Matches in SemOpenAlex for { <https://semopenalex.org/work/W4386598051> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W4386598051 abstract "In software metric datasets, the number of defective samples is always even fewer than that of non-defective samples, which makes follow-up research complex and difficult. Therefore, this essay provides a method of software defective data augmentation based on a variational autoencoder (VAE) and Wasserstein Generative Adversarial Network (WGAN). This process contains several steps. First, dimensionality reduction of software metric data is achieved by utilizing VAE, producing a set of codes (latent vectors); the distribution of the set is studied by WGAN and then “the code set (latent vectors)” is generated. Finally, the generated codes (latent vectors) are input into VAE to acquire defective data. This paper proposes a data augmentation method of a minority class, based on VAE and WGAN. The experiments performed in MINST, NSAS MDP confirm that 1) This data augmentation method is superior to WGAN, AE+WGAN, and SMOTE; 2) Introducing the variance of generated samples to the WGAN generator, the variety of those is efficiently improved." @default.
- W4386598051 created "2023-09-12" @default.
- W4386598051 creator A5037790992 @default.
- W4386598051 creator A5078875524 @default.
- W4386598051 date "2023-06-01" @default.
- W4386598051 modified "2023-09-29" @default.
- W4386598051 title "One software defective data augmentation method based on VAE and WGAN" @default.
- W4386598051 cites W1999117413 @default.
- W4386598051 cites W2024199384 @default.
- W4386598051 cites W2097883090 @default.
- W4386598051 cites W2103715428 @default.
- W4386598051 cites W2120457925 @default.
- W4386598051 cites W2130883460 @default.
- W4386598051 cites W2963073614 @default.
- W4386598051 cites W2963767194 @default.
- W4386598051 cites W2964268978 @default.
- W4386598051 cites W3004917840 @default.
- W4386598051 cites W3034601242 @default.
- W4386598051 cites W3120254195 @default.
- W4386598051 cites W3154236293 @default.
- W4386598051 cites W3196308991 @default.
- W4386598051 doi "https://doi.org/10.1109/frse58934.2023.00014" @default.
- W4386598051 hasPublicationYear "2023" @default.
- W4386598051 type Work @default.
- W4386598051 citedByCount "0" @default.
- W4386598051 crossrefType "proceedings-article" @default.
- W4386598051 hasAuthorship W4386598051A5037790992 @default.
- W4386598051 hasAuthorship W4386598051A5078875524 @default.
- W4386598051 hasConcept C101738243 @default.
- W4386598051 hasConcept C121332964 @default.
- W4386598051 hasConcept C124101348 @default.
- W4386598051 hasConcept C153180895 @default.
- W4386598051 hasConcept C154945302 @default.
- W4386598051 hasConcept C162324750 @default.
- W4386598051 hasConcept C163258240 @default.
- W4386598051 hasConcept C176217482 @default.
- W4386598051 hasConcept C177264268 @default.
- W4386598051 hasConcept C199360897 @default.
- W4386598051 hasConcept C21547014 @default.
- W4386598051 hasConcept C2776760102 @default.
- W4386598051 hasConcept C2777904410 @default.
- W4386598051 hasConcept C2780992000 @default.
- W4386598051 hasConcept C41008148 @default.
- W4386598051 hasConcept C50644808 @default.
- W4386598051 hasConcept C58489278 @default.
- W4386598051 hasConcept C62520636 @default.
- W4386598051 hasConceptScore W4386598051C101738243 @default.
- W4386598051 hasConceptScore W4386598051C121332964 @default.
- W4386598051 hasConceptScore W4386598051C124101348 @default.
- W4386598051 hasConceptScore W4386598051C153180895 @default.
- W4386598051 hasConceptScore W4386598051C154945302 @default.
- W4386598051 hasConceptScore W4386598051C162324750 @default.
- W4386598051 hasConceptScore W4386598051C163258240 @default.
- W4386598051 hasConceptScore W4386598051C176217482 @default.
- W4386598051 hasConceptScore W4386598051C177264268 @default.
- W4386598051 hasConceptScore W4386598051C199360897 @default.
- W4386598051 hasConceptScore W4386598051C21547014 @default.
- W4386598051 hasConceptScore W4386598051C2776760102 @default.
- W4386598051 hasConceptScore W4386598051C2777904410 @default.
- W4386598051 hasConceptScore W4386598051C2780992000 @default.
- W4386598051 hasConceptScore W4386598051C41008148 @default.
- W4386598051 hasConceptScore W4386598051C50644808 @default.
- W4386598051 hasConceptScore W4386598051C58489278 @default.
- W4386598051 hasConceptScore W4386598051C62520636 @default.
- W4386598051 hasFunder F4320322108 @default.
- W4386598051 hasLocation W43865980511 @default.
- W4386598051 hasOpenAccess W4386598051 @default.
- W4386598051 hasPrimaryLocation W43865980511 @default.
- W4386598051 hasRelatedWork W2292254049 @default.
- W4386598051 hasRelatedWork W2592385986 @default.
- W4386598051 hasRelatedWork W2772780115 @default.
- W4386598051 hasRelatedWork W2897995864 @default.
- W4386598051 hasRelatedWork W2998168123 @default.
- W4386598051 hasRelatedWork W3099179464 @default.
- W4386598051 hasRelatedWork W4214881770 @default.
- W4386598051 hasRelatedWork W4281924768 @default.
- W4386598051 hasRelatedWork W4287995534 @default.
- W4386598051 hasRelatedWork W4309838615 @default.
- W4386598051 isParatext "false" @default.
- W4386598051 isRetracted "false" @default.
- W4386598051 workType "article" @default.