FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4313332396> ?p ?o ?g. }

• W4313332396 endingPage "176" @default.
• W4313332396 startingPage "167" @default.
• W4313332396 abstract "This work presents the world’s first neural signal processor for seizure prediction, which includes a preprocessing unit, a feature extractor, a reconfigurable support vector machine (SVM) kernel, and a postprocessing unit. Seizure prediction performance is enhanced by on-chip training for model adaptation. Design optimization is applied across the layers of abstraction to minimize the area and energy. The area of the feature extractor is reduced by 28% with an approximated energy operator (AEO). The proposed scaling-based Newton–Raphson (NR) divider reduces the required number of iterations for division by 62.5%. For alternating direction method of multipliers (ADMM)-based SVM training, the computational complexity is reduced by up to 99.9% through pointer-based matrix multiplication. By leveraging the LDL decomposition, 80% multiplications for updating weights are saved. The chip achieves a seizure prediction performance with a 92.0% sensitivity and a 0.57/h false alarm rate (FAR). The training latency is 8.44 ms with a power dissipation of 2.31 mW at 6.05 MHz. Compared with an ARM Cortex-M3 microcontroller, this work achieves a <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$124times $ </tex-math></inline-formula> higher area efficiency and a <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$299times $ </tex-math></inline-formula> higher energy efficiency. The chip also supports seizure detection and achieves a sensitivity of 98.6% and an FAR of 0.18/h, exceeding the state-of-the-art designs." @default.
• W4313332396 created "2023-01-06" @default.
• W4313332396 creator A5042194278 @default.
• W4313332396 creator A5043326737 @default.
• W4313332396 creator A5046791287 @default.
• W4313332396 date "2023-01-01" @default.
• W4313332396 modified "2023-09-30" @default.
• W4313332396 title "A 96.2-nJ/class Neural Signal Processor With Adaptable Intelligence for Seizure Prediction" @default.
• W4313332396 cites W2008917039 @default.
• W4313332396 cites W2069115302 @default.
• W4313332396 cites W2073803275 @default.
• W4313332396 cites W2086659790 @default.
• W4313332396 cites W2086848249 @default.
• W4313332396 cites W2087347434 @default.
• W4313332396 cites W2104839346 @default.
• W4313332396 cites W2114537326 @default.
• W4313332396 cites W2159398070 @default.
• W4313332396 cites W2162800060 @default.
• W4313332396 cites W2167711152 @default.
• W4313332396 cites W2338092193 @default.
• W4313332396 cites W2342718072 @default.
• W4313332396 cites W2465455179 @default.
• W4313332396 cites W2606684606 @default.
• W4313332396 cites W2780723646 @default.
• W4313332396 cites W2804824909 @default.
• W4313332396 cites W2890191974 @default.
• W4313332396 cites W2898040341 @default.
• W4313332396 cites W2899212146 @default.
• W4313332396 cites W2962984603 @default.
• W4313332396 cites W2998694088 @default.
• W4313332396 cites W3080578087 @default.
• W4313332396 cites W4220761057 @default.
• W4313332396 doi "https://doi.org/10.1109/jssc.2022.3218240" @default.
• W4313332396 hasPublicationYear "2023" @default.
• W4313332396 type Work @default.
• W4313332396 citedByCount "1" @default.
• W4313332396 countsByYear W43133323962023 @default.
• W4313332396 crossrefType "journal-article" @default.
• W4313332396 hasAuthorship W4313332396A5042194278 @default.
• W4313332396 hasAuthorship W4313332396A5043326737 @default.
• W4313332396 hasAuthorship W4313332396A5046791287 @default.
• W4313332396 hasConcept C11413529 @default.
• W4313332396 hasConcept C12267149 @default.
• W4313332396 hasConcept C154945302 @default.
• W4313332396 hasConcept C165005293 @default.
• W4313332396 hasConcept C173608175 @default.
• W4313332396 hasConcept C41008148 @default.
• W4313332396 hasConcept C50644808 @default.
• W4313332396 hasConcept C76155785 @default.
• W4313332396 hasConcept C86111242 @default.
• W4313332396 hasConceptScore W4313332396C11413529 @default.
• W4313332396 hasConceptScore W4313332396C12267149 @default.
• W4313332396 hasConceptScore W4313332396C154945302 @default.
• W4313332396 hasConceptScore W4313332396C165005293 @default.
• W4313332396 hasConceptScore W4313332396C173608175 @default.
• W4313332396 hasConceptScore W4313332396C41008148 @default.
• W4313332396 hasConceptScore W4313332396C50644808 @default.
• W4313332396 hasConceptScore W4313332396C76155785 @default.
• W4313332396 hasConceptScore W4313332396C86111242 @default.
• W4313332396 hasFunder F4320322795 @default.
• W4313332396 hasFunder F4320323900 @default.
• W4313332396 hasIssue "1" @default.
• W4313332396 hasLocation W43133323961 @default.
• W4313332396 hasOpenAccess W4313332396 @default.
• W4313332396 hasPrimaryLocation W43133323961 @default.
• W4313332396 hasRelatedWork W1558545464 @default.
• W4313332396 hasRelatedWork W1984102830 @default.
• W4313332396 hasRelatedWork W1984303163 @default.
• W4313332396 hasRelatedWork W2074301136 @default.
• W4313332396 hasRelatedWork W2117014006 @default.
• W4313332396 hasRelatedWork W2170268965 @default.
• W4313332396 hasRelatedWork W2355927362 @default.
• W4313332396 hasRelatedWork W2372170743 @default.
• W4313332396 hasRelatedWork W2992977501 @default.
• W4313332396 hasRelatedWork W4233815414 @default.
• W4313332396 hasVolume "58" @default.
• W4313332396 isParatext "false" @default.
• W4313332396 isRetracted "false" @default.
• W4313332396 workType "article" @default.