FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4381336006> ?p ?o ?g. }

• W4381336006 endingPage "2743" @default.
• W4381336006 startingPage "2743" @default.
• W4381336006 abstract "A preponderance of brain–computer interface (BCI) publications proposing artificial neural networks for motor imagery (MI) electroencephalography (EEG) signal classification utilize one of the BCI Competition datasets. However, these databases encompass MI EEG data from a limited number of subjects, typically less than or equal to 10. Furthermore, the algorithms usually include only bandpass filtering as a means of reducing noise and increasing signal quality. In this study, we conducted a comparative analysis of five renowned neural networks (Shallow ConvNet, Deep ConvNet, EEGNet, EEGNet Fusion, and MI-EEGNet) utilizing open-access databases with a larger subject pool in conjunction with the BCI Competition IV 2a dataset to obtain statistically significant results. We employed the FASTER algorithm to eliminate artifacts from the EEG as a signal processing step and explored the potential for transfer learning to enhance classification results on artifact-filtered data. Our objective was to rank the neural networks; hence, in addition to classification accuracy, we introduced two supplementary metrics: accuracy improvement from chance level and the effect of transfer learning. The former is applicable to databases with varying numbers of classes, while the latter can underscore neural networks with robust generalization capabilities. Our metrics indicated that researchers should not disregard Shallow ConvNet and Deep ConvNet as they can outperform later published members of the EEGNet family." @default.
• W4381336006 created "2023-06-21" @default.
• W4381336006 creator A5017045430 @default.
• W4381336006 creator A5028142687 @default.
• W4381336006 creator A5036485659 @default.
• W4381336006 creator A5058882719 @default.
• W4381336006 creator A5072499791 @default.
• W4381336006 date "2023-06-20" @default.
• W4381336006 modified "2023-10-06" @default.
• W4381336006 title "Deep Comparisons of Neural Networks from the EEGNet Family" @default.
• W4381336006 cites W1576278180 @default.
• W4381336006 cites W1969878365 @default.
• W4381336006 cites W2023869733 @default.
• W4381336006 cites W2099579406 @default.
• W4381336006 cites W2101629643 @default.
• W4381336006 cites W2106006415 @default.
• W4381336006 cites W2119163516 @default.
• W4381336006 cites W2128404967 @default.
• W4381336006 cites W2151669316 @default.
• W4381336006 cites W2152119085 @default.
• W4381336006 cites W2153912116 @default.
• W4381336006 cites W2162800060 @default.
• W4381336006 cites W2218506909 @default.
• W4381336006 cites W2395579298 @default.
• W4381336006 cites W2557301950 @default.
• W4381336006 cites W2741907166 @default.
• W4381336006 cites W2776198882 @default.
• W4381336006 cites W2782903092 @default.
• W4381336006 cites W2801587739 @default.
• W4381336006 cites W2912885887 @default.
• W4381336006 cites W2963287333 @default.
• W4381336006 cites W3015898934 @default.
• W4381336006 cites W3043664281 @default.
• W4381336006 cites W3046051368 @default.
• W4381336006 cites W3080222908 @default.
• W4381336006 cites W3083693766 @default.
• W4381336006 cites W3101820167 @default.
• W4381336006 cites W3102455230 @default.
• W4381336006 cites W3113058752 @default.
• W4381336006 cites W3126287844 @default.
• W4381336006 cites W3133726839 @default.
• W4381336006 cites W3134577784 @default.
• W4381336006 cites W3139413607 @default.
• W4381336006 cites W3149909107 @default.
• W4381336006 cites W3165639284 @default.
• W4381336006 cites W3171116091 @default.
• W4381336006 cites W3171454251 @default.
• W4381336006 cites W3196236986 @default.
• W4381336006 cites W3198715997 @default.
• W4381336006 cites W3203548333 @default.
• W4381336006 cites W3208475607 @default.
• W4381336006 cites W3210269077 @default.
• W4381336006 cites W3213412168 @default.
• W4381336006 cites W4200409924 @default.
• W4381336006 cites W4211170405 @default.
• W4381336006 cites W4214493602 @default.
• W4381336006 cites W4232666784 @default.
• W4381336006 cites W4235522198 @default.
• W4381336006 cites W4283655414 @default.
• W4381336006 cites W4283817957 @default.
• W4381336006 cites W4285098698 @default.
• W4381336006 cites W4291014966 @default.
• W4381336006 cites W4291237121 @default.
• W4381336006 cites W4293004052 @default.
• W4381336006 cites W4293550306 @default.
• W4381336006 cites W4294919628 @default.
• W4381336006 cites W4300860283 @default.
• W4381336006 cites W4300942166 @default.
• W4381336006 cites W4312226636 @default.
• W4381336006 cites W1905772121 @default.
• W4381336006 doi "https://doi.org/10.3390/electronics12122743" @default.
• W4381336006 hasPublicationYear "2023" @default.
• W4381336006 type Work @default.
• W4381336006 citedByCount "0" @default.
• W4381336006 crossrefType "journal-article" @default.
• W4381336006 hasAuthorship W4381336006A5017045430 @default.
• W4381336006 hasAuthorship W4381336006A5028142687 @default.
• W4381336006 hasAuthorship W4381336006A5036485659 @default.
• W4381336006 hasAuthorship W4381336006A5058882719 @default.
• W4381336006 hasAuthorship W4381336006A5072499791 @default.
• W4381336006 hasBestOaLocation W43813360061 @default.
• W4381336006 hasConcept C103278499 @default.
• W4381336006 hasConcept C108583219 @default.
• W4381336006 hasConcept C113843644 @default.
• W4381336006 hasConcept C114614502 @default.
• W4381336006 hasConcept C115961682 @default.
• W4381336006 hasConcept C118552586 @default.
• W4381336006 hasConcept C119857082 @default.
• W4381336006 hasConcept C129307140 @default.
• W4381336006 hasConcept C134306372 @default.
• W4381336006 hasConcept C150899416 @default.
• W4381336006 hasConcept C153180895 @default.
• W4381336006 hasConcept C154945302 @default.
• W4381336006 hasConcept C15744967 @default.
• W4381336006 hasConcept C157915830 @default.
• W4381336006 hasConcept C164226766 @default.
• W4381336006 hasConcept C173201364 @default.
• W4381336006 hasConcept C173608175 @default.

• next