Combining two user-friendly machine learning tools increases species detection from acoustic recordings

IF 1 4区 生物学 Q3 ZOOLOGY Canadian Journal of Zoology Pub Date : 2023-11-06 DOI:10.1139/cjz-2023-0154
Cristian Pérez-Granados, Mariano J. Feldman, Marc J. Mazerolle
{"title":"Combining two user-friendly machine learning tools increases species detection from acoustic recordings","authors":"Cristian Pérez-Granados, Mariano J. Feldman, Marc J. Mazerolle","doi":"10.1139/cjz-2023-0154","DOIUrl":null,"url":null,"abstract":"Passive acoustic monitoring usually generates large datasets that require machine learning algorithms to scan sound files, although the complexity of developing machine learning algorithms can be a barrier. We assessed the ability and speed of two user-friendly machine learning tools, Kaleidoscope Pro and BirdNET, for detecting the American toad (Anaxyrus americanus, (Holbrook, 1836)) in sound recordings. We developed a two-step approach combining both tools to maximize species detection while minimizing the time needed for output verification. When considered separately, Kaleidoscope Pro successfully detected the American toad in 85.9% of recordings in the validation dataset, while BirdNET detected the species in 58.4% of recordings. Combining the two tools in the two-step approach increased the detection rate to 93.3%. We applied the two-step approach to a large acoustic dataset (n = 6,194 recordings). We started by scanning the dataset using Kaleidoscope Pro (species detected in 417 recordings), then we used BirdNET on the remaining recordings without confirmed presence. The two-step approach reduced the scanning time, the time needed for output verification, and added 37 additional species detections in 45 minutes. Our findings highlight that combining machine learning tools can improve species detectability while minimizing time and effort.","PeriodicalId":9484,"journal":{"name":"Canadian Journal of Zoology","volume":null,"pages":null},"PeriodicalIF":1.0000,"publicationDate":"2023-11-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Canadian Journal of Zoology","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1139/cjz-2023-0154","RegionNum":4,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ZOOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

Passive acoustic monitoring usually generates large datasets that require machine learning algorithms to scan sound files, although the complexity of developing machine learning algorithms can be a barrier. We assessed the ability and speed of two user-friendly machine learning tools, Kaleidoscope Pro and BirdNET, for detecting the American toad (Anaxyrus americanus, (Holbrook, 1836)) in sound recordings. We developed a two-step approach combining both tools to maximize species detection while minimizing the time needed for output verification. When considered separately, Kaleidoscope Pro successfully detected the American toad in 85.9% of recordings in the validation dataset, while BirdNET detected the species in 58.4% of recordings. Combining the two tools in the two-step approach increased the detection rate to 93.3%. We applied the two-step approach to a large acoustic dataset (n = 6,194 recordings). We started by scanning the dataset using Kaleidoscope Pro (species detected in 417 recordings), then we used BirdNET on the remaining recordings without confirmed presence. The two-step approach reduced the scanning time, the time needed for output verification, and added 37 additional species detections in 45 minutes. Our findings highlight that combining machine learning tools can improve species detectability while minimizing time and effort.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
结合两种用户友好的机器学习工具,增加了从录音中检测物种的能力
被动声学监测通常会生成大型数据集,这需要机器学习算法来扫描声音文件,尽管开发机器学习算法的复杂性可能是一个障碍。我们评估了两种用户友好的机器学习工具Kaleidoscope Pro和BirdNET的能力和速度,用于检测录音中的美洲蟾蜍(Anaxyrus americanus, (Holbrook, 1836))。我们开发了一种结合两种工具的两步方法,以最大限度地提高物种检测,同时最大限度地减少输出验证所需的时间。单独考虑时,Kaleidoscope Pro在验证数据集中成功检测到85.9%的美洲蟾蜍,而BirdNET在58.4%的记录中成功检测到该物种。两步法结合两种工具,检出率达到93.3%。我们将两步方法应用于大型声学数据集(n = 6194录音)。我们首先使用Kaleidoscope Pro扫描数据集(在417个记录中检测到的物种),然后我们使用BirdNET对剩余的未确认存在的记录进行扫描。两步法减少了扫描时间,输出验证所需的时间,并在45分钟内增加了37个额外的物种检测。我们的研究结果强调,结合机器学习工具可以提高物种可探测性,同时最大限度地减少时间和精力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
Canadian Journal of Zoology
Canadian Journal of Zoology 生物-动物学
CiteScore
2.40
自引率
0.00%
发文量
82
审稿时长
3 months
期刊介绍: Published since 1929, the Canadian Journal of Zoology is a monthly journal that reports on primary research contributed by respected international scientists in the broad field of zoology, including behaviour, biochemistry and physiology, developmental biology, ecology, genetics, morphology and ultrastructure, parasitology and pathology, and systematics and evolution. It also invites experts to submit review articles on topics of current interest.
期刊最新文献
Spatiotemporal distribution of the non-indigenous peach blossom jellyfish Craspedacusta sowerbii in British Columbia, Canada Spatiotemporal distribution of the non-indigenous peach blossom jellyfish Craspedacusta sowerbii in British Columbia, Canada Nursing behavior of wild polar bears in the Canadian High Arctic Seasonal dynamics of small mammal populations: resource availability and cold exposure interact to govern abundance Determinants of Multiple Brooding in Barn Swallows (Hirundo rustica) in Atlantic Canada
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1