FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4226073103> ?p ?o ?g. }

• W4226073103 endingPage "951" @default.
• W4226073103 startingPage "939" @default.
• W4226073103 abstract "Nowadays, with the development of various kinds of sensors in smartphones or wearable devices, human activity recognition (HAR) has been widely researched and has numerous applications in healthcare, smart city, etc. Many techniques based on hand-crafted feature engineering or deep neural network have been proposed for sensor based HAR. However, these existing methods usually recognize activities offline, which means the whole data should be collected before training, occupying large-capacity storage space. Moreover, once the offline model training finished, the trained model can't recognize new activities unless retraining from the start, thus with a high cost of time and space. In this paper, we propose a multi-modality incremental learning model, called HarMI, with continuous learning ability. The proposed HarMI model can start training quickly with little storage space and easily learn new activities without storing previous training data. In detail, we first adopt attention mechanism to align heterogeneous sensor data with different frequencies. In addition, to overcome catastrophic forgetting in incremental learning, HarMI utilizes the elastic weight consolidation and canonical correlation analysis from a multi-modality perspective. Extensive experiments based on two public datasets demonstrate that HarMI can achieve a superior performance compared with several state-of-the-arts." @default.
• W4226073103 created "2022-05-05" @default.
• W4226073103 creator A5002318539 @default.
• W4226073103 creator A5014737169 @default.
• W4226073103 creator A5021078005 @default.
• W4226073103 creator A5032503755 @default.
• W4226073103 creator A5041921496 @default.
• W4226073103 creator A5045982340 @default.
• W4226073103 creator A5049692788 @default.
• W4226073103 creator A5051177198 @default.
• W4226073103 date "2022-03-01" @default.
• W4226073103 modified "2023-10-14" @default.
• W4226073103 title "HarMI: Human Activity Recognition Via Multi-Modality Incremental Learning" @default.
• W4226073103 cites W1986870606 @default.
• W4226073103 cites W1996340400 @default.
• W4226073103 cites W2002261403 @default.
• W4226073103 cites W2026297770 @default.
• W4226073103 cites W2048679005 @default.
• W4226073103 cites W2057907879 @default.
• W4226073103 cites W2060277733 @default.
• W4226073103 cites W2143386621 @default.
• W4226073103 cites W2158498053 @default.
• W4226073103 cites W2290026361 @default.
• W4226073103 cites W2401932923 @default.
• W4226073103 cites W2473930607 @default.
• W4226073103 cites W2502651522 @default.
• W4226073103 cites W2553915786 @default.
• W4226073103 cites W2560647685 @default.
• W4226073103 cites W2590019597 @default.
• W4226073103 cites W2604630936 @default.
• W4226073103 cites W2626046541 @default.
• W4226073103 cites W2808310571 @default.
• W4226073103 cites W2949071326 @default.
• W4226073103 cites W2963954913 @default.
• W4226073103 cites W2964189064 @default.
• W4226073103 cites W2964249867 @default.
• W4226073103 cites W2964613865 @default.
• W4226073103 cites W2964937861 @default.
• W4226073103 cites W2965144482 @default.
• W4226073103 cites W2982012856 @default.
• W4226073103 cites W2997967197 @default.
• W4226073103 cites W3007527145 @default.
• W4226073103 cites W3100686023 @default.
• W4226073103 cites W3102438316 @default.
• W4226073103 cites W3110039506 @default.
• W4226073103 cites W3121192132 @default.
• W4226073103 cites W4249992252 @default.
• W4226073103 doi "https://doi.org/10.1109/jbhi.2021.3085602" @default.
• W4226073103 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/34061754" @default.
• W4226073103 hasPublicationYear "2022" @default.
• W4226073103 type Work @default.
• W4226073103 citedByCount "4" @default.
• W4226073103 countsByYear W42260731032022 @default.
• W4226073103 countsByYear W42260731032023 @default.
• W4226073103 crossrefType "journal-article" @default.
• W4226073103 hasAuthorship W4226073103A5002318539 @default.
• W4226073103 hasAuthorship W4226073103A5014737169 @default.
• W4226073103 hasAuthorship W4226073103A5021078005 @default.
• W4226073103 hasAuthorship W4226073103A5032503755 @default.
• W4226073103 hasAuthorship W4226073103A5041921496 @default.
• W4226073103 hasAuthorship W4226073103A5045982340 @default.
• W4226073103 hasAuthorship W4226073103A5049692788 @default.
• W4226073103 hasAuthorship W4226073103A5051177198 @default.
• W4226073103 hasConcept C108583219 @default.
• W4226073103 hasConcept C119857082 @default.
• W4226073103 hasConcept C121687571 @default.
• W4226073103 hasConcept C138885662 @default.
• W4226073103 hasConcept C144024400 @default.
• W4226073103 hasConcept C144133560 @default.
• W4226073103 hasConcept C147168706 @default.
• W4226073103 hasConcept C149635348 @default.
• W4226073103 hasConcept C150594956 @default.
• W4226073103 hasConcept C154945302 @default.
• W4226073103 hasConcept C155202549 @default.
• W4226073103 hasConcept C2778712577 @default.
• W4226073103 hasConcept C2778827112 @default.
• W4226073103 hasConcept C2779903281 @default.
• W4226073103 hasConcept C2780226545 @default.
• W4226073103 hasConcept C36289849 @default.
• W4226073103 hasConcept C41008148 @default.
• W4226073103 hasConcept C41895202 @default.
• W4226073103 hasConcept C50644808 @default.
• W4226073103 hasConcept C54290928 @default.
• W4226073103 hasConcept C67186912 @default.
• W4226073103 hasConcept C7149132 @default.
• W4226073103 hasConcept C77088390 @default.
• W4226073103 hasConceptScore W4226073103C108583219 @default.
• W4226073103 hasConceptScore W4226073103C119857082 @default.
• W4226073103 hasConceptScore W4226073103C121687571 @default.
• W4226073103 hasConceptScore W4226073103C138885662 @default.
• W4226073103 hasConceptScore W4226073103C144024400 @default.
• W4226073103 hasConceptScore W4226073103C144133560 @default.
• W4226073103 hasConceptScore W4226073103C147168706 @default.
• W4226073103 hasConceptScore W4226073103C149635348 @default.
• W4226073103 hasConceptScore W4226073103C150594956 @default.
• W4226073103 hasConceptScore W4226073103C154945302 @default.
• W4226073103 hasConceptScore W4226073103C155202549 @default.
• W4226073103 hasConceptScore W4226073103C2778712577 @default.

• next