FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313591142> ?p ?o ?g. }

• W4313591142 endingPage "401" @default.
• W4313591142 startingPage "387" @default.
• W4313591142 abstract "Abstract Complex bulk samples of insects from biodiversity surveys present a challenge for taxonomic identification, which could be overcome by high‐throughput imaging combined with machine learning for rapid classification of specimens. These procedures require that taxonomic labels from an existing source data set are used for model training and prediction of an unknown target sample. However, such transfer learning may be problematic for the study of new samples not previously encountered in an image set, for example, from unexplored ecosystems, and require methods of domain adaptation that reduce the differences in the feature distribution of the source and target domains (training and test sets). We assessed the efficiency of domain adaptation for family‐level classification of bulk samples of Coleoptera, as a critical first step in the characterization of biodiversity samples. Neural network models trained with images from a global database of Coleoptera were applied to a biodiversity sample from understudied forests in Cyprus as the target. Within‐dataset classification accuracy reached 98% and depended on the number and quality of training images, and on dataset complexity. The accuracy of between‐datasets predictions (across disparate source–target pairs that do not share any species or genera) was at most 82% and depended greatly on the standardization of the imaging procedure. An algorithm for domain adaptation, domain adversarial training of neural networks (DANN), significantly improved the prediction performance of models trained by non‐standardized, low‐quality images. Our findings demonstrate that existing databases can be used to train models and successfully classify images from unexplored biota, but the imaging conditions and classification algorithms need careful consideration." @default.
• W4313591142 created "2023-01-06" @default.
• W4313591142 creator A5000391318 @default.
• W4313591142 creator A5030762176 @default.
• W4313591142 creator A5061841033 @default.
• W4313591142 creator A5067799916 @default.
• W4313591142 creator A5086273259 @default.
• W4313591142 date "2023-01-04" @default.
• W4313591142 modified "2023-09-30" @default.
• W4313591142 title "Image‐based taxonomic classification of bulk insect biodiversity samples using deep learning and domain adaptation" @default.
• W4313591142 cites W1474287712 @default.
• W4313591142 cites W2031342017 @default.
• W4313591142 cites W2104309792 @default.
• W4313591142 cites W2114000877 @default.
• W4313591142 cites W2139183630 @default.
• W4313591142 cites W2145836476 @default.
• W4313591142 cites W2165698076 @default.
• W4313591142 cites W2330712633 @default.
• W4313591142 cites W2757251151 @default.
• W4313591142 cites W2806052816 @default.
• W4313591142 cites W2810289271 @default.
• W4313591142 cites W2907313906 @default.
• W4313591142 cites W2919115771 @default.
• W4313591142 cites W2919681993 @default.
• W4313591142 cites W2952113774 @default.
• W4313591142 cites W2979509742 @default.
• W4313591142 cites W2982381843 @default.
• W4313591142 cites W2997849610 @default.
• W4313591142 cites W3034230713 @default.
• W4313591142 cites W3042182083 @default.
• W4313591142 cites W3094439952 @default.
• W4313591142 cites W3097816393 @default.
• W4313591142 cites W3118571930 @default.
• W4313591142 cites W3139096123 @default.
• W4313591142 cites W3169935126 @default.
• W4313591142 cites W3170533949 @default.
• W4313591142 cites W3197348004 @default.
• W4313591142 cites W3201083518 @default.
• W4313591142 cites W3211532803 @default.
• W4313591142 cites W3215820471 @default.
• W4313591142 cites W4200111683 @default.
• W4313591142 cites W4213328656 @default.
• W4313591142 cites W4220863378 @default.
• W4313591142 cites W4224240815 @default.
• W4313591142 doi "https://doi.org/10.1111/syen.12583" @default.
• W4313591142 hasPublicationYear "2023" @default.
• W4313591142 type Work @default.
• W4313591142 citedByCount "1" @default.
• W4313591142 countsByYear W43135911422023 @default.
• W4313591142 crossrefType "journal-article" @default.
• W4313591142 hasAuthorship W4313591142A5000391318 @default.
• W4313591142 hasAuthorship W4313591142A5030762176 @default.
• W4313591142 hasAuthorship W4313591142A5061841033 @default.
• W4313591142 hasAuthorship W4313591142A5067799916 @default.
• W4313591142 hasAuthorship W4313591142A5086273259 @default.
• W4313591142 hasBestOaLocation W43135911421 @default.
• W4313591142 hasConcept C115961682 @default.
• W4313591142 hasConcept C116834253 @default.
• W4313591142 hasConcept C119857082 @default.
• W4313591142 hasConcept C130217890 @default.
• W4313591142 hasConcept C134306372 @default.
• W4313591142 hasConcept C138885662 @default.
• W4313591142 hasConcept C139807058 @default.
• W4313591142 hasConcept C150899416 @default.
• W4313591142 hasConcept C153180895 @default.
• W4313591142 hasConcept C154945302 @default.
• W4313591142 hasConcept C169760540 @default.
• W4313591142 hasConcept C177264268 @default.
• W4313591142 hasConcept C185592680 @default.
• W4313591142 hasConcept C18903297 @default.
• W4313591142 hasConcept C198531522 @default.
• W4313591142 hasConcept C199360897 @default.
• W4313591142 hasConcept C2776401178 @default.
• W4313591142 hasConcept C2776434776 @default.
• W4313591142 hasConcept C33923547 @default.
• W4313591142 hasConcept C36503486 @default.
• W4313591142 hasConcept C41008148 @default.
• W4313591142 hasConcept C41895202 @default.
• W4313591142 hasConcept C43617362 @default.
• W4313591142 hasConcept C50644808 @default.
• W4313591142 hasConcept C75294576 @default.
• W4313591142 hasConcept C86803240 @default.
• W4313591142 hasConcept C95623464 @default.
• W4313591142 hasConceptScore W4313591142C115961682 @default.
• W4313591142 hasConceptScore W4313591142C116834253 @default.
• W4313591142 hasConceptScore W4313591142C119857082 @default.
• W4313591142 hasConceptScore W4313591142C130217890 @default.
• W4313591142 hasConceptScore W4313591142C134306372 @default.
• W4313591142 hasConceptScore W4313591142C138885662 @default.
• W4313591142 hasConceptScore W4313591142C139807058 @default.
• W4313591142 hasConceptScore W4313591142C150899416 @default.
• W4313591142 hasConceptScore W4313591142C153180895 @default.
• W4313591142 hasConceptScore W4313591142C154945302 @default.
• W4313591142 hasConceptScore W4313591142C169760540 @default.
• W4313591142 hasConceptScore W4313591142C177264268 @default.
• W4313591142 hasConceptScore W4313591142C185592680 @default.
• W4313591142 hasConceptScore W4313591142C18903297 @default.
• W4313591142 hasConceptScore W4313591142C198531522 @default.

• next