FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4306913592> ?p ?o ?g. }

• W4306913592 endingPage "1249" @default.
• W4306913592 startingPage "1239" @default.
• W4306913592 abstract "Brain-computer interfaces (BCIs) is promising in interacting with machines through electroencephalogram (EEG) signal. The compact end-to-end neural network model for generalized BCIs, EEGNet, has been implemented in hardware to get near sensor intelligence, but without enough efficiency. To utilize EEGNet in low-power wearable device for long-term use, this paper proposes an efficient EEGNet inference accelerator. Firstly, the EEGNet model is compressed by embedded channel selection, normalization merging, and product quantization. The customized accelerator based on the compressed model is then designed. The multilayer convolutions are achieved by reusing multiplying-accumulators and processing elements (PEs) to minimize area of logic circuits, and the weights and intermediate results are quantized to minimize memory sizes. The PEs are clock-gated to save power. Experimental results in FPGA on three datasets show the good generalizing ability of the proposed design across three BCI diagrams, which only consumes 3.31% area and 1.35% power compared to the one-to-one parallel design. The speedup factors of 1.4, 3.5, and 3.7 are achieved by embedded channel selection with negligible loss of accuracy (-0.80%). The presented accelerator is also synthesized in 65 nm CMOS low power (LP) process and consumes 0.23M gates, 24.4 ms/inference, 0.267 mJ/inference, which is 87.22% more efficient than the implementation of EEGNet in a RISC-V MCU realized in 40 nm CMOS LP process in terms of area, and 20.77% more efficient in terms of energy efficiency on BCIC-IV-2a dataset." @default.
• W4306913592 created "2022-10-21" @default.
• W4306913592 creator A5023015877 @default.
• W4306913592 creator A5039575274 @default.
• W4306913592 creator A5087187152 @default.
• W4306913592 creator A5089503849 @default.
• W4306913592 date "2022-12-01" @default.
• W4306913592 modified "2023-10-18" @default.
• W4306913592 title "An Efficient Model-Compressed EEGNet Accelerator for Generalized Brain-Computer Interfaces With Near Sensor Intelligence" @default.
• W4306913592 cites W2099860996 @default.
• W4306913592 cites W2106006415 @default.
• W4306913592 cites W2119163516 @default.
• W4306913592 cites W2124509324 @default.
• W4306913592 cites W2130847623 @default.
• W4306913592 cites W2162399638 @default.
• W4306913592 cites W2169918686 @default.
• W4306913592 cites W2194775991 @default.
• W4306913592 cites W2218506909 @default.
• W4306913592 cites W2276486856 @default.
• W4306913592 cites W2507528282 @default.
• W4306913592 cites W2602279467 @default.
• W4306913592 cites W2741907166 @default.
• W4306913592 cites W2765817727 @default.
• W4306913592 cites W2800566345 @default.
• W4306913592 cites W2895947121 @default.
• W4306913592 cites W2919403121 @default.
• W4306913592 cites W2946485102 @default.
• W4306913592 cites W2946783148 @default.
• W4306913592 cites W2963232339 @default.
• W4306913592 cites W2997540115 @default.
• W4306913592 cites W2999206323 @default.
• W4306913592 cites W3009223401 @default.
• W4306913592 cites W3013195849 @default.
• W4306913592 cites W3027581678 @default.
• W4306913592 cites W3041051645 @default.
• W4306913592 cites W3080578087 @default.
• W4306913592 cites W3096176982 @default.
• W4306913592 cites W3097874358 @default.
• W4306913592 cites W3098961931 @default.
• W4306913592 cites W3102455230 @default.
• W4306913592 cites W3104225791 @default.
• W4306913592 cites W3126607918 @default.
• W4306913592 cites W3158014161 @default.
• W4306913592 cites W3173569316 @default.
• W4306913592 cites W3178956316 @default.
• W4306913592 cites W3198315730 @default.
• W4306913592 cites W4213238843 @default.
• W4306913592 doi "https://doi.org/10.1109/tbcas.2022.3215962" @default.
• W4306913592 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/36264734" @default.
• W4306913592 hasPublicationYear "2022" @default.
• W4306913592 type Work @default.
• W4306913592 citedByCount "1" @default.
• W4306913592 countsByYear W43069135922023 @default.
• W4306913592 crossrefType "journal-article" @default.
• W4306913592 hasAuthorship W4306913592A5023015877 @default.
• W4306913592 hasAuthorship W4306913592A5039575274 @default.
• W4306913592 hasAuthorship W4306913592A5087187152 @default.
• W4306913592 hasAuthorship W4306913592A5089503849 @default.
• W4306913592 hasConcept C11413529 @default.
• W4306913592 hasConcept C119599485 @default.
• W4306913592 hasConcept C127413603 @default.
• W4306913592 hasConcept C13164978 @default.
• W4306913592 hasConcept C173608175 @default.
• W4306913592 hasConcept C24326235 @default.
• W4306913592 hasConcept C2742236 @default.
• W4306913592 hasConcept C28855332 @default.
• W4306913592 hasConcept C41008148 @default.
• W4306913592 hasConcept C42935608 @default.
• W4306913592 hasConcept C46362747 @default.
• W4306913592 hasConcept C68339613 @default.
• W4306913592 hasConcept C9390403 @default.
• W4306913592 hasConceptScore W4306913592C11413529 @default.
• W4306913592 hasConceptScore W4306913592C119599485 @default.
• W4306913592 hasConceptScore W4306913592C127413603 @default.
• W4306913592 hasConceptScore W4306913592C13164978 @default.
• W4306913592 hasConceptScore W4306913592C173608175 @default.
• W4306913592 hasConceptScore W4306913592C24326235 @default.
• W4306913592 hasConceptScore W4306913592C2742236 @default.
• W4306913592 hasConceptScore W4306913592C28855332 @default.
• W4306913592 hasConceptScore W4306913592C41008148 @default.
• W4306913592 hasConceptScore W4306913592C42935608 @default.
• W4306913592 hasConceptScore W4306913592C46362747 @default.
• W4306913592 hasConceptScore W4306913592C68339613 @default.
• W4306913592 hasConceptScore W4306913592C9390403 @default.
• W4306913592 hasFunder F4320321001 @default.
• W4306913592 hasFunder F4320335787 @default.
• W4306913592 hasIssue "6" @default.
• W4306913592 hasLocation W43069135921 @default.
• W4306913592 hasLocation W43069135922 @default.
• W4306913592 hasOpenAccess W4306913592 @default.
• W4306913592 hasPrimaryLocation W43069135921 @default.
• W4306913592 hasRelatedWork W2365743651 @default.
• W4306913592 hasRelatedWork W2802661370 @default.
• W4306913592 hasRelatedWork W2926371525 @default.
• W4306913592 hasRelatedWork W2945182031 @default.
• W4306913592 hasRelatedWork W3211065149 @default.
• W4306913592 hasRelatedWork W4288375792 @default.
• W4306913592 hasRelatedWork W4290858055 @default.

• next