FRINK Linked Data Fragments server

Matches in SemOpenAlex for { <https://semopenalex.org/work/W4298042908> ?p ?o ?g. }

• W4298042908 endingPage "48" @default.
• W4298042908 startingPage "25" @default.
• W4298042908 abstract "Sentiment analysis is a popular technique for analyzing a person's behavior. Electroencephalography (EEG) is a non-invasive device for collecting brainwaves, which can be useful for identifying different emotions. The brain-computer interface (BCI) is a communication pathway between the brain's signals and an external device and can also be used to identify human emotions. Numerous studies have been conducted to distinguish human feelings using EEG signals. Deep learning (DL) algorithms are capable of identifying features from raw data. In this study, we use long short-term memory (LSTM) and a multilayer perceptron artificial neural network (MLP-ANN) to improve EEG data classification. We selected 640 datasets collected via a Muse EEG-powered headband with a global EEG position standard. We used five different combinations of activation functions with two best loss model operations and an Adam optimizer in both the LSTM and MLP-ANN algorithms, which helps in achieving better performance. We applied datasets containing different statistical features (mean median, standard deviation, etc.) from Kaggle's “EEG Brainwave Dataset: Feeling Emotions” database for the DL classifier model. We analyzed accuracy, execution time, and confusion matrix parameters and results show that both DL models achieved maximum accuracy for binary cross-entropy loss model, whereas the logcosh loss model of the MLP-ANN achieved the least accuracy." @default.
• W4298042908 created "2022-10-01" @default.
• W4298042908 creator A5007424657 @default.
• W4298042908 creator A5018586987 @default.
• W4298042908 creator A5038379220 @default.
• W4298042908 creator A5066175336 @default.
• W4298042908 creator A5072656786 @default.
• W4298042908 date "2023-01-01" @default.
• W4298042908 modified "2023-10-18" @default.
• W4298042908 title "A predictive method for emotional sentiment analysis by deep learning from EEG of brainwave dataset" @default.
• W4298042908 cites W1525254066 @default.
• W4298042908 cites W1525510058 @default.
• W4298042908 cites W2090530235 @default.
• W4298042908 cites W2095905361 @default.
• W4298042908 cites W2123504579 @default.
• W4298042908 cites W2132407017 @default.
• W4298042908 cites W2132889650 @default.
• W4298042908 cites W2160410052 @default.
• W4298042908 cites W2170883741 @default.
• W4298042908 cites W2347059862 @default.
• W4298042908 cites W2557301950 @default.
• W4298042908 cites W2589735465 @default.
• W4298042908 cites W2599251041 @default.
• W4298042908 cites W2763523016 @default.
• W4298042908 cites W2796045214 @default.
• W4298042908 cites W2799791930 @default.
• W4298042908 cites W2874390489 @default.
• W4298042908 cites W2883597459 @default.
• W4298042908 cites W2911969890 @default.
• W4298042908 cites W2916033447 @default.
• W4298042908 cites W2916188667 @default.
• W4298042908 cites W2919115771 @default.
• W4298042908 cites W2936836589 @default.
• W4298042908 cites W2954214015 @default.
• W4298042908 cites W2971837292 @default.
• W4298042908 cites W3033079718 @default.
• W4298042908 cites W3134827261 @default.
• W4298042908 cites W3197019214 @default.
• W4298042908 cites W4312670749 @default.
• W4298042908 cites W4312740499 @default.
• W4298042908 cites W4312740758 @default.
• W4298042908 doi "https://doi.org/10.1016/b978-0-323-90277-9.00002-x" @default.
• W4298042908 hasPublicationYear "2023" @default.
• W4298042908 type Work @default.
• W4298042908 citedByCount "1" @default.
• W4298042908 countsByYear W42980429082023 @default.
• W4298042908 crossrefType "book-chapter" @default.
• W4298042908 hasAuthorship W4298042908A5007424657 @default.
• W4298042908 hasAuthorship W4298042908A5018586987 @default.
• W4298042908 hasAuthorship W4298042908A5038379220 @default.
• W4298042908 hasAuthorship W4298042908A5066175336 @default.
• W4298042908 hasAuthorship W4298042908A5072656786 @default.
• W4298042908 hasConcept C118552586 @default.
• W4298042908 hasConcept C119857082 @default.
• W4298042908 hasConcept C12267149 @default.
• W4298042908 hasConcept C138602881 @default.
• W4298042908 hasConcept C153180895 @default.
• W4298042908 hasConcept C154945302 @default.
• W4298042908 hasConcept C15744967 @default.
• W4298042908 hasConcept C173201364 @default.
• W4298042908 hasConcept C179717631 @default.
• W4298042908 hasConcept C28490314 @default.
• W4298042908 hasConcept C41008148 @default.
• W4298042908 hasConcept C50644808 @default.
• W4298042908 hasConcept C522805319 @default.
• W4298042908 hasConcept C60908668 @default.
• W4298042908 hasConcept C66905080 @default.
• W4298042908 hasConcept C95623464 @default.
• W4298042908 hasConceptScore W4298042908C118552586 @default.
• W4298042908 hasConceptScore W4298042908C119857082 @default.
• W4298042908 hasConceptScore W4298042908C12267149 @default.
• W4298042908 hasConceptScore W4298042908C138602881 @default.
• W4298042908 hasConceptScore W4298042908C153180895 @default.
• W4298042908 hasConceptScore W4298042908C154945302 @default.
• W4298042908 hasConceptScore W4298042908C15744967 @default.
• W4298042908 hasConceptScore W4298042908C173201364 @default.
• W4298042908 hasConceptScore W4298042908C179717631 @default.
• W4298042908 hasConceptScore W4298042908C28490314 @default.
• W4298042908 hasConceptScore W4298042908C41008148 @default.
• W4298042908 hasConceptScore W4298042908C50644808 @default.
• W4298042908 hasConceptScore W4298042908C522805319 @default.
• W4298042908 hasConceptScore W4298042908C60908668 @default.
• W4298042908 hasConceptScore W4298042908C66905080 @default.
• W4298042908 hasConceptScore W4298042908C95623464 @default.
• W4298042908 hasLocation W42980429081 @default.
• W4298042908 hasOpenAccess W4298042908 @default.
• W4298042908 hasPrimaryLocation W42980429081 @default.
• W4298042908 hasRelatedWork W2116447301 @default.
• W4298042908 hasRelatedWork W2148064482 @default.
• W4298042908 hasRelatedWork W2924231309 @default.
• W4298042908 hasRelatedWork W3106494386 @default.
• W4298042908 hasRelatedWork W3153131991 @default.
• W4298042908 hasRelatedWork W3185179407 @default.
• W4298042908 hasRelatedWork W4231994957 @default.
• W4298042908 hasRelatedWork W4285741730 @default.
• W4298042908 hasRelatedWork W4361795583 @default.
• W4298042908 hasRelatedWork W3128183380 @default.
• W4298042908 isParatext "false" @default.

• next