Matches in SemOpenAlex for { <https://semopenalex.org/work/W3044203926> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W3044203926 abstract "In several application areas, such as medical diagnosis, spam filtering, fraud detection, and seismic data analysis, it is very usual to find relevant classification tasks where some class occurrences are rare. This is the so called class imbalance problem, which is a challenge in machine learning. In this work, we propose the SeismoFlow a flow-based generative model to create synthetic samples, aiming to address the class imbalance. Inspired by the Glow model, it uses interpolation on the learned latent space to produce synthetic samples for one rare class. We apply our approach to the development of a seismogram signal quality classifier. We introduce a dataset composed of5.223seismograms that are distributed between the good, medium, and bad classes and with their respective frequencies of 66.68%,31.54%, and 1.76%. Our methodology is evaluated on a stratified 10-fold cross-validation setting, using the Miniceptionmodel as a baseline, and assessing the effects of adding the generated samples on the training set of each iteration. In our experiments, we achieve an improvement of 13.9% on the rare class F1-score, while not hurting the metric value for the other classes and thus observing the overall accuracy improvement. Our empirical findings indicate that our method can generate high-quality synthetic seismograms with realistic looking and sufficient plurality to help the Miniception model to overcome the class imbalance problem. We believe that our results are a step forward in solving both the task of seismogram signal quality classification and class imbalance." @default.
- W3044203926 created "2020-07-29" @default.
- W3044203926 creator A5084466158 @default.
- W3044203926 creator A5085717651 @default.
- W3044203926 date "2020-07-23" @default.
- W3044203926 modified "2023-09-27" @default.
- W3044203926 title "SeismoGlow -- Data augmentation for the class imbalance problem" @default.
- W3044203926 cites W1680392829 @default.
- W3044203926 cites W1810943226 @default.
- W3044203926 cites W1866230956 @default.
- W3044203926 cites W189596042 @default.
- W3044203926 cites W1906598733 @default.
- W3044203926 cites W1959608418 @default.
- W3044203926 cites W2064675550 @default.
- W3044203926 cites W2097039814 @default.
- W3044203926 cites W2104167780 @default.
- W3044203926 cites W2107152312 @default.
- W3044203926 cites W2119717200 @default.
- W3044203926 cites W2130447687 @default.
- W3044203926 cites W2135181320 @default.
- W3044203926 cites W2150218618 @default.
- W3044203926 cites W2267126114 @default.
- W3044203926 cites W2409550820 @default.
- W3044203926 cites W2423557781 @default.
- W3044203926 cites W2519091744 @default.
- W3044203926 cites W2556783092 @default.
- W3044203926 cites W2592505114 @default.
- W3044203926 cites W2626778328 @default.
- W3044203926 cites W2766527293 @default.
- W3044203926 cites W2949117887 @default.
- W3044203926 cites W2951682695 @default.
- W3044203926 cites W2962897886 @default.
- W3044203926 cites W2963090522 @default.
- W3044203926 cites W2963139417 @default.
- W3044203926 cites W2963275229 @default.
- W3044203926 cites W2963716836 @default.
- W3044203926 cites W2963919714 @default.
- W3044203926 cites W2964020555 @default.
- W3044203926 cites W2964050365 @default.
- W3044203926 cites W2964121744 @default.
- W3044203926 hasPublicationYear "2020" @default.
- W3044203926 type Work @default.
- W3044203926 sameAs 3044203926 @default.
- W3044203926 citedByCount "0" @default.
- W3044203926 crossrefType "posted-content" @default.
- W3044203926 hasAuthorship W3044203926A5084466158 @default.
- W3044203926 hasAuthorship W3044203926A5085717651 @default.
- W3044203926 hasConcept C11413529 @default.
- W3044203926 hasConcept C119857082 @default.
- W3044203926 hasConcept C124101348 @default.
- W3044203926 hasConcept C153180895 @default.
- W3044203926 hasConcept C154945302 @default.
- W3044203926 hasConcept C160920958 @default.
- W3044203926 hasConcept C2777212361 @default.
- W3044203926 hasConcept C41008148 @default.
- W3044203926 hasConcept C95623464 @default.
- W3044203926 hasConceptScore W3044203926C11413529 @default.
- W3044203926 hasConceptScore W3044203926C119857082 @default.
- W3044203926 hasConceptScore W3044203926C124101348 @default.
- W3044203926 hasConceptScore W3044203926C153180895 @default.
- W3044203926 hasConceptScore W3044203926C154945302 @default.
- W3044203926 hasConceptScore W3044203926C160920958 @default.
- W3044203926 hasConceptScore W3044203926C2777212361 @default.
- W3044203926 hasConceptScore W3044203926C41008148 @default.
- W3044203926 hasConceptScore W3044203926C95623464 @default.
- W3044203926 hasLocation W30442039261 @default.
- W3044203926 hasOpenAccess W3044203926 @default.
- W3044203926 hasPrimaryLocation W30442039261 @default.
- W3044203926 hasRelatedWork W1753659477 @default.
- W3044203926 hasRelatedWork W1984610878 @default.
- W3044203926 hasRelatedWork W2069309752 @default.
- W3044203926 hasRelatedWork W2088059023 @default.
- W3044203926 hasRelatedWork W2217430106 @default.
- W3044203926 hasRelatedWork W2288707378 @default.
- W3044203926 hasRelatedWork W2296295948 @default.
- W3044203926 hasRelatedWork W2495778891 @default.
- W3044203926 hasRelatedWork W2804148081 @default.
- W3044203926 hasRelatedWork W2891982091 @default.
- W3044203926 hasRelatedWork W2901308856 @default.
- W3044203926 hasRelatedWork W2916773661 @default.
- W3044203926 hasRelatedWork W2922054794 @default.
- W3044203926 hasRelatedWork W2980748755 @default.
- W3044203926 hasRelatedWork W2983991711 @default.
- W3044203926 hasRelatedWork W3007204104 @default.
- W3044203926 hasRelatedWork W3039688475 @default.
- W3044203926 hasRelatedWork W3132602355 @default.
- W3044203926 hasRelatedWork W3165075898 @default.
- W3044203926 hasRelatedWork W2183647830 @default.
- W3044203926 isParatext "false" @default.
- W3044203926 isRetracted "false" @default.
- W3044203926 magId "3044203926" @default.
- W3044203926 workType "article" @default.