FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3044430114> ?p ?o ?g. }

• W3044430114 endingPage "e0236092" @default.
• W3044430114 startingPage "e0236092" @default.
• W3044430114 abstract "Automated monitoring of the movements and behaviour of animals is a valuable research tool. Recently, machine learning tools were applied to many species to classify units of behaviour. For the monitoring of wild species, collecting enough data for training models might be problematic, thus we examine how machine learning models trained on one species can be applied to another closely related species with similar behavioural conformation. We contrast two ways to calculate accuracies, termed here as overall and threshold accuracy, because the field has yet to define solid standards for reporting and measuring classification performances. We measure 21 dogs and 7 wolves, and find that overall accuracies are between 51 and 60% for classifying 8 behaviours (lay, sit, stand, walk, trot, run, eat, drink) when training and testing data are from the same species and between 41 and 51% when training and testing is cross-species. We show that using data from dogs to predict the behaviour of wolves is feasible. We also show that optimising the model for overall accuracy leads to similar overall and threshold accuracies, while optimizing for threshold accuracy leads to threshold accuracies well above 80%, but yielding very low overall accuracies, often below the chance level. Moreover, we show that the most common method for dividing the data between training and testing data (random selection of test data) overestimates the accuracy of models when applied to data of new specimens. Consequently, we argue that for the most common goals of animal behaviour recognition overall accuracy should be the preferred metric. Considering, that often the goal is to collect movement data without other methods of observation, we argue that training data and testing data should be divided by individual and not randomly." @default.
• W3044430114 created "2020-07-29" @default.
• W3044430114 creator A5009416463 @default.
• W3044430114 creator A5031822515 @default.
• W3044430114 creator A5045281783 @default.
• W3044430114 creator A5050709276 @default.
• W3044430114 creator A5073574310 @default.
• W3044430114 creator A5073799617 @default.
• W3044430114 creator A5075007001 @default.
• W3044430114 date "2020-07-20" @default.
• W3044430114 modified "2023-10-03" @default.
• W3044430114 title "Challenges of machine learning model validation using correlated behaviour data: Evaluation of cross-validation strategies and accuracy measures" @default.
• W3044430114 cites W1484249796 @default.
• W3044430114 cites W1975520369 @default.
• W3044430114 cites W1991501972 @default.
• W3044430114 cites W2006449752 @default.
• W3044430114 cites W2019147313 @default.
• W3044430114 cites W2024341973 @default.
• W3044430114 cites W2029538739 @default.
• W3044430114 cites W2047005779 @default.
• W3044430114 cites W2050090101 @default.
• W3044430114 cites W2053139129 @default.
• W3044430114 cites W2056454832 @default.
• W3044430114 cites W2061733446 @default.
• W3044430114 cites W2069207129 @default.
• W3044430114 cites W2078464065 @default.
• W3044430114 cites W2078948852 @default.
• W3044430114 cites W2084341220 @default.
• W3044430114 cites W2107687774 @default.
• W3044430114 cites W2108590926 @default.
• W3044430114 cites W2108916750 @default.
• W3044430114 cites W2119709271 @default.
• W3044430114 cites W2122303322 @default.
• W3044430114 cites W2152779085 @default.
• W3044430114 cites W2162518488 @default.
• W3044430114 cites W2162989219 @default.
• W3044430114 cites W2215065413 @default.
• W3044430114 cites W2305408943 @default.
• W3044430114 cites W2519036095 @default.
• W3044430114 cites W2605824147 @default.
• W3044430114 cites W2746245696 @default.
• W3044430114 cites W2777206827 @default.
• W3044430114 cites W2791893104 @default.
• W3044430114 cites W2906072722 @default.
• W3044430114 cites W2908432956 @default.
• W3044430114 cites W2917105194 @default.
• W3044430114 cites W2954385753 @default.
• W3044430114 cites W3105512282 @default.
• W3044430114 doi "https://doi.org/10.1371/journal.pone.0236092" @default.
• W3044430114 hasPubMedCentralId "https://www.ncbi.nlm.nih.gov/pmc/articles/7371169" @default.
• W3044430114 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/32687528" @default.
• W3044430114 hasPublicationYear "2020" @default.
• W3044430114 type Work @default.
• W3044430114 sameAs 3044430114 @default.
• W3044430114 citedByCount "25" @default.
• W3044430114 countsByYear W30444301142020 @default.
• W3044430114 countsByYear W30444301142021 @default.
• W3044430114 countsByYear W30444301142022 @default.
• W3044430114 countsByYear W30444301142023 @default.
• W3044430114 crossrefType "journal-article" @default.
• W3044430114 hasAuthorship W3044430114A5009416463 @default.
• W3044430114 hasAuthorship W3044430114A5031822515 @default.
• W3044430114 hasAuthorship W3044430114A5045281783 @default.
• W3044430114 hasAuthorship W3044430114A5050709276 @default.
• W3044430114 hasAuthorship W3044430114A5073574310 @default.
• W3044430114 hasAuthorship W3044430114A5073799617 @default.
• W3044430114 hasAuthorship W3044430114A5075007001 @default.
• W3044430114 hasBestOaLocation W30444301141 @default.
• W3044430114 hasConcept C119857082 @default.
• W3044430114 hasConcept C124101348 @default.
• W3044430114 hasConcept C154945302 @default.
• W3044430114 hasConcept C162324750 @default.
• W3044430114 hasConcept C169258074 @default.
• W3044430114 hasConcept C176217482 @default.
• W3044430114 hasConcept C202444582 @default.
• W3044430114 hasConcept C21547014 @default.
• W3044430114 hasConcept C27181475 @default.
• W3044430114 hasConcept C2776502983 @default.
• W3044430114 hasConcept C33923547 @default.
• W3044430114 hasConcept C41008148 @default.
• W3044430114 hasConcept C45804977 @default.
• W3044430114 hasConcept C51632099 @default.
• W3044430114 hasConcept C9652623 @default.
• W3044430114 hasConceptScore W3044430114C119857082 @default.
• W3044430114 hasConceptScore W3044430114C124101348 @default.
• W3044430114 hasConceptScore W3044430114C154945302 @default.
• W3044430114 hasConceptScore W3044430114C162324750 @default.
• W3044430114 hasConceptScore W3044430114C169258074 @default.
• W3044430114 hasConceptScore W3044430114C176217482 @default.
• W3044430114 hasConceptScore W3044430114C202444582 @default.
• W3044430114 hasConceptScore W3044430114C21547014 @default.
• W3044430114 hasConceptScore W3044430114C27181475 @default.
• W3044430114 hasConceptScore W3044430114C2776502983 @default.
• W3044430114 hasConceptScore W3044430114C33923547 @default.
• W3044430114 hasConceptScore W3044430114C41008148 @default.
• W3044430114 hasConceptScore W3044430114C45804977 @default.
• W3044430114 hasConceptScore W3044430114C51632099 @default.
• W3044430114 hasConceptScore W3044430114C9652623 @default.

• next