Matches in SemOpenAlex for { <https://semopenalex.org/work/W3106662783> ?p ?o ?g. }
Showing items 1 to 81 of
81
with 100 items per page.
- W3106662783 endingPage "1" @default.
- W3106662783 startingPage "1" @default.
- W3106662783 abstract "Activity recognition based on channel state information (CSI) plays an increasingly important role in human computer interaction. However most CSI activity recognition systems need to re-collect a large amount of samples and retrain model when they are used in new environments or recognize new types of activities, which greatly reduces the practicality of CSI activity recognition. To address this problem we design an adaptable CSI activity recognition system based on meta-learning, which only needs to fine-tune model with very little train effort when it is used in new environments or recognize new types of activities. To prevent the loss of CSI time information after feature extraction with multi-layer CNN, we add time encoding on CSI data as the input of CNN neural network. Considering that CSI data may be labeled incorrectly during labeling process, we improve categorical cross entropy loss(CCE) to enhance the system's robustness to these mislabeled data. We test our system on the gesture dataset and the body activity dataset, and the experimental results show that our system achieves average accuracy of 72% with 1 sample of each new activity and 89.6% with 5 samples of each new activity." @default.
- W3106662783 created "2020-12-07" @default.
- W3106662783 creator A5017142254 @default.
- W3106662783 creator A5035299839 @default.
- W3106662783 creator A5055205123 @default.
- W3106662783 creator A5064222660 @default.
- W3106662783 date "2020-01-01" @default.
- W3106662783 modified "2023-09-29" @default.
- W3106662783 title "Human Activity Recognition Across Scenes and Categories Based on CSI" @default.
- W3106662783 cites W2022304611 @default.
- W3106662783 cites W2055450809 @default.
- W3106662783 cites W2069313697 @default.
- W3106662783 cites W2089695767 @default.
- W3106662783 cites W2090702298 @default.
- W3106662783 cites W2095396347 @default.
- W3106662783 cites W2122336786 @default.
- W3106662783 cites W2122687876 @default.
- W3106662783 cites W2340862004 @default.
- W3106662783 cites W2753866421 @default.
- W3106662783 cites W2755767288 @default.
- W3106662783 cites W2756200584 @default.
- W3106662783 cites W2794189208 @default.
- W3106662783 cites W2794843057 @default.
- W3106662783 cites W2796919335 @default.
- W3106662783 cites W2802039875 @default.
- W3106662783 cites W2803428049 @default.
- W3106662783 cites W2890485850 @default.
- W3106662783 cites W2890686146 @default.
- W3106662783 cites W2890967649 @default.
- W3106662783 cites W2895416001 @default.
- W3106662783 cites W2904632047 @default.
- W3106662783 cites W2907860196 @default.
- W3106662783 cites W2921700058 @default.
- W3106662783 cites W2929084559 @default.
- W3106662783 cites W2938652275 @default.
- W3106662783 cites W2957105406 @default.
- W3106662783 cites W2964055695 @default.
- W3106662783 cites W2973078060 @default.
- W3106662783 cites W2996971795 @default.
- W3106662783 doi "https://doi.org/10.1109/tmc.2020.3041756" @default.
- W3106662783 hasPublicationYear "2020" @default.
- W3106662783 type Work @default.
- W3106662783 sameAs 3106662783 @default.
- W3106662783 citedByCount "21" @default.
- W3106662783 countsByYear W31066627832021 @default.
- W3106662783 countsByYear W31066627832022 @default.
- W3106662783 countsByYear W31066627832023 @default.
- W3106662783 crossrefType "journal-article" @default.
- W3106662783 hasAuthorship W3106662783A5017142254 @default.
- W3106662783 hasAuthorship W3106662783A5035299839 @default.
- W3106662783 hasAuthorship W3106662783A5055205123 @default.
- W3106662783 hasAuthorship W3106662783A5064222660 @default.
- W3106662783 hasConcept C121687571 @default.
- W3106662783 hasConcept C153180895 @default.
- W3106662783 hasConcept C154945302 @default.
- W3106662783 hasConcept C31972630 @default.
- W3106662783 hasConcept C41008148 @default.
- W3106662783 hasConceptScore W3106662783C121687571 @default.
- W3106662783 hasConceptScore W3106662783C153180895 @default.
- W3106662783 hasConceptScore W3106662783C154945302 @default.
- W3106662783 hasConceptScore W3106662783C31972630 @default.
- W3106662783 hasConceptScore W3106662783C41008148 @default.
- W3106662783 hasLocation W31066627831 @default.
- W3106662783 hasOpenAccess W3106662783 @default.
- W3106662783 hasPrimaryLocation W31066627831 @default.
- W3106662783 hasRelatedWork W1602226726 @default.
- W3106662783 hasRelatedWork W1891287906 @default.
- W3106662783 hasRelatedWork W1969648729 @default.
- W3106662783 hasRelatedWork W2007815619 @default.
- W3106662783 hasRelatedWork W2188464267 @default.
- W3106662783 hasRelatedWork W2291700858 @default.
- W3106662783 hasRelatedWork W2891219753 @default.
- W3106662783 hasRelatedWork W2922225723 @default.
- W3106662783 hasRelatedWork W2954309397 @default.
- W3106662783 hasRelatedWork W3106494386 @default.
- W3106662783 isParatext "false" @default.
- W3106662783 isRetracted "false" @default.
- W3106662783 magId "3106662783" @default.
- W3106662783 workType "article" @default.