FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4317107612> ?p ?o ?g. }

• W4317107612 endingPage "1083" @default.
• W4317107612 startingPage "1083" @default.
• W4317107612 abstract "The ubiquity of smartphones equipped with multiple sensors has provided the possibility of automatically recognizing of human activity, which can benefit intelligent applications such as smart homes, health monitoring, and aging care. However, there are two major barriers to deploying an activity recognition model in real-world scenarios. Firstly, deep learning models for activity recognition use a large amount of sensor data, which are privacy-sensitive and hence cannot be shared or uploaded to a centralized server. Secondly, divergence in the distribution of sensory data exists among multiple individuals due to their diverse behavioral patterns and lifestyles, which contributes to difficulty in recognizing activity for large-scale users or ’cold-starts’ for new users. To address these problems, we propose DivAR, a diversity-aware activity recognition framework based on a federated Meta-Learning architecture, which can extract general sensory features shared among individuals by a centralized embedding network and individual-specific features by attention module in each decentralized network. Specifically, we first classify individuals into multiple clusters according to their behavioral patterns and social factors. We then apply meta-learning in the architecture of federated learning, where a centralized meta-model learns common feature representations that can be transferred across all clusters of individuals, and multiple decentralized cluster-specific models are utilized to learn cluster-specific features. For each cluster-specific model, a CNN-based attention module learns cluster-specific features from the global model. In this way, by training with sensory data locally, privacy-sensitive information existing in sensory data can be preserved. To evaluate the model, we conduct two data collection experiments by collecting sensor readings from naturally used smartphones annotated with activity information in the real-life environment and constructing two multi-individual heterogeneous datasets. In addition, social characteristics including personality, mental health state, and behavior patterns are surveyed using questionnaires. Finally, extensive empirical results demonstrate that the proposed diversity-aware activity recognition model has a relatively better generalization ability and achieves competitive performance on multi-individual activity recognition tasks." @default.
• W4317107612 created "2023-01-18" @default.
• W4317107612 creator A5010119230 @default.
• W4317107612 creator A5040305341 @default.
• W4317107612 creator A5044725906 @default.
• W4317107612 creator A5058334910 @default.
• W4317107612 creator A5089012283 @default.
• W4317107612 date "2023-01-17" @default.
• W4317107612 modified "2023-10-14" @default.
• W4317107612 title "Federated Meta-Learning with Attention for Diversity-Aware Human Activity Recognition" @default.
• W4317107612 cites W1527911497 @default.
• W4317107612 cites W1536680647 @default.
• W4317107612 cites W1966732563 @default.
• W4317107612 cites W1971361852 @default.
• W4317107612 cites W1973872977 @default.
• W4317107612 cites W1991468035 @default.
• W4317107612 cites W2017634428 @default.
• W4317107612 cites W2026297770 @default.
• W4317107612 cites W2037646636 @default.
• W4317107612 cites W2056068852 @default.
• W4317107612 cites W2057907879 @default.
• W4317107612 cites W2091432990 @default.
• W4317107612 cites W2097575504 @default.
• W4317107612 cites W2103868202 @default.
• W4317107612 cites W2117130368 @default.
• W4317107612 cites W2121269968 @default.
• W4317107612 cites W2132322340 @default.
• W4317107612 cites W2161897659 @default.
• W4317107612 cites W2243012843 @default.
• W4317107612 cites W2270470215 @default.
• W4317107612 cites W2283596621 @default.
• W4317107612 cites W2539690336 @default.
• W4317107612 cites W2553915786 @default.
• W4317107612 cites W2600980968 @default.
• W4317107612 cites W2621205740 @default.
• W4317107612 cites W2736191430 @default.
• W4317107612 cites W2766419757 @default.
• W4317107612 cites W2783920628 @default.
• W4317107612 cites W2785232201 @default.
• W4317107612 cites W2851629429 @default.
• W4317107612 cites W2945404821 @default.
• W4317107612 cites W2963373106 @default.
• W4317107612 cites W2965144482 @default.
• W4317107612 cites W3012409400 @default.
• W4317107612 cites W3033787231 @default.
• W4317107612 cites W3099025572 @default.
• W4317107612 cites W3100470991 @default.
• W4317107612 cites W3128981305 @default.
• W4317107612 cites W3141797743 @default.
• W4317107612 cites W3170544981 @default.
• W4317107612 cites W3194933758 @default.
• W4317107612 cites W3211781253 @default.
• W4317107612 cites W4205243614 @default.
• W4317107612 cites W4211208325 @default.
• W4317107612 doi "https://doi.org/10.3390/s23031083" @default.
• W4317107612 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36772123" @default.
• W4317107612 hasPublicationYear "2023" @default.
• W4317107612 type Work @default.
• W4317107612 citedByCount "2" @default.
• W4317107612 countsByYear W43171076122023 @default.
• W4317107612 crossrefType "journal-article" @default.
• W4317107612 hasAuthorship W4317107612A5010119230 @default.
• W4317107612 hasAuthorship W4317107612A5040305341 @default.
• W4317107612 hasAuthorship W4317107612A5044725906 @default.
• W4317107612 hasAuthorship W4317107612A5058334910 @default.
• W4317107612 hasAuthorship W4317107612A5089012283 @default.
• W4317107612 hasBestOaLocation W43171076121 @default.
• W4317107612 hasConcept C107457646 @default.
• W4317107612 hasConcept C119857082 @default.
• W4317107612 hasConcept C121687571 @default.
• W4317107612 hasConcept C136764020 @default.
• W4317107612 hasConcept C138885662 @default.
• W4317107612 hasConcept C154945302 @default.
• W4317107612 hasConcept C2776401178 @default.
• W4317107612 hasConcept C41008148 @default.
• W4317107612 hasConcept C41895202 @default.
• W4317107612 hasConcept C71901391 @default.
• W4317107612 hasConceptScore W4317107612C107457646 @default.
• W4317107612 hasConceptScore W4317107612C119857082 @default.
• W4317107612 hasConceptScore W4317107612C121687571 @default.
• W4317107612 hasConceptScore W4317107612C136764020 @default.
• W4317107612 hasConceptScore W4317107612C138885662 @default.
• W4317107612 hasConceptScore W4317107612C154945302 @default.
• W4317107612 hasConceptScore W4317107612C2776401178 @default.
• W4317107612 hasConceptScore W4317107612C41008148 @default.
• W4317107612 hasConceptScore W4317107612C41895202 @default.
• W4317107612 hasConceptScore W4317107612C71901391 @default.
• W4317107612 hasFunder F4320316081 @default.
• W4317107612 hasFunder F4320320300 @default.
• W4317107612 hasFunder F4320321001 @default.
• W4317107612 hasFunder F4320322795 @default.
• W4317107612 hasFunder F4320326270 @default.
• W4317107612 hasFunder F4320327282 @default.
• W4317107612 hasIssue "3" @default.
• W4317107612 hasLocation W43171076121 @default.
• W4317107612 hasLocation W43171076122 @default.
• W4317107612 hasLocation W43171076123 @default.
• W4317107612 hasOpenAccess W4317107612 @default.

• next