Matches in SemOpenAlex for { <https://semopenalex.org/work/W3100412866> ?p ?o ?g. }
- W3100412866 endingPage "1" @default.
- W3100412866 startingPage "1" @default.
- W3100412866 abstract "Automatic dietary monitoring (ADM) stands as a challenging application in wearable healthcare technologies. In this paper, we define an ADM to perform food intake classification (FIC) over throat microphone recordings. We investigate the use of transfer learning to design an improved FIC system. Although labeled data with acoustic close-talk microphones are abundant, throat data is scarce. Therefore, we propose a new adaptation framework based on teacher/student learning. The teacher network is trained over high-quality acoustic microphone recordings, whereas the student network distills deep feature extraction capacity of the teacher over a parallel dataset. Our approach allows us to transfer the representational capacity, adds robustness to the resulting model, and improves the FIC through throat microphone recordings. The classification problem is formulated as a spectra-temporal sequence recognition using the Convolutional LSTM (ConvLSTM) models. We evaluate the proposed approach using a large scale acoustic dataset collected from online recordings, an in-house food intake throat microphone dataset, and a parallel speech dataset. The bidirectional ConvLSTM network with the proposed domain adaptation approach consistently outperforms the SVM- and CNN-based baseline methods and attains 85.2% accuracy for the classification of 10 different food intake items. This translates to 17.8% accuracy improvement with the proposed domain adaptation." @default.
- W3100412866 created "2020-11-23" @default.
- W3100412866 creator A5005250255 @default.
- W3100412866 creator A5064993025 @default.
- W3100412866 date "2020-01-01" @default.
- W3100412866 modified "2023-09-26" @default.
- W3100412866 title "Domain Adaptation for Food Intake Classification with Teacher/Student Learning" @default.
- W3100412866 cites W1037176813 @default.
- W3100412866 cites W1485009520 @default.
- W3100412866 cites W1509793305 @default.
- W3100412866 cites W1592410721 @default.
- W3100412866 cites W1689711448 @default.
- W3100412866 cites W1821462560 @default.
- W3100412866 cites W1922655562 @default.
- W3100412866 cites W1931662771 @default.
- W3100412866 cites W1964678094 @default.
- W3100412866 cites W2003530571 @default.
- W3100412866 cites W2004353783 @default.
- W3100412866 cites W2005708641 @default.
- W3100412866 cites W2022198541 @default.
- W3100412866 cites W2033545549 @default.
- W3100412866 cites W2047607460 @default.
- W3100412866 cites W2059995923 @default.
- W3100412866 cites W2111362445 @default.
- W3100412866 cites W2114646697 @default.
- W3100412866 cites W2114983184 @default.
- W3100412866 cites W2122897458 @default.
- W3100412866 cites W2136933783 @default.
- W3100412866 cites W2144685889 @default.
- W3100412866 cites W2161399571 @default.
- W3100412866 cites W2162226056 @default.
- W3100412866 cites W2162449135 @default.
- W3100412866 cites W2166344203 @default.
- W3100412866 cites W2332593236 @default.
- W3100412866 cites W2344284192 @default.
- W3100412866 cites W2395579298 @default.
- W3100412866 cites W2407080277 @default.
- W3100412866 cites W2508301911 @default.
- W3100412866 cites W2508418541 @default.
- W3100412866 cites W2512865187 @default.
- W3100412866 cites W2548576580 @default.
- W3100412866 cites W2755426661 @default.
- W3100412866 cites W2757028014 @default.
- W3100412866 cites W2766887854 @default.
- W3100412866 cites W2788855590 @default.
- W3100412866 cites W2798717976 @default.
- W3100412866 cites W2808022699 @default.
- W3100412866 cites W2883660395 @default.
- W3100412866 cites W2891344401 @default.
- W3100412866 cites W2903560743 @default.
- W3100412866 cites W2916979304 @default.
- W3100412866 cites W2962894366 @default.
- W3100412866 cites W2963523217 @default.
- W3100412866 cites W2964081807 @default.
- W3100412866 cites W2964288524 @default.
- W3100412866 doi "https://doi.org/10.1109/tmm.2020.3038315" @default.
- W3100412866 hasPublicationYear "2020" @default.
- W3100412866 type Work @default.
- W3100412866 sameAs 3100412866 @default.
- W3100412866 citedByCount "0" @default.
- W3100412866 crossrefType "journal-article" @default.
- W3100412866 hasAuthorship W3100412866A5005250255 @default.
- W3100412866 hasAuthorship W3100412866A5064993025 @default.
- W3100412866 hasConcept C104317684 @default.
- W3100412866 hasConcept C119857082 @default.
- W3100412866 hasConcept C120665830 @default.
- W3100412866 hasConcept C121332964 @default.
- W3100412866 hasConcept C12267149 @default.
- W3100412866 hasConcept C139807058 @default.
- W3100412866 hasConcept C149635348 @default.
- W3100412866 hasConcept C150594956 @default.
- W3100412866 hasConcept C150899416 @default.
- W3100412866 hasConcept C153180895 @default.
- W3100412866 hasConcept C154945302 @default.
- W3100412866 hasConcept C185592680 @default.
- W3100412866 hasConcept C2776434776 @default.
- W3100412866 hasConcept C2778263558 @default.
- W3100412866 hasConcept C28490314 @default.
- W3100412866 hasConcept C41008148 @default.
- W3100412866 hasConcept C52622490 @default.
- W3100412866 hasConcept C55493867 @default.
- W3100412866 hasConcept C63479239 @default.
- W3100412866 hasConcept C68115822 @default.
- W3100412866 hasConcept C76155785 @default.
- W3100412866 hasConcept C95623464 @default.
- W3100412866 hasConceptScore W3100412866C104317684 @default.
- W3100412866 hasConceptScore W3100412866C119857082 @default.
- W3100412866 hasConceptScore W3100412866C120665830 @default.
- W3100412866 hasConceptScore W3100412866C121332964 @default.
- W3100412866 hasConceptScore W3100412866C12267149 @default.
- W3100412866 hasConceptScore W3100412866C139807058 @default.
- W3100412866 hasConceptScore W3100412866C149635348 @default.
- W3100412866 hasConceptScore W3100412866C150594956 @default.
- W3100412866 hasConceptScore W3100412866C150899416 @default.
- W3100412866 hasConceptScore W3100412866C153180895 @default.
- W3100412866 hasConceptScore W3100412866C154945302 @default.
- W3100412866 hasConceptScore W3100412866C185592680 @default.
- W3100412866 hasConceptScore W3100412866C2776434776 @default.