Matches in SemOpenAlex for { <https://semopenalex.org/work/W2950976972> ?p ?o ?g. }
- W2950976972 endingPage "68428" @default.
- W2950976972 startingPage "68415" @default.
- W2950976972 abstract "The process of recording Electroencephalography (EEG) signals is onerous and requires massive storage to store signals at an applicable frequency rate. In this work, we propose the EventRelated Potential Encoder Network (ERPENet); a multi-task autoencoder-based model, that can be applied to any ERP-related tasks. The strength of ERPENet lies in its capability to handle various kinds of ERP datasets and its robustness across multiple recording setups, enabling joint training across datasets. ERPENet incorporates Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM), in an autoencoder setup, which tries to simultaneously compress the input EEG signal and extract related P300 features into a latent vector. Here, we can infer the process for generating the latent vector as universal joint feature extraction. The network also includes a classification part for attended and unattended events classification as an auxiliary task. We experimented on six different P300 datasets. The results show that the latent vector exhibits better compression capability than the previous state-of-the-art semi-supervised autoencoder model. For attended and unattended events classification, pre-trained weights are adopted as initial weights and tested on unseen P300 datasets to evaluate the adaptability of the model, which shortens the training process as compared to using random Xavier weight initialization. At the compression rate of 6.84, the classification accuracy outperforms conventional P300 classification models: XdawnLDA, DeepConvNet, and EEGNet achieving 79.37% - 88.52% classification accuracy depending on the dataset." @default.
- W2950976972 created "2019-06-27" @default.
- W2950976972 creator A5004012466 @default.
- W2950976972 creator A5022621021 @default.
- W2950976972 creator A5030009288 @default.
- W2950976972 creator A5031876450 @default.
- W2950976972 creator A5050282933 @default.
- W2950976972 date "2019-01-01" @default.
- W2950976972 modified "2023-09-29" @default.
- W2950976972 title "Universal Joint Feature Extraction for P300 EEG Classification Using Multi-Task Autoencoder" @default.
- W2950976972 cites W117999694 @default.
- W2950976972 cites W1832693441 @default.
- W2950976972 cites W1898865053 @default.
- W2950976972 cites W1975898493 @default.
- W2950976972 cites W1984120270 @default.
- W2950976972 cites W1995513458 @default.
- W2950976972 cites W2009797711 @default.
- W2950976972 cites W2020122740 @default.
- W2950976972 cites W2025950086 @default.
- W2950976972 cites W2027101175 @default.
- W2950976972 cites W2033419225 @default.
- W2950976972 cites W2045818160 @default.
- W2950976972 cites W2055890155 @default.
- W2950976972 cites W2056515034 @default.
- W2950976972 cites W2064675550 @default.
- W2950976972 cites W2068562173 @default.
- W2950976972 cites W2076857836 @default.
- W2950976972 cites W2086213036 @default.
- W2950976972 cites W2094017272 @default.
- W2950976972 cites W2099323129 @default.
- W2950976972 cites W2100495367 @default.
- W2950976972 cites W2104063964 @default.
- W2950976972 cites W2110545034 @default.
- W2950976972 cites W2111414067 @default.
- W2950976972 cites W2150796457 @default.
- W2950976972 cites W2161565164 @default.
- W2950976972 cites W2163727886 @default.
- W2950976972 cites W2170498245 @default.
- W2950976972 cites W2194775991 @default.
- W2950976972 cites W2526755872 @default.
- W2950976972 cites W2535388113 @default.
- W2950976972 cites W2556806401 @default.
- W2950976972 cites W2741907166 @default.
- W2950976972 cites W2766584688 @default.
- W2950976972 cites W2766736793 @default.
- W2950976972 cites W2767033786 @default.
- W2950976972 cites W2792885690 @default.
- W2950976972 cites W2794345050 @default.
- W2950976972 cites W2801752756 @default.
- W2950976972 cites W2805466995 @default.
- W2950976972 cites W2883827556 @default.
- W2950976972 cites W2887773909 @default.
- W2950976972 cites W2890057045 @default.
- W2950976972 cites W2964054038 @default.
- W2950976972 doi "https://doi.org/10.1109/access.2019.2919143" @default.
- W2950976972 hasPublicationYear "2019" @default.
- W2950976972 type Work @default.
- W2950976972 sameAs 2950976972 @default.
- W2950976972 citedByCount "72" @default.
- W2950976972 countsByYear W29509769722018 @default.
- W2950976972 countsByYear W29509769722019 @default.
- W2950976972 countsByYear W29509769722020 @default.
- W2950976972 countsByYear W29509769722021 @default.
- W2950976972 countsByYear W29509769722022 @default.
- W2950976972 countsByYear W29509769722023 @default.
- W2950976972 crossrefType "journal-article" @default.
- W2950976972 hasAuthorship W2950976972A5004012466 @default.
- W2950976972 hasAuthorship W2950976972A5022621021 @default.
- W2950976972 hasAuthorship W2950976972A5030009288 @default.
- W2950976972 hasAuthorship W2950976972A5031876450 @default.
- W2950976972 hasAuthorship W2950976972A5050282933 @default.
- W2950976972 hasBestOaLocation W29509769721 @default.
- W2950976972 hasConcept C101738243 @default.
- W2950976972 hasConcept C104317684 @default.
- W2950976972 hasConcept C108583219 @default.
- W2950976972 hasConcept C111919701 @default.
- W2950976972 hasConcept C114466953 @default.
- W2950976972 hasConcept C118505674 @default.
- W2950976972 hasConcept C118552586 @default.
- W2950976972 hasConcept C119857082 @default.
- W2950976972 hasConcept C12267149 @default.
- W2950976972 hasConcept C153180895 @default.
- W2950976972 hasConcept C154945302 @default.
- W2950976972 hasConcept C15744967 @default.
- W2950976972 hasConcept C185592680 @default.
- W2950976972 hasConcept C199360897 @default.
- W2950976972 hasConcept C28490314 @default.
- W2950976972 hasConcept C41008148 @default.
- W2950976972 hasConcept C522805319 @default.
- W2950976972 hasConcept C52622490 @default.
- W2950976972 hasConcept C55493867 @default.
- W2950976972 hasConcept C63479239 @default.
- W2950976972 hasConcept C81363708 @default.
- W2950976972 hasConceptScore W2950976972C101738243 @default.
- W2950976972 hasConceptScore W2950976972C104317684 @default.
- W2950976972 hasConceptScore W2950976972C108583219 @default.
- W2950976972 hasConceptScore W2950976972C111919701 @default.
- W2950976972 hasConceptScore W2950976972C114466953 @default.