FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387010474> ?p ?o ?g. }

• W4387010474 endingPage "106669" @default.
• W4387010474 startingPage "106650" @default.
• W4387010474 abstract "Human activity recognition (HAR) has applications ranging from security to healthcare. Typically these systems are composed of data acquisition and activity recognition models. In this work, we compared the accuracy of two acquisition systems: Inertial Measurement Units (IMUs) vs Movement Analysis Systems (MAS). We trained models to recognize arm exercises using state-of-the-art deep learning architectures and compared their accuracy. MAS uses a camera array and reflective markers. IMU uses accelerometers, gyroscopes, and magnetometers. Sensors of both systems were attached to different locations of the upper limb. We captured and annotated 3 datasets, each one using both systems simultaneously. For activity recognition, we trained 8 architectures, each one with different operations and layers configurations. The best architectures were a combination of CNN, LSTM, and Transformer achieving test accuracy from 89% to 99% on average. We evaluated how feature selection reduced the sensors required. We found IMU and MAS data were able to distinguish correctly the arm exercises. CNN layers at the beginning produced better accuracy on challenging datasets. IMU had advantages over other aquisition systems for activity recognition. We analyzed the relations between models accuracy, signal waveforms, signals correlation, sampling rate, exercise duration, and window size. Finally, we proposed the use of a single IMU located at the wrist and a variable-size window extraction." @default.
• W4387010474 created "2023-09-26" @default.
• W4387010474 creator A5033288172 @default.
• W4387010474 creator A5042924715 @default.
• W4387010474 creator A5066190474 @default.
• W4387010474 creator A5072300632 @default.
• W4387010474 creator A5092934146 @default.
• W4387010474 creator A5092934147 @default.
• W4387010474 date "2023-01-01" @default.
• W4387010474 modified "2023-10-09" @default.
• W4387010474 title "Accuracy comparison of CNN, LSTM, and Transformer for activity recognition using IMU and visual markers" @default.
• W4387010474 cites W123295786 @default.
• W4387010474 cites W1689711448 @default.
• W4387010474 cites W1930624869 @default.
• W4387010474 cites W1973376993 @default.
• W4387010474 cites W1988066034 @default.
• W4387010474 cites W2002577311 @default.
• W4387010474 cites W2009398857 @default.
• W4387010474 cites W2064327970 @default.
• W4387010474 cites W2064675550 @default.
• W4387010474 cites W2120133484 @default.
• W4387010474 cites W2164760349 @default.
• W4387010474 cites W2511719117 @default.
• W4387010474 cites W2514173981 @default.
• W4387010474 cites W2596563802 @default.
• W4387010474 cites W2765473510 @default.
• W4387010474 cites W2886735509 @default.
• W4387010474 cites W2911964244 @default.
• W4387010474 cites W2917819557 @default.
• W4387010474 cites W2922355425 @default.
• W4387010474 cites W2927123024 @default.
• W4387010474 cites W2946273500 @default.
• W4387010474 cites W2972818416 @default.
• W4387010474 cites W2979826702 @default.
• W4387010474 cites W3002496996 @default.
• W4387010474 cites W3022796439 @default.
• W4387010474 cites W3082120068 @default.
• W4387010474 cites W3089186933 @default.
• W4387010474 cites W3091225957 @default.
• W4387010474 cites W3094625321 @default.
• W4387010474 cites W3134689613 @default.
• W4387010474 cites W3174752903 @default.
• W4387010474 cites W3211040285 @default.
• W4387010474 cites W3215807065 @default.
• W4387010474 cites W4214843096 @default.
• W4387010474 cites W4220659807 @default.
• W4387010474 cites W4249972823 @default.
• W4387010474 cites W4283273834 @default.
• W4387010474 cites W4289172806 @default.
• W4387010474 cites W4290635396 @default.
• W4387010474 cites W4308822715 @default.
• W4387010474 cites W4313830062 @default.
• W4387010474 cites W4322743576 @default.
• W4387010474 cites W4379537994 @default.
• W4387010474 doi "https://doi.org/10.1109/access.2023.3318563" @default.
• W4387010474 hasPublicationYear "2023" @default.
• W4387010474 type Work @default.
• W4387010474 citedByCount "0" @default.
• W4387010474 crossrefType "journal-article" @default.
• W4387010474 hasAuthorship W4387010474A5033288172 @default.
• W4387010474 hasAuthorship W4387010474A5042924715 @default.
• W4387010474 hasAuthorship W4387010474A5066190474 @default.
• W4387010474 hasAuthorship W4387010474A5072300632 @default.
• W4387010474 hasAuthorship W4387010474A5092934146 @default.
• W4387010474 hasAuthorship W4387010474A5092934147 @default.
• W4387010474 hasBestOaLocation W43870104741 @default.
• W4387010474 hasConcept C111919701 @default.
• W4387010474 hasConcept C121332964 @default.
• W4387010474 hasConcept C121687571 @default.
• W4387010474 hasConcept C127413603 @default.
• W4387010474 hasConcept C146978453 @default.
• W4387010474 hasConcept C151233233 @default.
• W4387010474 hasConcept C153180895 @default.
• W4387010474 hasConcept C154945302 @default.
• W4387010474 hasConcept C158488048 @default.
• W4387010474 hasConcept C31972630 @default.
• W4387010474 hasConcept C41008148 @default.
• W4387010474 hasConcept C52622490 @default.
• W4387010474 hasConcept C62520636 @default.
• W4387010474 hasConcept C79061980 @default.
• W4387010474 hasConcept C89805583 @default.
• W4387010474 hasConceptScore W4387010474C111919701 @default.
• W4387010474 hasConceptScore W4387010474C121332964 @default.
• W4387010474 hasConceptScore W4387010474C121687571 @default.
• W4387010474 hasConceptScore W4387010474C127413603 @default.
• W4387010474 hasConceptScore W4387010474C146978453 @default.
• W4387010474 hasConceptScore W4387010474C151233233 @default.
• W4387010474 hasConceptScore W4387010474C153180895 @default.
• W4387010474 hasConceptScore W4387010474C154945302 @default.
• W4387010474 hasConceptScore W4387010474C158488048 @default.
• W4387010474 hasConceptScore W4387010474C31972630 @default.
• W4387010474 hasConceptScore W4387010474C41008148 @default.
• W4387010474 hasConceptScore W4387010474C52622490 @default.
• W4387010474 hasConceptScore W4387010474C62520636 @default.
• W4387010474 hasConceptScore W4387010474C79061980 @default.
• W4387010474 hasConceptScore W4387010474C89805583 @default.
• W4387010474 hasFunder F4320307764 @default.
• W4387010474 hasFunder F4320315062 @default.

• next