Matches in SemOpenAlex for { <https://semopenalex.org/work/W4376632795> ?p ?o ?g. }
Showing items 1 to 67 of
67
with 100 items per page.
- W4376632795 abstract "Individual differences of Electroencephalogram (EEG) could cause the domain shift which would significantly degrade the performance of cross-subject strategy. The domain adversarial neural networks (DANN), where the classification loss and domain loss jointly update the parameters of feature extractor, are adopted to deal with the domain shift. However, limited EEG data quantity and strong individual difference are challenges for the DANN with cumbersome feature extractor. In this work, we propose knowledge distillation (KD) based lightweight DANN to enhance cross-subject EEG-based emotion recognition. Specifically, the teacher model with strong context learning ability is utilized to learn complex temporal dynamics and spatial correlations of EEG, and robust lightweight student model is guided by the teacher model to learn more difficult domain-invariant features. In the feature-based KD framework, a transformer-based hierarchical temporalspatial learning model is served as the teacher model. The student model, which is composed of Bi-LSTM units, is a lightweight version of the teacher model. Hence, the student model could be supervised to mimic the robust feature representations of teacher model by leveraging complementary latent temporal features and spatial features. In the DANN-based cross-subject emotion recognition, we combine the obtained student model and a lightweight temporal-spatial feature interaction module as the feature extractor. And the feature aggregation is fed to the emotion classifier and domain classifier for domain-invariant feature learning. To verify the effectiveness of the proposed method, we conduct the subject-independent experiments on the public dataset DEAP with arousal and valence classification. The outstanding performance and t-SNE visualization of latent features verify the advantage and effectiveness of the proposed method." @default.
- W4376632795 created "2023-05-17" @default.
- W4376632795 creator A5000879177 @default.
- W4376632795 creator A5029032691 @default.
- W4376632795 creator A5030841645 @default.
- W4376632795 creator A5044055624 @default.
- W4376632795 creator A5056053058 @default.
- W4376632795 date "2023-05-12" @default.
- W4376632795 modified "2023-09-23" @default.
- W4376632795 title "A Lightweight Domain Adversarial Neural Network Based on Knowledge Distillation for EEG-based Cross-subject Emotion Recognition" @default.
- W4376632795 doi "https://doi.org/10.48550/arxiv.2305.07446" @default.
- W4376632795 hasPublicationYear "2023" @default.
- W4376632795 type Work @default.
- W4376632795 citedByCount "0" @default.
- W4376632795 crossrefType "posted-content" @default.
- W4376632795 hasAuthorship W4376632795A5000879177 @default.
- W4376632795 hasAuthorship W4376632795A5029032691 @default.
- W4376632795 hasAuthorship W4376632795A5030841645 @default.
- W4376632795 hasAuthorship W4376632795A5044055624 @default.
- W4376632795 hasAuthorship W4376632795A5056053058 @default.
- W4376632795 hasBestOaLocation W43766327951 @default.
- W4376632795 hasConcept C117978034 @default.
- W4376632795 hasConcept C119857082 @default.
- W4376632795 hasConcept C127413603 @default.
- W4376632795 hasConcept C138885662 @default.
- W4376632795 hasConcept C153180895 @default.
- W4376632795 hasConcept C154945302 @default.
- W4376632795 hasConcept C21880701 @default.
- W4376632795 hasConcept C2776401178 @default.
- W4376632795 hasConcept C28490314 @default.
- W4376632795 hasConcept C41008148 @default.
- W4376632795 hasConcept C41895202 @default.
- W4376632795 hasConcept C50644808 @default.
- W4376632795 hasConcept C52622490 @default.
- W4376632795 hasConcept C59404180 @default.
- W4376632795 hasConcept C95623464 @default.
- W4376632795 hasConceptScore W4376632795C117978034 @default.
- W4376632795 hasConceptScore W4376632795C119857082 @default.
- W4376632795 hasConceptScore W4376632795C127413603 @default.
- W4376632795 hasConceptScore W4376632795C138885662 @default.
- W4376632795 hasConceptScore W4376632795C153180895 @default.
- W4376632795 hasConceptScore W4376632795C154945302 @default.
- W4376632795 hasConceptScore W4376632795C21880701 @default.
- W4376632795 hasConceptScore W4376632795C2776401178 @default.
- W4376632795 hasConceptScore W4376632795C28490314 @default.
- W4376632795 hasConceptScore W4376632795C41008148 @default.
- W4376632795 hasConceptScore W4376632795C41895202 @default.
- W4376632795 hasConceptScore W4376632795C50644808 @default.
- W4376632795 hasConceptScore W4376632795C52622490 @default.
- W4376632795 hasConceptScore W4376632795C59404180 @default.
- W4376632795 hasConceptScore W4376632795C95623464 @default.
- W4376632795 hasLocation W43766327951 @default.
- W4376632795 hasOpenAccess W4376632795 @default.
- W4376632795 hasPrimaryLocation W43766327951 @default.
- W4376632795 hasRelatedWork W2016461833 @default.
- W4376632795 hasRelatedWork W2022996092 @default.
- W4376632795 hasRelatedWork W2188464267 @default.
- W4376632795 hasRelatedWork W2546942002 @default.
- W4376632795 hasRelatedWork W2784352036 @default.
- W4376632795 hasRelatedWork W2807311372 @default.
- W4376632795 hasRelatedWork W2899683012 @default.
- W4376632795 hasRelatedWork W2905846897 @default.
- W4376632795 hasRelatedWork W3197541072 @default.
- W4376632795 hasRelatedWork W4367598285 @default.
- W4376632795 isParatext "false" @default.
- W4376632795 isRetracted "false" @default.
- W4376632795 workType "article" @default.