Matches in SemOpenAlex for { <https://semopenalex.org/work/W2972980327> ?p ?o ?g. }
Showing items 1 to 83 of
83
with 100 items per page.
- W2972980327 abstract "The goal of the SHL recognition challenge 2019 is to recognize transportation modalities in a sensor placement independent manner. In this paper, the performance of shallow neural networks is benchmarked by Team Orion in such a manner on the dataset provided in the challenge, using 156 handcrafted temporal and spectral features per sensor through the application of parallel processing and out-of-memory architecture. Using scaled conjugate gradient back-propagation (SCGB) algorithm, combining classes 7 and 8 and taking 5000 frames of bag-hips-torso data from validation set, classification accuracy of 87.2% was obtained on the validation dataset of the same labels for a shallow two-layer feed-forward network. 71% accuracy was obtained on the validation set of classes 7 and 8 via transfer of 2500 frames using another shallow neural network of similar architecture. Using empirically observed variable based transfer of 7088 frames from hand validation data to training dataset, 77.5% accuracy was obtained on hand validation data for classes 1 to 7/8, and 70% classification accuracy of classes 7 and 8 via transfer of 1809 frames from hand validation data. The results illustrate how carefully crafted features coupled with empirical transfer of labeled knowledge and combination of problematic classes can tune a neural classifier to work in a new feature space." @default.
- W2972980327 created "2019-09-19" @default.
- W2972980327 creator A5004319249 @default.
- W2972980327 creator A5018591931 @default.
- W2972980327 creator A5021634779 @default.
- W2972980327 creator A5049700514 @default.
- W2972980327 creator A5056668029 @default.
- W2972980327 creator A5080895628 @default.
- W2972980327 date "2019-09-09" @default.
- W2972980327 modified "2023-10-12" @default.
- W2972980327 title "Position independent activity recognition using shallow neural architecture and empirical modeling" @default.
- W2972980327 cites W2001058334 @default.
- W2972980327 cites W2034015004 @default.
- W2972980327 cites W2051812123 @default.
- W2972980327 cites W2126125555 @default.
- W2972980327 cites W2165698076 @default.
- W2972980327 cites W2168189108 @default.
- W2972980327 cites W2485241682 @default.
- W2972980327 cites W2556328250 @default.
- W2972980327 cites W2566846788 @default.
- W2972980327 cites W2567482009 @default.
- W2972980327 cites W2592949994 @default.
- W2972980327 cites W2883074505 @default.
- W2972980327 cites W2891857646 @default.
- W2972980327 cites W2899151654 @default.
- W2972980327 cites W2899180859 @default.
- W2972980327 cites W2899424401 @default.
- W2972980327 cites W2899506323 @default.
- W2972980327 cites W2972497135 @default.
- W2972980327 doi "https://doi.org/10.1145/3341162.3345572" @default.
- W2972980327 hasPublicationYear "2019" @default.
- W2972980327 type Work @default.
- W2972980327 sameAs 2972980327 @default.
- W2972980327 citedByCount "7" @default.
- W2972980327 countsByYear W29729803272019 @default.
- W2972980327 countsByYear W29729803272020 @default.
- W2972980327 countsByYear W29729803272022 @default.
- W2972980327 crossrefType "proceedings-article" @default.
- W2972980327 hasAuthorship W2972980327A5004319249 @default.
- W2972980327 hasAuthorship W2972980327A5018591931 @default.
- W2972980327 hasAuthorship W2972980327A5021634779 @default.
- W2972980327 hasAuthorship W2972980327A5049700514 @default.
- W2972980327 hasAuthorship W2972980327A5056668029 @default.
- W2972980327 hasAuthorship W2972980327A5080895628 @default.
- W2972980327 hasConcept C119857082 @default.
- W2972980327 hasConcept C124101348 @default.
- W2972980327 hasConcept C150899416 @default.
- W2972980327 hasConcept C153180895 @default.
- W2972980327 hasConcept C154945302 @default.
- W2972980327 hasConcept C177264268 @default.
- W2972980327 hasConcept C199360897 @default.
- W2972980327 hasConcept C41008148 @default.
- W2972980327 hasConcept C50644808 @default.
- W2972980327 hasConcept C58489278 @default.
- W2972980327 hasConcept C95623464 @default.
- W2972980327 hasConceptScore W2972980327C119857082 @default.
- W2972980327 hasConceptScore W2972980327C124101348 @default.
- W2972980327 hasConceptScore W2972980327C150899416 @default.
- W2972980327 hasConceptScore W2972980327C153180895 @default.
- W2972980327 hasConceptScore W2972980327C154945302 @default.
- W2972980327 hasConceptScore W2972980327C177264268 @default.
- W2972980327 hasConceptScore W2972980327C199360897 @default.
- W2972980327 hasConceptScore W2972980327C41008148 @default.
- W2972980327 hasConceptScore W2972980327C50644808 @default.
- W2972980327 hasConceptScore W2972980327C58489278 @default.
- W2972980327 hasConceptScore W2972980327C95623464 @default.
- W2972980327 hasLocation W29729803271 @default.
- W2972980327 hasOpenAccess W2972980327 @default.
- W2972980327 hasPrimaryLocation W29729803271 @default.
- W2972980327 hasRelatedWork W2362198218 @default.
- W2972980327 hasRelatedWork W2391251536 @default.
- W2972980327 hasRelatedWork W2886688859 @default.
- W2972980327 hasRelatedWork W2961085424 @default.
- W2972980327 hasRelatedWork W2979740303 @default.
- W2972980327 hasRelatedWork W3135401135 @default.
- W2972980327 hasRelatedWork W3165580226 @default.
- W2972980327 hasRelatedWork W3201126466 @default.
- W2972980327 hasRelatedWork W4282827391 @default.
- W2972980327 hasRelatedWork W4386828785 @default.
- W2972980327 isParatext "false" @default.
- W2972980327 isRetracted "false" @default.
- W2972980327 magId "2972980327" @default.
- W2972980327 workType "article" @default.