Matches in SemOpenAlex for { <https://semopenalex.org/work/W3009913006> ?p ?o ?g. }
- W3009913006 endingPage "47246" @default.
- W3009913006 startingPage "47232" @default.
- W3009913006 abstract "Many research fields are now faced with huge volumes of data automatically generated by specialised equipment. Astronomy is a discipline that deals with large collections of images difficult to handle by experts alone. As a consequence, astronomers have been relying on the power of the crowds, as a form of citizen science, for the classification of galaxy images by amateur people. However, the new generation of telescopes that will produce images at a higher rate highlights the limitations of this approach, and the use of machine learning methods for automatic classification is considered essential. The goal of this paper is to shed light on the automated classification of galaxy images exploring two distinct machine learning strategies. First, following the classical approach consisting of feature extraction together with a classifier, we compare the state-of-the-art feature extractor for this problem, the WND-CHARM, with our proposal based on autoencoders for feature extraction on galaxy images. We then compare these results with an end-to-end classification using convolutional neural networks. To better leverage the available citizen science data, we also investigate a pre-training scheme that exploits both amateur- and expert-labelled data. Our experiments reveal that autoencoders greatly speed up feature extraction in comparison with WND-CHARM and both classification strategies, either using convolutional neural networks or feature extraction, reach comparable accuracy. The use of pre-training in convolutional neural networks, however, has allowed us to provide even better results." @default.
- W3009913006 created "2020-03-13" @default.
- W3009913006 creator A5000220725 @default.
- W3009913006 creator A5024981509 @default.
- W3009913006 creator A5075541426 @default.
- W3009913006 creator A5091177679 @default.
- W3009913006 date "2020-01-01" @default.
- W3009913006 modified "2023-10-04" @default.
- W3009913006 title "Galaxy Image Classification Based on Citizen Science Data: A Comparative Study" @default.
- W3009913006 cites W1498436455 @default.
- W3009913006 cites W1587746149 @default.
- W3009913006 cites W1864141944 @default.
- W3009913006 cites W1924655545 @default.
- W3009913006 cites W1971491685 @default.
- W3009913006 cites W1972552638 @default.
- W3009913006 cites W1994616650 @default.
- W3009913006 cites W2013991942 @default.
- W3009913006 cites W2023037133 @default.
- W3009913006 cites W2028070629 @default.
- W3009913006 cites W2044738244 @default.
- W3009913006 cites W2056916542 @default.
- W3009913006 cites W2058379217 @default.
- W3009913006 cites W2089883218 @default.
- W3009913006 cites W2097117768 @default.
- W3009913006 cites W2103186798 @default.
- W3009913006 cites W2105802267 @default.
- W3009913006 cites W2108598243 @default.
- W3009913006 cites W2112193291 @default.
- W3009913006 cites W2112796928 @default.
- W3009913006 cites W2113665876 @default.
- W3009913006 cites W2119387367 @default.
- W3009913006 cites W2119936234 @default.
- W3009913006 cites W2122111042 @default.
- W3009913006 cites W2130164698 @default.
- W3009913006 cites W2135375759 @default.
- W3009913006 cites W2139212933 @default.
- W3009913006 cites W2142827986 @default.
- W3009913006 cites W2165879419 @default.
- W3009913006 cites W2166658986 @default.
- W3009913006 cites W2194775991 @default.
- W3009913006 cites W2248723555 @default.
- W3009913006 cites W2295675274 @default.
- W3009913006 cites W2529128248 @default.
- W3009913006 cites W2549139847 @default.
- W3009913006 cites W2622826443 @default.
- W3009913006 cites W2625817666 @default.
- W3009913006 cites W2745075853 @default.
- W3009913006 cites W2800680069 @default.
- W3009913006 cites W2804191040 @default.
- W3009913006 cites W2883005809 @default.
- W3009913006 cites W2884821113 @default.
- W3009913006 cites W2890060745 @default.
- W3009913006 cites W2890160131 @default.
- W3009913006 cites W2904989010 @default.
- W3009913006 cites W2908671501 @default.
- W3009913006 cites W2911964244 @default.
- W3009913006 cites W2913507157 @default.
- W3009913006 cites W2917393555 @default.
- W3009913006 cites W2921711398 @default.
- W3009913006 cites W2962949934 @default.
- W3009913006 cites W2963375465 @default.
- W3009913006 cites W2964300371 @default.
- W3009913006 cites W2983459436 @default.
- W3009913006 cites W3099775912 @default.
- W3009913006 cites W3100901804 @default.
- W3009913006 cites W3102094077 @default.
- W3009913006 cites W3102260122 @default.
- W3009913006 cites W3104062568 @default.
- W3009913006 cites W3121912651 @default.
- W3009913006 cites W4231109964 @default.
- W3009913006 cites W4247359480 @default.
- W3009913006 doi "https://doi.org/10.1109/access.2020.2978804" @default.
- W3009913006 hasPublicationYear "2020" @default.
- W3009913006 type Work @default.
- W3009913006 sameAs 3009913006 @default.
- W3009913006 citedByCount "14" @default.
- W3009913006 countsByYear W30099130062020 @default.
- W3009913006 countsByYear W30099130062021 @default.
- W3009913006 countsByYear W30099130062022 @default.
- W3009913006 countsByYear W30099130062023 @default.
- W3009913006 crossrefType "journal-article" @default.
- W3009913006 hasAuthorship W3009913006A5000220725 @default.
- W3009913006 hasAuthorship W3009913006A5024981509 @default.
- W3009913006 hasAuthorship W3009913006A5075541426 @default.
- W3009913006 hasAuthorship W3009913006A5091177679 @default.
- W3009913006 hasBestOaLocation W30099130061 @default.
- W3009913006 hasConcept C115961682 @default.
- W3009913006 hasConcept C117978034 @default.
- W3009913006 hasConcept C119857082 @default.
- W3009913006 hasConcept C127413603 @default.
- W3009913006 hasConcept C153083717 @default.
- W3009913006 hasConcept C153180895 @default.
- W3009913006 hasConcept C154945302 @default.
- W3009913006 hasConcept C165696696 @default.
- W3009913006 hasConcept C17744445 @default.
- W3009913006 hasConcept C199539241 @default.
- W3009913006 hasConcept C21880701 @default.
- W3009913006 hasConcept C2778044066 @default.