Matches in SemOpenAlex for { <https://semopenalex.org/work/W4324291243> ?p ?o ?g. }
Showing items 1 to 92 of
92
with 100 items per page.
- W4324291243 endingPage "2355" @default.
- W4324291243 startingPage "2342" @default.
- W4324291243 abstract "User identification enables secure access to data and machines in smart factories. Compared with other modalities, ECG-based user identification is rising due to its intrinsic liveness proof and invulnerability to spoofing without contact. On the other hand, as new employees are registered at the factory, the ECG-based user identification system needs to be updated based on the new coming data. This scenario can be defined as an online class-incremental learning (O-CIL) problem. By exploiting hardware-software co- design, this work presents a Scalable QR-decomposition-based extreme learning machine (S-QRD-ELM) engine that can effectively and efficiently support O-CIL for ECG-based user identification. At the software level, we apply the concept of “the others” class and inversion-free QR-decomposition (QRD) recursive least squares to the S-QRD-ELM. This makes S-QRD-ELM achieve 79.7% higher accuracy in the O-CIL scenario compared with the neural network trained with back-propagation (BP-NN). At the hardware level, a one-dimensional diagonally-mapped linear array (1D-DMLA) is proposed to efficiently compute the QRD and back-substitution (BS) operations inside the S-QRD-ELM, reducing 98.5% of the silicon area. Moreover, the integrated processing element (PE) design with the unified COordinate Rotation DIgital Computer (u-CORDIC) further reduces 15.3% of the area and 22.4% of the power consumption. This engine is fabricated in 40nm CMOS technology with a <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$1.33times 1.33$ </tex-math></inline-formula> mm2 die area. The chip achieves <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$0.02mu text{J}$ </tex-math></inline-formula> /sample and <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$2.47mu text{J}$ </tex-math></inline-formula> /sample inferencing and learning energy efficiency, respectively, which is <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$6.4times $ </tex-math></inline-formula> and <inline-formula xmlns:mml=http://www.w3.org/1998/Math/MathML xmlns:xlink=http://www.w3.org/1999/xlink> <tex-math notation=LaTeX>$28.5times $ </tex-math></inline-formula> than the state-of-the-art. To the best of our knowledge, the proposed highly energy-efficient S-QRD-ELM engine is the first chip to meet the requirements of O-CIL for ECG-based user identification." @default.
- W4324291243 created "2023-03-16" @default.
- W4324291243 creator A5048315308 @default.
- W4324291243 creator A5057700442 @default.
- W4324291243 creator A5060083525 @default.
- W4324291243 creator A5069905671 @default.
- W4324291243 date "2023-06-01" @default.
- W4324291243 modified "2023-10-18" @default.
- W4324291243 title "S-QRD-ELM: Scalable QR-Decomposition-Based Extreme Learning Machine Engine Supporting Online Class-Incremental Learning for ECG-Based User Identification" @default.
- W4324291243 cites W2011961109 @default.
- W4324291243 cites W2111072639 @default.
- W4324291243 cites W2138061685 @default.
- W4324291243 cites W2150633168 @default.
- W4324291243 cites W2162273778 @default.
- W4324291243 cites W2162800060 @default.
- W4324291243 cites W2473930607 @default.
- W4324291243 cites W2560647685 @default.
- W4324291243 cites W2782009593 @default.
- W4324291243 cites W2794557162 @default.
- W4324291243 cites W2898485213 @default.
- W4324291243 cites W2911149048 @default.
- W4324291243 cites W2945997721 @default.
- W4324291243 cites W2963347423 @default.
- W4324291243 cites W2964189064 @default.
- W4324291243 cites W3081320461 @default.
- W4324291243 cites W3122976726 @default.
- W4324291243 cites W3125116114 @default.
- W4324291243 cites W3158528914 @default.
- W4324291243 cites W4226236362 @default.
- W4324291243 cites W4285171379 @default.
- W4324291243 doi "https://doi.org/10.1109/tcsi.2023.3253705" @default.
- W4324291243 hasPublicationYear "2023" @default.
- W4324291243 type Work @default.
- W4324291243 citedByCount "0" @default.
- W4324291243 crossrefType "journal-article" @default.
- W4324291243 hasAuthorship W4324291243A5048315308 @default.
- W4324291243 hasAuthorship W4324291243A5057700442 @default.
- W4324291243 hasAuthorship W4324291243A5060083525 @default.
- W4324291243 hasAuthorship W4324291243A5069905671 @default.
- W4324291243 hasConcept C111919701 @default.
- W4324291243 hasConcept C116834253 @default.
- W4324291243 hasConcept C119857082 @default.
- W4324291243 hasConcept C121332964 @default.
- W4324291243 hasConcept C154945302 @default.
- W4324291243 hasConcept C158693339 @default.
- W4324291243 hasConcept C188060507 @default.
- W4324291243 hasConcept C2777904410 @default.
- W4324291243 hasConcept C2780150128 @default.
- W4324291243 hasConcept C41008148 @default.
- W4324291243 hasConcept C48044578 @default.
- W4324291243 hasConcept C50644808 @default.
- W4324291243 hasConcept C59822182 @default.
- W4324291243 hasConcept C62520636 @default.
- W4324291243 hasConcept C77088390 @default.
- W4324291243 hasConcept C86803240 @default.
- W4324291243 hasConceptScore W4324291243C111919701 @default.
- W4324291243 hasConceptScore W4324291243C116834253 @default.
- W4324291243 hasConceptScore W4324291243C119857082 @default.
- W4324291243 hasConceptScore W4324291243C121332964 @default.
- W4324291243 hasConceptScore W4324291243C154945302 @default.
- W4324291243 hasConceptScore W4324291243C158693339 @default.
- W4324291243 hasConceptScore W4324291243C188060507 @default.
- W4324291243 hasConceptScore W4324291243C2777904410 @default.
- W4324291243 hasConceptScore W4324291243C2780150128 @default.
- W4324291243 hasConceptScore W4324291243C41008148 @default.
- W4324291243 hasConceptScore W4324291243C48044578 @default.
- W4324291243 hasConceptScore W4324291243C50644808 @default.
- W4324291243 hasConceptScore W4324291243C59822182 @default.
- W4324291243 hasConceptScore W4324291243C62520636 @default.
- W4324291243 hasConceptScore W4324291243C77088390 @default.
- W4324291243 hasConceptScore W4324291243C86803240 @default.
- W4324291243 hasFunder F4320322795 @default.
- W4324291243 hasIssue "6" @default.
- W4324291243 hasLocation W43242912431 @default.
- W4324291243 hasOpenAccess W4324291243 @default.
- W4324291243 hasPrimaryLocation W43242912431 @default.
- W4324291243 hasRelatedWork W1525510058 @default.
- W4324291243 hasRelatedWork W1545807863 @default.
- W4324291243 hasRelatedWork W2295628041 @default.
- W4324291243 hasRelatedWork W2475251269 @default.
- W4324291243 hasRelatedWork W2969890106 @default.
- W4324291243 hasRelatedWork W3134233996 @default.
- W4324291243 hasRelatedWork W3185179407 @default.
- W4324291243 hasRelatedWork W4320060020 @default.
- W4324291243 hasRelatedWork W1629725936 @default.
- W4324291243 hasRelatedWork W2921296813 @default.
- W4324291243 hasVolume "70" @default.
- W4324291243 isParatext "false" @default.
- W4324291243 isRetracted "false" @default.
- W4324291243 workType "article" @default.