English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

The process of recording Electroencephalography (EEG) signals is onerous andrequires massive storage to store signals at an applicable frequency rate. Inthis work, we propose the EventRelated Potential Encoder Network (ERPENet); amulti-task autoencoder-based model, that can be applied to any ERP-relatedtasks. The strength of ERPENet lies in its capability to handle various kindsof ERP datasets and its robustness across multiple recording setups, enablingjoint training across datasets. ERPENet incorporates Convolutional NeuralNetworks (CNNs) and Long Short-Term Memory (LSTM), in an autoencoder setup,which tries to simultaneously compress the input EEG signal and extract relatedP300 features into a latent vector. Here, we can infer the process forgenerating the latent vector as universal joint feature extraction. The networkalso includes a classification part for attended and unattended eventsclassification as an auxiliary task. We experimented on six different P300datasets. The results show that the latent vector exhibits better compressioncapability than the previous state-of-the-art semi-supervised autoencodermodel. For attended and unattended events classification, pre-trained weightsare adopted as initial weights and tested on unseen P300 datasets to evaluatethe adaptability of the model, which shortens the training process as comparedto using random Xavier weight initialization. At the compression rate of 6.84,the classification accuracy outperforms conventional P300 classificationmodels: XdawnLDA, DeepConvNet, and EEGNet achieving 79.37% - 88.52%classification accuracy depending on the dataset.

Universal Joint Feature Extraction for P300 EEG Classification using Multi-task Autoencoder