cited.
spellingShingle Agricultural Science
Di, Nayan
Sharif, Muhammad Zahid
Hu, Zongwen
Xue, Renjie
Yu, Baizhong
Applicability of VGGish embedding in bee colony monitoring: comparison with MFCC in colony sound classification
title Applicability of VGGish embedding in bee colony monitoring: comparison with MFCC in colony sound classification
title_full Applicability of VGGish embedding in bee colony monitoring: comparison with MFCC in colony sound classification
title_fullStr Applicability of VGGish embedding in bee colony monitoring: comparison with MFCC in colony sound classification
title_full_unstemmed Applicability of VGGish embedding in bee colony monitoring: comparison with MFCC in colony sound classification
title_short Applicability of VGGish embedding in bee colony monitoring: comparison with MFCC in colony sound classification
title_sort applicability of vggish embedding in bee colony monitoring: comparison with mfcc in colony sound classification
topic Agricultural Science
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9884476/
https://www.ncbi.nlm.nih.gov/pubmed/36721779
http://dx.doi.org/10.7717/peerj.14696
work_keys_str_mv AT dinayan applicabilityofvggishembeddinginbeecolonymonitoringcomparisonwithmfccincolonysoundclassification
AT sharifmuhammadzahid applicabilityofvggishembeddinginbeecolonymonitoringcomparisonwithmfccincolonysoundclassification
AT huzongwen applicabilityofvggishembeddinginbeecolonymonitoringcomparisonwithmfccincolonysoundclassification
AT xuerenjie applicabilityofvggishembeddinginbeecolonymonitoringcomparisonwithmfccincolonysoundclassification
AT yubaizhong applicabilityofvggishembeddinginbeecolonymonitoringcomparisonwithmfccincolonysoundclassification