Matches in SemOpenAlex for { <https://semopenalex.org/work/W2810816559> ?p ?o ?g. }
Showing items 1 to 79 of
79
with 100 items per page.
- W2810816559 abstract "Machine learning classifiers using surface electromyography are important for human-machine interfacing and device control. Conventional classifiers such as support vector machines (SVMs) use manually extracted features based on e.g. wavelets. These features tend to be fixed and non-person specific, which is a key limitation due to high person-to-person variability of myography signals. Deep neural networks, by contrast, can automatically extract person specific features - an important advantage. However, deep neural networks typically have the drawback of large numbers of parameters, requiring large training data sets and powerful hardware not suited to embedded systems. This paper solves these problems by introducing a compact deep neural network architecture that is much smaller than existing counterparts. The performance of the compact deep net is benchmarked against an SVM and compared to other contemporary architectures across 10 human subjects, comparing Myo and Delsys Trigno electrode sets. The accuracy of the compact deep net was found to be 84.2±.06% versus 70.5±0.07% for the SVM on the Myo, and 80.3±.07% versus 67.8±0.09% for the Delsys system, demonstrating the superior effectiveness of the proposed compact network, which had just 5,889 parameters - orders of magnitude less than some contemporary alternatives in this domain while maintaining better performance." @default.
- W2810816559 created "2018-07-10" @default.
- W2810816559 creator A5023642229 @default.
- W2810816559 creator A5071097412 @default.
- W2810816559 creator A5077789614 @default.
- W2810816559 date "2018-08-01" @default.
- W2810816559 modified "2023-10-05" @default.
- W2810816559 title "Compact Deep Neural Networks for Computationally Efficient Gesture Classification From Electromyography Signals" @default.
- W2810816559 cites W1992456026 @default.
- W2810816559 cites W2008437881 @default.
- W2810816559 cites W2066327120 @default.
- W2810816559 cites W2073476715 @default.
- W2810816559 cites W2082480549 @default.
- W2810816559 cites W2092126505 @default.
- W2810816559 cites W2106526692 @default.
- W2810816559 cites W2133935519 @default.
- W2810816559 cites W2158728671 @default.
- W2810816559 cites W2170505850 @default.
- W2810816559 cites W2171219007 @default.
- W2810816559 cites W2295398032 @default.
- W2810816559 cites W2516710120 @default.
- W2810816559 cites W2555541061 @default.
- W2810816559 cites W2556533447 @default.
- W2810816559 cites W2684229413 @default.
- W2810816559 cites W2762706434 @default.
- W2810816559 cites W2787157199 @default.
- W2810816559 cites W2919115771 @default.
- W2810816559 doi "https://doi.org/10.1109/biorob.2018.8487853" @default.
- W2810816559 hasPublicationYear "2018" @default.
- W2810816559 type Work @default.
- W2810816559 sameAs 2810816559 @default.
- W2810816559 citedByCount "11" @default.
- W2810816559 countsByYear W28108165592019 @default.
- W2810816559 countsByYear W28108165592020 @default.
- W2810816559 countsByYear W28108165592021 @default.
- W2810816559 countsByYear W28108165592022 @default.
- W2810816559 countsByYear W28108165592023 @default.
- W2810816559 crossrefType "proceedings-article" @default.
- W2810816559 hasAuthorship W2810816559A5023642229 @default.
- W2810816559 hasAuthorship W2810816559A5071097412 @default.
- W2810816559 hasAuthorship W2810816559A5077789614 @default.
- W2810816559 hasBestOaLocation W28108165592 @default.
- W2810816559 hasConcept C108583219 @default.
- W2810816559 hasConcept C119857082 @default.
- W2810816559 hasConcept C12267149 @default.
- W2810816559 hasConcept C153180895 @default.
- W2810816559 hasConcept C154945302 @default.
- W2810816559 hasConcept C2776303644 @default.
- W2810816559 hasConcept C41008148 @default.
- W2810816559 hasConcept C50644808 @default.
- W2810816559 hasConcept C9390403 @default.
- W2810816559 hasConceptScore W2810816559C108583219 @default.
- W2810816559 hasConceptScore W2810816559C119857082 @default.
- W2810816559 hasConceptScore W2810816559C12267149 @default.
- W2810816559 hasConceptScore W2810816559C153180895 @default.
- W2810816559 hasConceptScore W2810816559C154945302 @default.
- W2810816559 hasConceptScore W2810816559C2776303644 @default.
- W2810816559 hasConceptScore W2810816559C41008148 @default.
- W2810816559 hasConceptScore W2810816559C50644808 @default.
- W2810816559 hasConceptScore W2810816559C9390403 @default.
- W2810816559 hasLocation W28108165591 @default.
- W2810816559 hasLocation W28108165592 @default.
- W2810816559 hasLocation W28108165593 @default.
- W2810816559 hasOpenAccess W2810816559 @default.
- W2810816559 hasPrimaryLocation W28108165591 @default.
- W2810816559 hasRelatedWork W2136184105 @default.
- W2810816559 hasRelatedWork W3013515612 @default.
- W2810816559 hasRelatedWork W4223943233 @default.
- W2810816559 hasRelatedWork W4225161397 @default.
- W2810816559 hasRelatedWork W4312200629 @default.
- W2810816559 hasRelatedWork W4360585206 @default.
- W2810816559 hasRelatedWork W4364306694 @default.
- W2810816559 hasRelatedWork W4380075502 @default.
- W2810816559 hasRelatedWork W4380086463 @default.
- W2810816559 hasRelatedWork W2345184372 @default.
- W2810816559 isParatext "false" @default.
- W2810816559 isRetracted "false" @default.
- W2810816559 magId "2810816559" @default.
- W2810816559 workType "article" @default.