FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4319660302> ?p ?o ?g. }

• W4319660302 endingPage "014010" @default.
• W4319660302 startingPage "014010" @default.
• W4319660302 abstract "Abstract The vast majority of studies that process and analyze neural signals are conducted on cloud computing resources, which is often necessary for the demanding requirements of deep neural network workloads. However, applications such as epileptic seizure detection stand to benefit from edge devices that can securely analyze sensitive medical data in a real-time and personalised manner. In this work, we propose a novel neuromorphic computing approach to seizure detection using a surrogate gradient-based deep spiking neural network (SNN), which consists of a novel spiking ConvLSTM unit. We have trained, validated, and rigorously tested the proposed SNN model across three publicly accessible datasets, including Boston Children’s Hospital–MIT (CHB-MIT) dataset from the U.S., and the Freiburg (FB) and EPILEPSIAE intracranial electroencephalogram datasets from Germany. The average leave-one-out cross-validation area under the curve score for FB, CHB-MIT and EPILEPSIAE datasets can reach 92.7 <?CDATA $%$?> <mml:math xmlns:mml=http://www.w3.org/1998/Math/MathML overflow=scroll> <mml:mi mathvariant=normal>%</mml:mi> </mml:math> , 89.0 <?CDATA $%$?> <mml:math xmlns:mml=http://www.w3.org/1998/Math/MathML overflow=scroll> <mml:mi mathvariant=normal>%</mml:mi> </mml:math> , and 81.1 <?CDATA $%$?> <mml:math xmlns:mml=http://www.w3.org/1998/Math/MathML overflow=scroll> <mml:mi mathvariant=normal>%</mml:mi> </mml:math> , respectively, while the computational overhead and energy consumption are significantly reduced when compared to alternative state-of-the-art models, showing the potential for building an accurate hardware-friendly, low-power neuromorphic system. This is the first feasibility study using a deep SNN for seizure detection on several reliable public datasets." @default.
• W4319660302 created "2023-02-10" @default.
• W4319660302 creator A5005904353 @default.
• W4319660302 creator A5055081506 @default.
• W4319660302 creator A5065017416 @default.
• W4319660302 creator A5070106809 @default.
• W4319660302 creator A5077867821 @default.
• W4319660302 date "2023-02-24" @default.
• W4319660302 modified "2023-09-30" @default.
• W4319660302 title "Neuromorphic deep spiking neural networks for seizure detection" @default.
• W4319660302 cites W1920696238 @default.
• W4319660302 cites W1978437325 @default.
• W4319660302 cites W2016854448 @default.
• W4319660302 cites W2024482587 @default.
• W4319660302 cites W2080982747 @default.
• W4319660302 cites W2086848249 @default.
• W4319660302 cites W2104930442 @default.
• W4319660302 cites W2114942458 @default.
• W4319660302 cites W2128011414 @default.
• W4319660302 cites W2171266607 @default.
• W4319660302 cites W2292324092 @default.
• W4319660302 cites W2774975003 @default.
• W4319660302 cites W2783525259 @default.
• W4319660302 cites W2792846986 @default.
• W4319660302 cites W2805290054 @default.
• W4319660302 cites W2915978837 @default.
• W4319660302 cites W2963290013 @default.
• W4319660302 cites W2984844508 @default.
• W4319660302 cites W2990793844 @default.
• W4319660302 cites W3016911444 @default.
• W4319660302 cites W3021793483 @default.
• W4319660302 cites W3033564916 @default.
• W4319660302 cites W3086758027 @default.
• W4319660302 cites W3153513446 @default.
• W4319660302 cites W3165430704 @default.
• W4319660302 cites W3213168237 @default.
• W4319660302 cites W4210735738 @default.
• W4319660302 cites W4221069728 @default.
• W4319660302 cites W4231972715 @default.
• W4319660302 cites W4236868170 @default.
• W4319660302 cites W4289526576 @default.
• W4319660302 cites W4312081476 @default.
• W4319660302 doi "https://doi.org/10.1088/2634-4386/acbab8" @default.
• W4319660302 hasPublicationYear "2023" @default.
• W4319660302 type Work @default.
• W4319660302 citedByCount "3" @default.
• W4319660302 countsByYear W43196603022023 @default.
• W4319660302 crossrefType "journal-article" @default.
• W4319660302 hasAuthorship W4319660302A5005904353 @default.
• W4319660302 hasAuthorship W4319660302A5055081506 @default.
• W4319660302 hasAuthorship W4319660302A5065017416 @default.
• W4319660302 hasAuthorship W4319660302A5070106809 @default.
• W4319660302 hasAuthorship W4319660302A5077867821 @default.
• W4319660302 hasBestOaLocation W43196603021 @default.
• W4319660302 hasConcept C11413529 @default.
• W4319660302 hasConcept C11731999 @default.
• W4319660302 hasConcept C119857082 @default.
• W4319660302 hasConcept C151927369 @default.
• W4319660302 hasConcept C154945302 @default.
• W4319660302 hasConcept C166957645 @default.
• W4319660302 hasConcept C2781324535 @default.
• W4319660302 hasConcept C41008148 @default.
• W4319660302 hasConcept C50644808 @default.
• W4319660302 hasConcept C95457728 @default.
• W4319660302 hasConceptScore W4319660302C11413529 @default.
• W4319660302 hasConceptScore W4319660302C11731999 @default.
• W4319660302 hasConceptScore W4319660302C119857082 @default.
• W4319660302 hasConceptScore W4319660302C151927369 @default.
• W4319660302 hasConceptScore W4319660302C154945302 @default.
• W4319660302 hasConceptScore W4319660302C166957645 @default.
• W4319660302 hasConceptScore W4319660302C2781324535 @default.
• W4319660302 hasConceptScore W4319660302C41008148 @default.
• W4319660302 hasConceptScore W4319660302C50644808 @default.
• W4319660302 hasConceptScore W4319660302C95457728 @default.
• W4319660302 hasFunder F4320307764 @default.
• W4319660302 hasFunder F4320315885 @default.
• W4319660302 hasFunder F4320320966 @default.
• W4319660302 hasIssue "1" @default.
• W4319660302 hasLocation W43196603021 @default.
• W4319660302 hasLocation W43196603022 @default.
• W4319660302 hasLocation W43196603023 @default.
• W4319660302 hasOpenAccess W4319660302 @default.
• W4319660302 hasPrimaryLocation W43196603021 @default.
• W4319660302 hasRelatedWork W2756276189 @default.
• W4319660302 hasRelatedWork W3036281692 @default.
• W4319660302 hasRelatedWork W3040867865 @default.
• W4319660302 hasRelatedWork W3089892344 @default.
• W4319660302 hasRelatedWork W3117246098 @default.
• W4319660302 hasRelatedWork W4306160827 @default.
• W4319660302 hasRelatedWork W4312445171 @default.
• W4319660302 hasRelatedWork W4313442939 @default.
• W4319660302 hasRelatedWork W4386227043 @default.
• W4319660302 hasRelatedWork W4386536395 @default.
• W4319660302 hasVolume "3" @default.
• W4319660302 isParatext "false" @default.
• W4319660302 isRetracted "false" @default.
• W4319660302 workType "article" @default.