Matches in SemOpenAlex for { <https://semopenalex.org/work/W2945763771> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W2945763771 endingPage "681" @default.
- W2945763771 startingPage "670" @default.
- W2945763771 abstract "This paper introduces a novel electroencephalogram (EEG) data classification scheme together with its implementation in hardware using an innovative approach. The proposed scheme integrates into a single, end-to-end trainable model a spatial filtering technique and a neural network based classifier. The spatial filters, as well as, the coefficients of the neural network classifier are simultaneously estimated during training. By using different time-locked spatial filters, we introduce for the first time the notion of attention in EEG processing, which allows for the efficient capturing of the temporal dependencies and/or variability of the EEG sequential data. One of the most important benefits of our approach is that the proposed classifier is able to construct highly discriminative features directly from raw EEG data and, at the same time, to exploit the function approximation properties of neural networks, in order to produce highly accurate classification results. The evaluation of the proposed methodology, using public available EEG datasets, indicates that it outperforms the standard EEG classification approach based on filtering and classification as two separated steps. Moreover, we present a prototype implementation of the proposed scheme in state-of-the-art reconfigurable hardware; our novel implementation outperforms by more than one order of magnitude, in terms of power efficiency, the conventional CPU-based approaches." @default.
- W2945763771 created "2019-05-29" @default.
- W2945763771 creator A5022563712 @default.
- W2945763771 creator A5032739499 @default.
- W2945763771 creator A5057445534 @default.
- W2945763771 creator A5065898973 @default.
- W2945763771 date "2019-08-01" @default.
- W2945763771 modified "2023-10-16" @default.
- W2945763771 title "A Unified Novel Neural Network Approach and a Prototype Hardware Implementation for Ultra-Low Power EEG Classification" @default.
- W2945763771 cites W1976920880 @default.
- W2945763771 cites W1982802415 @default.
- W2945763771 cites W1986762730 @default.
- W2945763771 cites W1995506038 @default.
- W2945763771 cites W2018040425 @default.
- W2945763771 cites W2026186900 @default.
- W2945763771 cites W2030328665 @default.
- W2945763771 cites W2047545657 @default.
- W2945763771 cites W2067992844 @default.
- W2945763771 cites W2082070408 @default.
- W2945763771 cites W2088042856 @default.
- W2945763771 cites W2093296486 @default.
- W2945763771 cites W2104063964 @default.
- W2945763771 cites W2107549039 @default.
- W2945763771 cites W2110203423 @default.
- W2945763771 cites W2126761123 @default.
- W2945763771 cites W2131321253 @default.
- W2945763771 cites W2142280324 @default.
- W2945763771 cites W2152119085 @default.
- W2945763771 cites W2155617375 @default.
- W2945763771 cites W2584942583 @default.
- W2945763771 cites W2884236118 @default.
- W2945763771 cites W2896663785 @default.
- W2945763771 cites W2913140232 @default.
- W2945763771 cites W2914072416 @default.
- W2945763771 cites W4236362309 @default.
- W2945763771 doi "https://doi.org/10.1109/tbcas.2019.2916981" @default.
- W2945763771 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/31095497" @default.
- W2945763771 hasPublicationYear "2019" @default.
- W2945763771 type Work @default.
- W2945763771 sameAs 2945763771 @default.
- W2945763771 citedByCount "14" @default.
- W2945763771 countsByYear W29457637712019 @default.
- W2945763771 countsByYear W29457637712020 @default.
- W2945763771 countsByYear W29457637712021 @default.
- W2945763771 countsByYear W29457637712022 @default.
- W2945763771 crossrefType "journal-article" @default.
- W2945763771 hasAuthorship W2945763771A5022563712 @default.
- W2945763771 hasAuthorship W2945763771A5032739499 @default.
- W2945763771 hasAuthorship W2945763771A5057445534 @default.
- W2945763771 hasAuthorship W2945763771A5065898973 @default.
- W2945763771 hasConcept C118552586 @default.
- W2945763771 hasConcept C119857082 @default.
- W2945763771 hasConcept C121475858 @default.
- W2945763771 hasConcept C153180895 @default.
- W2945763771 hasConcept C154945302 @default.
- W2945763771 hasConcept C15744967 @default.
- W2945763771 hasConcept C165696696 @default.
- W2945763771 hasConcept C38652104 @default.
- W2945763771 hasConcept C41008148 @default.
- W2945763771 hasConcept C50644808 @default.
- W2945763771 hasConcept C522805319 @default.
- W2945763771 hasConcept C95623464 @default.
- W2945763771 hasConcept C97931131 @default.
- W2945763771 hasConceptScore W2945763771C118552586 @default.
- W2945763771 hasConceptScore W2945763771C119857082 @default.
- W2945763771 hasConceptScore W2945763771C121475858 @default.
- W2945763771 hasConceptScore W2945763771C153180895 @default.
- W2945763771 hasConceptScore W2945763771C154945302 @default.
- W2945763771 hasConceptScore W2945763771C15744967 @default.
- W2945763771 hasConceptScore W2945763771C165696696 @default.
- W2945763771 hasConceptScore W2945763771C38652104 @default.
- W2945763771 hasConceptScore W2945763771C41008148 @default.
- W2945763771 hasConceptScore W2945763771C50644808 @default.
- W2945763771 hasConceptScore W2945763771C522805319 @default.
- W2945763771 hasConceptScore W2945763771C95623464 @default.
- W2945763771 hasConceptScore W2945763771C97931131 @default.
- W2945763771 hasIssue "4" @default.
- W2945763771 hasLocation W29457637711 @default.
- W2945763771 hasLocation W29457637712 @default.
- W2945763771 hasOpenAccess W2945763771 @default.
- W2945763771 hasPrimaryLocation W29457637711 @default.
- W2945763771 hasRelatedWork W1652783584 @default.
- W2945763771 hasRelatedWork W1990254706 @default.
- W2945763771 hasRelatedWork W2024160000 @default.
- W2945763771 hasRelatedWork W2044507188 @default.
- W2945763771 hasRelatedWork W2104535716 @default.
- W2945763771 hasRelatedWork W2112343299 @default.
- W2945763771 hasRelatedWork W2773500201 @default.
- W2945763771 hasRelatedWork W2905846897 @default.
- W2945763771 hasRelatedWork W74886973 @default.
- W2945763771 hasRelatedWork W82679236 @default.
- W2945763771 hasVolume "13" @default.
- W2945763771 isParatext "false" @default.
- W2945763771 isRetracted "false" @default.
- W2945763771 magId "2945763771" @default.
- W2945763771 workType "article" @default.