干旱区生态环境知识资源中心(Arid): Statistical learning mitigation of false positives from template-detected data in automated acoustic wildlife monitoring

Arid

DOI	10.1080/09524622.2019.1605309
	Statistical learning mitigation of false positives from template-detected data in automated acoustic wildlife monitoring
	Balantic, Cathleen M.1; Donovan, Therese M.2
通讯作者	Balantic, Cathleen M.
来源期刊	BIOACOUSTICS-THE INTERNATIONAL JOURNAL OF ANIMAL SOUND AND ITS RECORDING
ISSN	0952-4622
EISSN	2165-0586
出版年	2020
卷号	29 期号:3 页码:296-321
英文摘要	Audio sampling of the environment can provide long-term, landscape-scale presence-absence data to model populations of sound-producing wildlife. Automated detection systems allow researchers to avoid manually searching through large volumes of recordings, but often produce unacceptable false positive rates. We developed methods that allow researchers to improve template-based automated detection using a suite of statistical learning algorithms when false positive rates are problematic. To test our method, we acquired 668 hours of recordings in the Sonoran Desert, California USA between March 2016 and May 2017, and created spectrogram cross-correlation templates for three target avian species. We trained and tested five classification algorithms and four performance-weighted ensemble classifier methods on target signals and false alarms from March 2016, and then selected high-performing ensemble classifiers from the train/test phase to predict the class of new detections thereafter. For three target species, our ensemble classifiers were able to identify 98%, 81%, and 100% of false alarms compared with the baseline template detection system, and comparative positive predictive values improved from 6% to 69%, 87% to 95%, and 2% to 77%. We show that statistical learning approaches can be implemented to mitigate false detections acquired via template-based automated detection in automated acoustic wildlife monitoring.
英文关键词	Automated acoustic monitoring bioacoustics false positives machine learning species identification statistical learning
类型	Article
语种	英语
国家	USA
开放获取类型	hybrid
收录类别	SCI-E
WOS记录号	WOS:000470380800001
WOS关键词	SPECIES OCCURRENCE ; OCCUPANCY MODELS ; FRAMEWORK
WOS类目	Zoology
WOS研究方向	Zoology
来源机构	United States Geological Survey
资源类型	期刊论文
条目标识符	http://119.78.100.177/qdio/handle/2XILL650/214589
作者单位	1.Univ Vermont, Vermont Cooperat Fish & Wildlife Res Unit, Burlington, VT 05405 USA; 2.Univ Vermont, Rubenstein Sch Environm & Nat Resources, Vermont Cooperat Fish & Wildlife Res Unit, US Geol Survey, Burlington, VT USA
推荐引用方式 GB/T 7714	Balantic, Cathleen M.,Donovan, Therese M.. Statistical learning mitigation of false positives from template-detected data in automated acoustic wildlife monitoring[J]. United States Geological Survey,2020,29(3):296-321.
APA	Balantic, Cathleen M.,&Donovan, Therese M..(2020).Statistical learning mitigation of false positives from template-detected data in automated acoustic wildlife monitoring.BIOACOUSTICS-THE INTERNATIONAL JOURNAL OF ANIMAL SOUND AND ITS RECORDING,29(3),296-321.
MLA	Balantic, Cathleen M.,et al."Statistical learning mitigation of false positives from template-detected data in automated acoustic wildlife monitoring".BIOACOUSTICS-THE INTERNATIONAL JOURNAL OF ANIMAL SOUND AND ITS RECORDING 29.3(2020):296-321.