Matches in SemOpenAlex for { <https://semopenalex.org/work/W4289201293> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W4289201293 endingPage "105232" @default.
- W4289201293 startingPage "105232" @default.
- W4289201293 abstract "Time series data is of great value in data mining and analysis, but it often comes with the problem of data partly missing in many fields. So it is necessary to impute missing values from raw data to improve accuracy in the analysis of time series. Conventional methods based on interpolation ignore the temporal correlation of data. Recurrent Neural Networks (RNN) are good at capturing temporal relationships, while they have a limitation to obtain the potential correlations in multivariate time series. Based on Generative Adversarial Networks, this paper proposes a new model for time series imputation. The key contributions of the paper are: (i) A feature extraction module is designed to reduce the influence of irrelevant features in raw data. (ii) A bidirectional Gated Recurrent Unit (GRU) module is applied to capture the temporal relationships. A temporal attention mechanism is also designed to help capture important correlations in long sequences which will be neglected by conventional RNN. (iii) A new feature attention based on multi-head self-attention is proposed to extract the potential correlations within multivariate features. (iv) A temporal hint mechanism is added so that the discriminator can perform better in identifying fake data and the generator can learn the distribution of raw data better. The proposed model has been tested on 4 real-world datasets. Two metrics are applied to evaluate the results: Root Mean Square Error and Mean Absolute Error. The results illustrate that our model is superior to the other 10 state-of-the-art methods in most cases." @default.
- W4289201293 created "2022-08-01" @default.
- W4289201293 creator A5012957281 @default.
- W4289201293 creator A5069874944 @default.
- W4289201293 date "2022-10-01" @default.
- W4289201293 modified "2023-10-16" @default.
- W4289201293 title "MBGAN: An improved generative adversarial network with multi-head self-attention and bidirectional RNN for time series imputation" @default.
- W4289201293 cites W1634075355 @default.
- W4289201293 cites W2040731319 @default.
- W4289201293 cites W2396881363 @default.
- W4289201293 cites W2738434210 @default.
- W4289201293 cites W2747672283 @default.
- W4289201293 cites W2761311579 @default.
- W4289201293 cites W2769575588 @default.
- W4289201293 cites W2774603473 @default.
- W4289201293 cites W2884466206 @default.
- W4289201293 cites W2964010366 @default.
- W4289201293 cites W2979294180 @default.
- W4289201293 cites W2986349107 @default.
- W4289201293 cites W2987385519 @default.
- W4289201293 cites W2997705255 @default.
- W4289201293 cites W3000659041 @default.
- W4289201293 cites W3008627481 @default.
- W4289201293 cites W3035623224 @default.
- W4289201293 cites W3048301386 @default.
- W4289201293 cites W3101942798 @default.
- W4289201293 cites W3102476541 @default.
- W4289201293 cites W3108376771 @default.
- W4289201293 cites W3109901740 @default.
- W4289201293 cites W3111763173 @default.
- W4289201293 cites W3119582991 @default.
- W4289201293 cites W3121341047 @default.
- W4289201293 cites W3128430136 @default.
- W4289201293 cites W3135594323 @default.
- W4289201293 cites W3193962426 @default.
- W4289201293 cites W3196402958 @default.
- W4289201293 doi "https://doi.org/10.1016/j.engappai.2022.105232" @default.
- W4289201293 hasPublicationYear "2022" @default.
- W4289201293 type Work @default.
- W4289201293 citedByCount "10" @default.
- W4289201293 countsByYear W42892012932023 @default.
- W4289201293 crossrefType "journal-article" @default.
- W4289201293 hasAuthorship W4289201293A5012957281 @default.
- W4289201293 hasAuthorship W4289201293A5069874944 @default.
- W4289201293 hasConcept C104114177 @default.
- W4289201293 hasConcept C119857082 @default.
- W4289201293 hasConcept C124101348 @default.
- W4289201293 hasConcept C137800194 @default.
- W4289201293 hasConcept C147168706 @default.
- W4289201293 hasConcept C151406439 @default.
- W4289201293 hasConcept C153180895 @default.
- W4289201293 hasConcept C154945302 @default.
- W4289201293 hasConcept C161584116 @default.
- W4289201293 hasConcept C167966045 @default.
- W4289201293 hasConcept C2779803651 @default.
- W4289201293 hasConcept C39890363 @default.
- W4289201293 hasConcept C41008148 @default.
- W4289201293 hasConcept C50644808 @default.
- W4289201293 hasConcept C58041806 @default.
- W4289201293 hasConcept C76155785 @default.
- W4289201293 hasConcept C9357733 @default.
- W4289201293 hasConcept C94915269 @default.
- W4289201293 hasConceptScore W4289201293C104114177 @default.
- W4289201293 hasConceptScore W4289201293C119857082 @default.
- W4289201293 hasConceptScore W4289201293C124101348 @default.
- W4289201293 hasConceptScore W4289201293C137800194 @default.
- W4289201293 hasConceptScore W4289201293C147168706 @default.
- W4289201293 hasConceptScore W4289201293C151406439 @default.
- W4289201293 hasConceptScore W4289201293C153180895 @default.
- W4289201293 hasConceptScore W4289201293C154945302 @default.
- W4289201293 hasConceptScore W4289201293C161584116 @default.
- W4289201293 hasConceptScore W4289201293C167966045 @default.
- W4289201293 hasConceptScore W4289201293C2779803651 @default.
- W4289201293 hasConceptScore W4289201293C39890363 @default.
- W4289201293 hasConceptScore W4289201293C41008148 @default.
- W4289201293 hasConceptScore W4289201293C50644808 @default.
- W4289201293 hasConceptScore W4289201293C58041806 @default.
- W4289201293 hasConceptScore W4289201293C76155785 @default.
- W4289201293 hasConceptScore W4289201293C9357733 @default.
- W4289201293 hasConceptScore W4289201293C94915269 @default.
- W4289201293 hasFunder F4320335777 @default.
- W4289201293 hasLocation W42892012931 @default.
- W4289201293 hasOpenAccess W4289201293 @default.
- W4289201293 hasPrimaryLocation W42892012931 @default.
- W4289201293 hasRelatedWork W1574575415 @default.
- W4289201293 hasRelatedWork W2024529227 @default.
- W4289201293 hasRelatedWork W2081476516 @default.
- W4289201293 hasRelatedWork W2181530120 @default.
- W4289201293 hasRelatedWork W2581984549 @default.
- W4289201293 hasRelatedWork W3028371478 @default.
- W4289201293 hasRelatedWork W3144172081 @default.
- W4289201293 hasRelatedWork W3179858851 @default.
- W4289201293 hasRelatedWork W4211215373 @default.
- W4289201293 hasRelatedWork W3123177881 @default.
- W4289201293 hasVolume "115" @default.
- W4289201293 isParatext "false" @default.
- W4289201293 isRetracted "false" @default.
- W4289201293 workType "article" @default.