Matches in SemOpenAlex for { <https://semopenalex.org/work/W4310191638> ?p ?o ?g. }
- W4310191638 endingPage "9272" @default.
- W4310191638 startingPage "9272" @default.
- W4310191638 abstract "Graph neural networks have been successfully applied to sleep stage classification, but there are still challenges: (1) How to effectively utilize epoch information of EEG-adjacent channels owing to their different interaction effects. (2) How to extract the most representative features according to confused transitional information in confused stages. (3) How to improve classification accuracy of sleep stages compared with existing models. To address these shortcomings, we propose a multi-layer graph attention network (MGANet). Node-level attention prompts the graph attention convolution and GRU to focus on and differentiate the interaction between channels in the time-frequency domain and the spatial domain, respectively. The multi-head spatial-temporal mechanism balances the channel weights and dynamically adjusts channel features, and a multi-layer graph attention network accurately expresses the spatial sleep information. Moreover, stage-level attention is applied to easily confused sleep stages, which effectively improves the limitations of a graph convolutional network in large-scale graph sleep stages. The experimental results demonstrated classification accuracy; MF1 and Kappa reached 0.825, 0.814, and 0.775 and 0.873, 0.801, and 0.827 for the ISRUC and SHHS datasets, respectively, which showed that MGANet outperformed the state-of-the-art baselines." @default.
- W4310191638 created "2022-11-30" @default.
- W4310191638 creator A5002525885 @default.
- W4310191638 creator A5015195367 @default.
- W4310191638 creator A5016330336 @default.
- W4310191638 creator A5023360624 @default.
- W4310191638 creator A5054502150 @default.
- W4310191638 date "2022-11-28" @default.
- W4310191638 modified "2023-09-27" @default.
- W4310191638 title "Multi-Layer Graph Attention Network for Sleep Stage Classification Based on EEG" @default.
- W4310191638 cites W1545241942 @default.
- W4310191638 cites W1554223333 @default.
- W4310191638 cites W160785014 @default.
- W4310191638 cites W1993220166 @default.
- W4310191638 cites W2050359514 @default.
- W4310191638 cites W2063093002 @default.
- W4310191638 cites W2147264168 @default.
- W4310191638 cites W2152556184 @default.
- W4310191638 cites W2172894528 @default.
- W4310191638 cites W2180889008 @default.
- W4310191638 cites W244799260 @default.
- W4310191638 cites W2539353608 @default.
- W4310191638 cites W2587736287 @default.
- W4310191638 cites W2604096629 @default.
- W4310191638 cites W2771006757 @default.
- W4310191638 cites W2793841943 @default.
- W4310191638 cites W2805075551 @default.
- W4310191638 cites W2893892260 @default.
- W4310191638 cites W2922255081 @default.
- W4310191638 cites W2950301853 @default.
- W4310191638 cites W2963919481 @default.
- W4310191638 cites W3034369844 @default.
- W4310191638 cites W3044656331 @default.
- W4310191638 cites W3046236234 @default.
- W4310191638 cites W3081446688 @default.
- W4310191638 cites W3088922629 @default.
- W4310191638 cites W3129064953 @default.
- W4310191638 cites W3158818505 @default.
- W4310191638 cites W3159541278 @default.
- W4310191638 cites W3198543070 @default.
- W4310191638 cites W4205935690 @default.
- W4310191638 cites W4206203292 @default.
- W4310191638 cites W4280630954 @default.
- W4310191638 doi "https://doi.org/10.3390/s22239272" @default.
- W4310191638 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36501974" @default.
- W4310191638 hasPublicationYear "2022" @default.
- W4310191638 type Work @default.
- W4310191638 citedByCount "2" @default.
- W4310191638 countsByYear W43101916382023 @default.
- W4310191638 crossrefType "journal-article" @default.
- W4310191638 hasAuthorship W4310191638A5002525885 @default.
- W4310191638 hasAuthorship W4310191638A5015195367 @default.
- W4310191638 hasAuthorship W4310191638A5016330336 @default.
- W4310191638 hasAuthorship W4310191638A5023360624 @default.
- W4310191638 hasAuthorship W4310191638A5054502150 @default.
- W4310191638 hasBestOaLocation W43101916381 @default.
- W4310191638 hasConcept C118552586 @default.
- W4310191638 hasConcept C124101348 @default.
- W4310191638 hasConcept C132525143 @default.
- W4310191638 hasConcept C153180895 @default.
- W4310191638 hasConcept C154945302 @default.
- W4310191638 hasConcept C15744967 @default.
- W4310191638 hasConcept C2778205975 @default.
- W4310191638 hasConcept C2910364982 @default.
- W4310191638 hasConcept C2993807640 @default.
- W4310191638 hasConcept C41008148 @default.
- W4310191638 hasConcept C45347329 @default.
- W4310191638 hasConcept C50644808 @default.
- W4310191638 hasConcept C522805319 @default.
- W4310191638 hasConcept C80444323 @default.
- W4310191638 hasConcept C81363708 @default.
- W4310191638 hasConceptScore W4310191638C118552586 @default.
- W4310191638 hasConceptScore W4310191638C124101348 @default.
- W4310191638 hasConceptScore W4310191638C132525143 @default.
- W4310191638 hasConceptScore W4310191638C153180895 @default.
- W4310191638 hasConceptScore W4310191638C154945302 @default.
- W4310191638 hasConceptScore W4310191638C15744967 @default.
- W4310191638 hasConceptScore W4310191638C2778205975 @default.
- W4310191638 hasConceptScore W4310191638C2910364982 @default.
- W4310191638 hasConceptScore W4310191638C2993807640 @default.
- W4310191638 hasConceptScore W4310191638C41008148 @default.
- W4310191638 hasConceptScore W4310191638C45347329 @default.
- W4310191638 hasConceptScore W4310191638C50644808 @default.
- W4310191638 hasConceptScore W4310191638C522805319 @default.
- W4310191638 hasConceptScore W4310191638C80444323 @default.
- W4310191638 hasConceptScore W4310191638C81363708 @default.
- W4310191638 hasIssue "23" @default.
- W4310191638 hasLocation W43101916381 @default.
- W4310191638 hasLocation W43101916382 @default.
- W4310191638 hasLocation W43101916383 @default.
- W4310191638 hasLocation W43101916384 @default.
- W4310191638 hasOpenAccess W4310191638 @default.
- W4310191638 hasPrimaryLocation W43101916381 @default.
- W4310191638 hasRelatedWork W2175746458 @default.
- W4310191638 hasRelatedWork W2732542196 @default.
- W4310191638 hasRelatedWork W2738221750 @default.
- W4310191638 hasRelatedWork W2760085659 @default.
- W4310191638 hasRelatedWork W2767651786 @default.