Matches in SemOpenAlex for { <https://semopenalex.org/work/W4292074927> ?p ?o ?g. }
Showing items 1 to 87 of
87
with 100 items per page.
- W4292074927 endingPage "11532" @default.
- W4292074927 startingPage "11512" @default.
- W4292074927 abstract "<abstract> <p>With the rapid development and application of the mobile Internet, it is necessary to analyze and classify mobile traffic to meet the needs of users. Due to the difficulty in collecting some application data, the mobile traffic data presents a long-tailed distribution, resulting in a decrease in classification accuracy. In addition, the original GAN is difficult to train, and it is prone to mode collapse. Therefore, this paper introduces the self-attention mechanism and gradient normalization into the auxiliary classifier generative adversarial network to form SA-ACGAN-GN model to solve the long-tailed distribution and training stability problems of mobile traffic data. This method firstly converts the traffic into images; secondly, to improve the quality of the generated images, the self-attention mechanism is introduced into the ACGAN model to obtain the global geometric features of the images; finally, the gradient normalization strategy is added to SA-ACGAN to further improve the data augmentation effect and improve the training stability. It can be seen from the cross-validation experimental data that, on the basis of using the same classifier, the SA-ACGAN-GN algorithm proposed in this paper, compared with other comparison algorithms, has the best precision reaching 93.8%; after adding gradient normalization, during the training process of the model, the classification loss decreases rapidly and the loss curve fluctuates less, indicating that the method proposed in this paper can not only effectively improve the long-tail problem of the dataset, but also enhance the stability of the model training.</p> </abstract>" @default.
- W4292074927 created "2022-08-17" @default.
- W4292074927 creator A5031315906 @default.
- W4292074927 creator A5039865469 @default.
- W4292074927 creator A5042194405 @default.
- W4292074927 date "2022-01-01" @default.
- W4292074927 modified "2023-09-24" @default.
- W4292074927 title "Research on mobile traffic data augmentation methods based on SA-ACGAN-GN" @default.
- W4292074927 cites W2096118443 @default.
- W4292074927 cites W2099454382 @default.
- W4292074927 cites W2148143831 @default.
- W4292074927 cites W2756182389 @default.
- W4292074927 cites W2761748950 @default.
- W4292074927 cites W2787505794 @default.
- W4292074927 cites W2898413119 @default.
- W4292074927 cites W2899901572 @default.
- W4292074927 cites W2919493784 @default.
- W4292074927 cites W2970412293 @default.
- W4292074927 cites W2979389376 @default.
- W4292074927 cites W2981318525 @default.
- W4292074927 cites W2982853004 @default.
- W4292074927 cites W3033266910 @default.
- W4292074927 cites W3082260310 @default.
- W4292074927 cites W3093778635 @default.
- W4292074927 cites W3100100256 @default.
- W4292074927 cites W3121886859 @default.
- W4292074927 cites W3128258769 @default.
- W4292074927 cites W3131088496 @default.
- W4292074927 cites W3159433923 @default.
- W4292074927 cites W3190219082 @default.
- W4292074927 cites W3205323312 @default.
- W4292074927 cites W4210743106 @default.
- W4292074927 doi "https://doi.org/10.3934/mbe.2022536" @default.
- W4292074927 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36124601" @default.
- W4292074927 hasPublicationYear "2022" @default.
- W4292074927 type Work @default.
- W4292074927 citedByCount "1" @default.
- W4292074927 countsByYear W42920749272023 @default.
- W4292074927 crossrefType "journal-article" @default.
- W4292074927 hasAuthorship W4292074927A5031315906 @default.
- W4292074927 hasAuthorship W4292074927A5039865469 @default.
- W4292074927 hasAuthorship W4292074927A5042194405 @default.
- W4292074927 hasBestOaLocation W42920749271 @default.
- W4292074927 hasConcept C11413529 @default.
- W4292074927 hasConcept C119857082 @default.
- W4292074927 hasConcept C124101348 @default.
- W4292074927 hasConcept C136886441 @default.
- W4292074927 hasConcept C144024400 @default.
- W4292074927 hasConcept C153180895 @default.
- W4292074927 hasConcept C154945302 @default.
- W4292074927 hasConcept C19165224 @default.
- W4292074927 hasConcept C39890363 @default.
- W4292074927 hasConcept C41008148 @default.
- W4292074927 hasConcept C95623464 @default.
- W4292074927 hasConceptScore W4292074927C11413529 @default.
- W4292074927 hasConceptScore W4292074927C119857082 @default.
- W4292074927 hasConceptScore W4292074927C124101348 @default.
- W4292074927 hasConceptScore W4292074927C136886441 @default.
- W4292074927 hasConceptScore W4292074927C144024400 @default.
- W4292074927 hasConceptScore W4292074927C153180895 @default.
- W4292074927 hasConceptScore W4292074927C154945302 @default.
- W4292074927 hasConceptScore W4292074927C19165224 @default.
- W4292074927 hasConceptScore W4292074927C39890363 @default.
- W4292074927 hasConceptScore W4292074927C41008148 @default.
- W4292074927 hasConceptScore W4292074927C95623464 @default.
- W4292074927 hasIssue "11" @default.
- W4292074927 hasLocation W42920749271 @default.
- W4292074927 hasLocation W42920749272 @default.
- W4292074927 hasLocation W42920749273 @default.
- W4292074927 hasOpenAccess W4292074927 @default.
- W4292074927 hasPrimaryLocation W42920749271 @default.
- W4292074927 hasRelatedWork W1991269640 @default.
- W4292074927 hasRelatedWork W2016839265 @default.
- W4292074927 hasRelatedWork W2167582322 @default.
- W4292074927 hasRelatedWork W2563096758 @default.
- W4292074927 hasRelatedWork W2742991909 @default.
- W4292074927 hasRelatedWork W2972035100 @default.
- W4292074927 hasRelatedWork W3200179079 @default.
- W4292074927 hasRelatedWork W4386053843 @default.
- W4292074927 hasRelatedWork W2508457823 @default.
- W4292074927 hasRelatedWork W3158004940 @default.
- W4292074927 hasVolume "19" @default.
- W4292074927 isParatext "false" @default.
- W4292074927 isRetracted "false" @default.
- W4292074927 workType "article" @default.