Matches in SemOpenAlex for { <https://semopenalex.org/work/W2962222774> ?p ?o ?g. }
Showing items 1 to 100 of
100
with 100 items per page.
- W2962222774 abstract "Abstract This paper aims to apply machine learning techniques to an automated epileptic seizure detection using EEG signals to help neurologists in a time-consuming diagnostic process. We employ two approaches based on convolution neural networks (CNNs) and artificial neural networks (ANNs) to provide a probability of seizure occurrence in a windowed EEG recording of 18 channels. In order to extract relevant features based on time, frequency, and time-frequency domains for these networks, we consider an improvement of the Bayesian error rate from a baseline. Features of which the improvement rates are higher than the significant level are considered. These dominant features extracted from all EEG channels are concatenated as the input for ANN with 7 hidden layers, while the input of CNN is taken as raw multi-channel EEG signals. Using multi-concept of deep CNN in image processing, we exploit 2D-filter decomposition to handle the signal in spatial and temporal domains. Our experiments based on CHB-MIT Scalp EEG Database showed that both ANN and CNN were able to perform with the overall accuracy of up to 99.07% and F1-score of up to 77.04%. ANN with dominant features is more capable of detecting seizure events than CNN whereas CNN requiring no feature extraction is slightly better than ANN in classification accuracy." @default.
- W2962222774 created "2019-07-23" @default.
- W2962222774 creator A5033554751 @default.
- W2962222774 creator A5044405321 @default.
- W2962222774 creator A5089492833 @default.
- W2962222774 creator A5033564254 @default.
- W2962222774 date "2019-07-15" @default.
- W2962222774 modified "2023-09-24" @default.
- W2962222774 title "A Comparison of Deep Neural Networks for Seizure Detection in EEG Signals" @default.
- W2962222774 cites W1604539019 @default.
- W2962222774 cites W1818768602 @default.
- W2962222774 cites W1978437325 @default.
- W2962222774 cites W1998272035 @default.
- W2962222774 cites W2000527874 @default.
- W2962222774 cites W2004547695 @default.
- W2962222774 cites W2005305683 @default.
- W2962222774 cites W2016054699 @default.
- W2962222774 cites W2027927824 @default.
- W2962222774 cites W2035987281 @default.
- W2962222774 cites W2042323927 @default.
- W2962222774 cites W2097117768 @default.
- W2962222774 cites W2119269525 @default.
- W2962222774 cites W2132240828 @default.
- W2962222774 cites W2162800060 @default.
- W2962222774 cites W2183341477 @default.
- W2962222774 cites W2288333483 @default.
- W2962222774 cites W2402787549 @default.
- W2962222774 cites W2513671774 @default.
- W2962222774 cites W2553015255 @default.
- W2962222774 cites W2582398088 @default.
- W2962222774 cites W2593873339 @default.
- W2962222774 cites W2750384459 @default.
- W2962222774 cites W2759483166 @default.
- W2962222774 cites W2898738372 @default.
- W2962222774 cites W2906882276 @default.
- W2962222774 cites W3106324661 @default.
- W2962222774 doi "https://doi.org/10.1101/702654" @default.
- W2962222774 hasPublicationYear "2019" @default.
- W2962222774 type Work @default.
- W2962222774 sameAs 2962222774 @default.
- W2962222774 citedByCount "13" @default.
- W2962222774 countsByYear W29622227742020 @default.
- W2962222774 countsByYear W29622227742021 @default.
- W2962222774 countsByYear W29622227742022 @default.
- W2962222774 countsByYear W29622227742023 @default.
- W2962222774 crossrefType "posted-content" @default.
- W2962222774 hasAuthorship W2962222774A5033554751 @default.
- W2962222774 hasAuthorship W2962222774A5033564254 @default.
- W2962222774 hasAuthorship W2962222774A5044405321 @default.
- W2962222774 hasAuthorship W2962222774A5089492833 @default.
- W2962222774 hasBestOaLocation W29622227741 @default.
- W2962222774 hasConcept C108583219 @default.
- W2962222774 hasConcept C118552586 @default.
- W2962222774 hasConcept C138885662 @default.
- W2962222774 hasConcept C153180895 @default.
- W2962222774 hasConcept C154945302 @default.
- W2962222774 hasConcept C15744967 @default.
- W2962222774 hasConcept C2776401178 @default.
- W2962222774 hasConcept C2779334592 @default.
- W2962222774 hasConcept C28490314 @default.
- W2962222774 hasConcept C41008148 @default.
- W2962222774 hasConcept C41895202 @default.
- W2962222774 hasConcept C45347329 @default.
- W2962222774 hasConcept C50644808 @default.
- W2962222774 hasConcept C522805319 @default.
- W2962222774 hasConcept C52622490 @default.
- W2962222774 hasConcept C81363708 @default.
- W2962222774 hasConceptScore W2962222774C108583219 @default.
- W2962222774 hasConceptScore W2962222774C118552586 @default.
- W2962222774 hasConceptScore W2962222774C138885662 @default.
- W2962222774 hasConceptScore W2962222774C153180895 @default.
- W2962222774 hasConceptScore W2962222774C154945302 @default.
- W2962222774 hasConceptScore W2962222774C15744967 @default.
- W2962222774 hasConceptScore W2962222774C2776401178 @default.
- W2962222774 hasConceptScore W2962222774C2779334592 @default.
- W2962222774 hasConceptScore W2962222774C28490314 @default.
- W2962222774 hasConceptScore W2962222774C41008148 @default.
- W2962222774 hasConceptScore W2962222774C41895202 @default.
- W2962222774 hasConceptScore W2962222774C45347329 @default.
- W2962222774 hasConceptScore W2962222774C50644808 @default.
- W2962222774 hasConceptScore W2962222774C522805319 @default.
- W2962222774 hasConceptScore W2962222774C52622490 @default.
- W2962222774 hasConceptScore W2962222774C81363708 @default.
- W2962222774 hasLocation W29622227741 @default.
- W2962222774 hasOpenAccess W2962222774 @default.
- W2962222774 hasPrimaryLocation W29622227741 @default.
- W2962222774 hasRelatedWork W2059299633 @default.
- W2962222774 hasRelatedWork W2279398222 @default.
- W2962222774 hasRelatedWork W2732542196 @default.
- W2962222774 hasRelatedWork W2738221750 @default.
- W2962222774 hasRelatedWork W2760085659 @default.
- W2962222774 hasRelatedWork W2773120646 @default.
- W2962222774 hasRelatedWork W3011074480 @default.
- W2962222774 hasRelatedWork W3156786002 @default.
- W2962222774 hasRelatedWork W4299822940 @default.
- W2962222774 hasRelatedWork W4312417841 @default.
- W2962222774 isParatext "false" @default.
- W2962222774 isRetracted "false" @default.
- W2962222774 magId "2962222774" @default.
- W2962222774 workType "article" @default.