FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W2901347941> ?p ?o ?g. }

• W2901347941 endingPage "53" @default.
• W2901347941 startingPage "45" @default.
• W2901347941 abstract "Owing to major technological advances, bioacoustics has become a burgeoning field inecological research worldwide. Autonomous passive acoustic recorders are becoming widelyused to monitor aerial insectivorous bats, and automatic classifiers have emerged to aidresearchers in the daunting task of analyzing the resulting massive acoustic datasets.However, the scarcity of comprehensive reference call libraries still hampers their widerapplication in highly diverse tropical assemblages. Capitalizing on a unique acoustic datasetof more than 650,000 bat call sequences collected over a 3-year period in the BrazilianAmazon, the aims of this study were (a) to assess how pre-identified recordings of free-flyingand hand-released bats could be used to train an automatic classification algorithm (randomforest), and (b) to optimize acoustic analysis protocols by combining automatic classificationwith visual post-validation, whereby we evaluated the proportion of sound files to be postvalidatedfor different thresholds of classification accuracy. Classifiers were trained at speciesor sonotype (group of species with similar calls) level. Random forest models confirmed thereliability of using calls of both free-flying and hand-released bats to train custom-builtautomatic classifiers. To achieve a general classification accuracy of ~85%, random foresthad to be trained with at least 500 pulses per species/sonotype. For seven out of 20 sonotypes,the most abundant in our dataset, we obtained high classification accuracy (>90%). Adoptinga desired accuracy probability threshold of 95% for the random forest classifier, we found thatthe percentage of sound files required for manual post-validation could be reduced by up to75%, a significant saving in terms of workload. Combining automatic classification withmanual ID through fully customizable classifiers implemented in open-source software asdemonstrated here shows great potential to help overcome the acknowledged risks and biasesassociated with the sole reliance on automatic classification." @default.
• W2901347941 created "2018-11-29" @default.
• W2901347941 creator A5004221643 @default.
• W2901347941 creator A5016333383 @default.
• W2901347941 creator A5019065681 @default.
• W2901347941 creator A5024649802 @default.
• W2901347941 creator A5034490743 @default.
• W2901347941 creator A5073639288 @default.
• W2901347941 date "2019-01-01" @default.
• W2901347941 modified "2023-10-17" @default.
• W2901347941 title "Stronger together: Combining automated classifiers with manual post-validation optimizes the workload vs reliability trade-off of species identification in bat acoustic surveys" @default.
• W2901347941 cites W117825165 @default.
• W2901347941 cites W1514601846 @default.
• W2901347941 cites W1597981062 @default.
• W2901347941 cites W1879913591 @default.
• W2901347941 cites W1969962627 @default.
• W2901347941 cites W1973012017 @default.
• W2901347941 cites W1988724590 @default.
• W2901347941 cites W1992325744 @default.
• W2901347941 cites W2005469763 @default.
• W2901347941 cites W2006269021 @default.
• W2901347941 cites W2014562034 @default.
• W2901347941 cites W2024608641 @default.
• W2901347941 cites W2031604783 @default.
• W2901347941 cites W2044275931 @default.
• W2901347941 cites W2048242198 @default.
• W2901347941 cites W2055869330 @default.
• W2901347941 cites W2058731966 @default.
• W2901347941 cites W2063123034 @default.
• W2901347941 cites W2068544015 @default.
• W2901347941 cites W2081199277 @default.
• W2901347941 cites W2082020890 @default.
• W2901347941 cites W2086123829 @default.
• W2901347941 cites W2092956609 @default.
• W2901347941 cites W2097381303 @default.
• W2901347941 cites W2100704846 @default.
• W2901347941 cites W2103118270 @default.
• W2901347941 cites W2106108160 @default.
• W2901347941 cites W2109904102 @default.
• W2901347941 cites W2114829768 @default.
• W2901347941 cites W2115561712 @default.
• W2901347941 cites W2115796660 @default.
• W2901347941 cites W2127657748 @default.
• W2901347941 cites W2129585530 @default.
• W2901347941 cites W2139617295 @default.
• W2901347941 cites W2147243671 @default.
• W2901347941 cites W2150492159 @default.
• W2901347941 cites W2152286298 @default.
• W2901347941 cites W2160746362 @default.
• W2901347941 cites W2162702523 @default.
• W2901347941 cites W2163244483 @default.
• W2901347941 cites W2292336283 @default.
• W2901347941 cites W2337334210 @default.
• W2901347941 cites W2340594420 @default.
• W2901347941 cites W2394413942 @default.
• W2901347941 cites W2496964865 @default.
• W2901347941 cites W2531623272 @default.
• W2901347941 cites W2550419635 @default.
• W2901347941 cites W2589897646 @default.
• W2901347941 cites W2612144927 @default.
• W2901347941 cites W2614388010 @default.
• W2901347941 cites W2615221506 @default.
• W2901347941 cites W2729675707 @default.
• W2901347941 cites W2772345051 @default.
• W2901347941 cites W2783303214 @default.
• W2901347941 cites W2796373134 @default.
• W2901347941 cites W2911964244 @default.
• W2901347941 cites W2029439661 @default.
• W2901347941 doi "https://doi.org/10.1016/j.ecoinf.2018.11.004" @default.
• W2901347941 hasPublicationYear "2019" @default.
• W2901347941 type Work @default.
• W2901347941 sameAs 2901347941 @default.
• W2901347941 citedByCount "32" @default.
• W2901347941 countsByYear W29013479412019 @default.
• W2901347941 countsByYear W29013479412020 @default.
• W2901347941 countsByYear W29013479412021 @default.
• W2901347941 countsByYear W29013479412022 @default.
• W2901347941 countsByYear W29013479412023 @default.
• W2901347941 crossrefType "journal-article" @default.
• W2901347941 hasAuthorship W2901347941A5004221643 @default.
• W2901347941 hasAuthorship W2901347941A5016333383 @default.
• W2901347941 hasAuthorship W2901347941A5019065681 @default.
• W2901347941 hasAuthorship W2901347941A5024649802 @default.
• W2901347941 hasAuthorship W2901347941A5034490743 @default.
• W2901347941 hasAuthorship W2901347941A5073639288 @default.
• W2901347941 hasBestOaLocation W29013479412 @default.
• W2901347941 hasConcept C111919701 @default.
• W2901347941 hasConcept C116834253 @default.
• W2901347941 hasConcept C119857082 @default.
• W2901347941 hasConcept C121332964 @default.
• W2901347941 hasConcept C154945302 @default.
• W2901347941 hasConcept C163258240 @default.
• W2901347941 hasConcept C18903297 @default.
• W2901347941 hasConcept C2778476105 @default.
• W2901347941 hasConcept C41008148 @default.
• W2901347941 hasConcept C43214815 @default.
• W2901347941 hasConcept C62520636 @default.
• W2901347941 hasConcept C86803240 @default.

• next