FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W3025821620> ?p ?o ?g. }

• W3025821620 endingPage "90554" @default.
• W3025821620 startingPage "90542" @default.
• W3025821620 abstract "Deep learning has been widely used for implementing human activity recognition from wearable sensors like inertial measurement units. The performance of deep activity recognition is heavily affected by the amount and variability of the labeled data available for training the deep learning models. On the other hand, it is costly and time-consuming to collect and label data. Given limited training data, it is hard to maintain high performance across a wide range of subjects, due to the differences in the underlying data distribution of the training and the testing sets. In this work, we develop a novel solution that applies adversarial learning to improve cross-subject performance by generating training data that mimic artificial subjects - i.e. through data augmentation - and enforcing the activity classifier to ignore subject-dependent information. Contrary to domain adaptation methods, our solution does not utilize any data from subjects of the test set (or target domain). Furthermore, our solution is versatile as it can be utilized together with any deep neural network as the classifier. Considering the open dataset PAMAP2, nearly 10% higher cross-subject performance in terms of F1-score can be achieved when training a CNN-LSTM-based classifier with our solution. A performance gain of 5% is also observed when our solution is applied to a state-of-the-art HAR classifier composed of a combination of inception neural network and recurrent neural network. We also investigate different influencing factors of classification performance (i.e. selection of sensor modalities, sampling rates and the number of subjects in the training data), and summarize a practical guideline for implementing deep learning solutions for sensor-based human activity recognition." @default.
• W3025821620 created "2020-05-21" @default.
• W3025821620 creator A5008784833 @default.
• W3025821620 creator A5069437467 @default.
• W3025821620 date "2020-01-01" @default.
• W3025821620 modified "2023-09-26" @default.
• W3025821620 title "Improving Cross-Subject Activity Recognition via Adversarial Learning" @default.
• W3025821620 cites W2019342228 @default.
• W3025821620 cites W2026297770 @default.
• W3025821620 cites W2073401630 @default.
• W3025821620 cites W2128892560 @default.
• W3025821620 cites W2270470215 @default.
• W3025821620 cites W2548335893 @default.
• W3025821620 cites W2593768305 @default.
• W3025821620 cites W2594230123 @default.
• W3025821620 cites W2604630936 @default.
• W3025821620 cites W2751594996 @default.
• W3025821620 cites W2752848408 @default.
• W3025821620 cites W2756073160 @default.
• W3025821620 cites W2770091665 @default.
• W3025821620 cites W2771247593 @default.
• W3025821620 cites W2771251325 @default.
• W3025821620 cites W2775631770 @default.
• W3025821620 cites W2786808285 @default.
• W3025821620 cites W2796127628 @default.
• W3025821620 cites W2796447146 @default.
• W3025821620 cites W2801049060 @default.
• W3025821620 cites W2851629429 @default.
• W3025821620 cites W2883074505 @default.
• W3025821620 cites W2887355508 @default.
• W3025821620 cites W2888680699 @default.
• W3025821620 cites W2894702700 @default.
• W3025821620 cites W2897132279 @default.
• W3025821620 cites W2897551993 @default.
• W3025821620 cites W2907255073 @default.
• W3025821620 cites W2954350473 @default.
• W3025821620 cites W2962793481 @default.
• W3025821620 cites W2963935481 @default.
• W3025821620 cites W2964092203 @default.
• W3025821620 cites W2973200074 @default.
• W3025821620 cites W2973630397 @default.
• W3025821620 doi "https://doi.org/10.1109/access.2020.2993818" @default.
• W3025821620 hasPublicationYear "2020" @default.
• W3025821620 type Work @default.
• W3025821620 sameAs 3025821620 @default.
• W3025821620 citedByCount "7" @default.
• W3025821620 countsByYear W30258216202021 @default.
• W3025821620 countsByYear W30258216202022 @default.
• W3025821620 countsByYear W30258216202023 @default.
• W3025821620 crossrefType "journal-article" @default.
• W3025821620 hasAuthorship W3025821620A5008784833 @default.
• W3025821620 hasAuthorship W3025821620A5069437467 @default.
• W3025821620 hasBestOaLocation W30258216201 @default.
• W3025821620 hasConcept C108583219 @default.
• W3025821620 hasConcept C119857082 @default.
• W3025821620 hasConcept C121687571 @default.
• W3025821620 hasConcept C149635348 @default.
• W3025821620 hasConcept C150594956 @default.
• W3025821620 hasConcept C154945302 @default.
• W3025821620 hasConcept C16910744 @default.
• W3025821620 hasConcept C169903167 @default.
• W3025821620 hasConcept C199360897 @default.
• W3025821620 hasConcept C2776145971 @default.
• W3025821620 hasConcept C2776434776 @default.
• W3025821620 hasConcept C2984842247 @default.
• W3025821620 hasConcept C37736160 @default.
• W3025821620 hasConcept C41008148 @default.
• W3025821620 hasConcept C50644808 @default.
• W3025821620 hasConcept C51632099 @default.
• W3025821620 hasConcept C95623464 @default.
• W3025821620 hasConceptScore W3025821620C108583219 @default.
• W3025821620 hasConceptScore W3025821620C119857082 @default.
• W3025821620 hasConceptScore W3025821620C121687571 @default.
• W3025821620 hasConceptScore W3025821620C149635348 @default.
• W3025821620 hasConceptScore W3025821620C150594956 @default.
• W3025821620 hasConceptScore W3025821620C154945302 @default.
• W3025821620 hasConceptScore W3025821620C16910744 @default.
• W3025821620 hasConceptScore W3025821620C169903167 @default.
• W3025821620 hasConceptScore W3025821620C199360897 @default.
• W3025821620 hasConceptScore W3025821620C2776145971 @default.
• W3025821620 hasConceptScore W3025821620C2776434776 @default.
• W3025821620 hasConceptScore W3025821620C2984842247 @default.
• W3025821620 hasConceptScore W3025821620C37736160 @default.
• W3025821620 hasConceptScore W3025821620C41008148 @default.
• W3025821620 hasConceptScore W3025821620C50644808 @default.
• W3025821620 hasConceptScore W3025821620C51632099 @default.
• W3025821620 hasConceptScore W3025821620C95623464 @default.
• W3025821620 hasFunder F4320328501 @default.
• W3025821620 hasLocation W30258216201 @default.
• W3025821620 hasLocation W30258216202 @default.
• W3025821620 hasOpenAccess W3025821620 @default.
• W3025821620 hasPrimaryLocation W30258216201 @default.
• W3025821620 hasRelatedWork W2742051693 @default.
• W3025821620 hasRelatedWork W2888680699 @default.
• W3025821620 hasRelatedWork W3025821620 @default.
• W3025821620 hasRelatedWork W3101081936 @default.
• W3025821620 hasRelatedWork W3158264953 @default.
• W3025821620 hasRelatedWork W3186065094 @default.

• next