Matches in SemOpenAlex for { <https://semopenalex.org/work/W4377864771> ?p ?o ?g. }
Showing items 1 to 71 of
71
with 100 items per page.
- W4377864771 abstract "In this work, we propose an open-source scalable end-to-end RTL framework FieldHAR, for complex human activity recognition (HAR) from heterogeneous sensors using artificial neural networks (ANN) optimized for FPGA or ASIC integration. FieldHAR aims to address the lack of apparatus to transform complex HAR methodologies often limited to offline evaluation to efficient run-time edge applications. The framework uses parallel sensor interfaces and integer-based multi-branch convolutional neural networks (CNNs) to support flexible modality extensions with synchronous sampling at the maximum rate of each sensor. To validate the framework, we used a sensor-rich kitchen scenario HAR application which was demonstrated in a previous offline study. Through resource-aware optimizations, with FieldHAR the entire RTL solution was created from data acquisition to ANN inference taking as low as 25% logic elements and 2% memory bits of a low-end Cyclone IV FPGA and less than 1% accuracy loss from the original FP32 precision offline study. The RTL implementation also shows advantages over MCU-based solutions, including superior data acquisition performance and virtually eliminating ANN inference bottleneck." @default.
- W4377864771 created "2023-05-24" @default.
- W4377864771 creator A5011877804 @default.
- W4377864771 creator A5018144921 @default.
- W4377864771 creator A5033088986 @default.
- W4377864771 creator A5033091196 @default.
- W4377864771 creator A5057986515 @default.
- W4377864771 creator A5063453660 @default.
- W4377864771 creator A5072694516 @default.
- W4377864771 creator A5079181491 @default.
- W4377864771 date "2023-05-22" @default.
- W4377864771 modified "2023-10-18" @default.
- W4377864771 title "FieldHAR: A Fully Integrated End-to-end RTL Framework for Human Activity Recognition with Neural Networks from Heterogeneous Sensors" @default.
- W4377864771 doi "https://doi.org/10.48550/arxiv.2305.12824" @default.
- W4377864771 hasPublicationYear "2023" @default.
- W4377864771 type Work @default.
- W4377864771 citedByCount "0" @default.
- W4377864771 crossrefType "posted-content" @default.
- W4377864771 hasAuthorship W4377864771A5011877804 @default.
- W4377864771 hasAuthorship W4377864771A5018144921 @default.
- W4377864771 hasAuthorship W4377864771A5033088986 @default.
- W4377864771 hasAuthorship W4377864771A5033091196 @default.
- W4377864771 hasAuthorship W4377864771A5057986515 @default.
- W4377864771 hasAuthorship W4377864771A5063453660 @default.
- W4377864771 hasAuthorship W4377864771A5072694516 @default.
- W4377864771 hasAuthorship W4377864771A5079181491 @default.
- W4377864771 hasBestOaLocation W43778647711 @default.
- W4377864771 hasConcept C108583219 @default.
- W4377864771 hasConcept C118524514 @default.
- W4377864771 hasConcept C149635348 @default.
- W4377864771 hasConcept C154945302 @default.
- W4377864771 hasConcept C2776214188 @default.
- W4377864771 hasConcept C2780513914 @default.
- W4377864771 hasConcept C41008148 @default.
- W4377864771 hasConcept C42935608 @default.
- W4377864771 hasConcept C48044578 @default.
- W4377864771 hasConcept C50644808 @default.
- W4377864771 hasConcept C77088390 @default.
- W4377864771 hasConcept C77390884 @default.
- W4377864771 hasConcept C81363708 @default.
- W4377864771 hasConcept C9390403 @default.
- W4377864771 hasConceptScore W4377864771C108583219 @default.
- W4377864771 hasConceptScore W4377864771C118524514 @default.
- W4377864771 hasConceptScore W4377864771C149635348 @default.
- W4377864771 hasConceptScore W4377864771C154945302 @default.
- W4377864771 hasConceptScore W4377864771C2776214188 @default.
- W4377864771 hasConceptScore W4377864771C2780513914 @default.
- W4377864771 hasConceptScore W4377864771C41008148 @default.
- W4377864771 hasConceptScore W4377864771C42935608 @default.
- W4377864771 hasConceptScore W4377864771C48044578 @default.
- W4377864771 hasConceptScore W4377864771C50644808 @default.
- W4377864771 hasConceptScore W4377864771C77088390 @default.
- W4377864771 hasConceptScore W4377864771C77390884 @default.
- W4377864771 hasConceptScore W4377864771C81363708 @default.
- W4377864771 hasConceptScore W4377864771C9390403 @default.
- W4377864771 hasLocation W43778647711 @default.
- W4377864771 hasOpenAccess W4377864771 @default.
- W4377864771 hasPrimaryLocation W43778647711 @default.
- W4377864771 hasRelatedWork W1589309932 @default.
- W4377864771 hasRelatedWork W1975010174 @default.
- W4377864771 hasRelatedWork W2114354660 @default.
- W4377864771 hasRelatedWork W2134422574 @default.
- W4377864771 hasRelatedWork W2954307240 @default.
- W4377864771 hasRelatedWork W2966987601 @default.
- W4377864771 hasRelatedWork W2984236338 @default.
- W4377864771 hasRelatedWork W3010492628 @default.
- W4377864771 hasRelatedWork W4361251788 @default.
- W4377864771 hasRelatedWork W2506672464 @default.
- W4377864771 isParatext "false" @default.
- W4377864771 isRetracted "false" @default.
- W4377864771 workType "article" @default.