Electroencephalogram (EEG) is prone to several artifacts that often lead to misclassification of neural features in Brain-Computer Interfaces (BCI) [1]. In recent years, deep learning (DL) techniques have been successfully used to decode brain activities using EEG data [2]. Most of the proposed methods use a hand-made preprocessing strategy to remove EEG noise before feeding the data into Neural Networks (NNs) [2], [3]. In contrast, others do not explicitly mention the preprocessing performed.
Towards a Domain-Specific Neural Network Approach for EEG Bad Channel Detection
Velu Kumaravel;Francesco Paissan;Elisabetta Farella
2021-01-01
Abstract
Electroencephalogram (EEG) is prone to several artifacts that often lead to misclassification of neural features in Brain-Computer Interfaces (BCI) [1]. In recent years, deep learning (DL) techniques have been successfully used to decode brain activities using EEG data [2]. Most of the proposed methods use a hand-made preprocessing strategy to remove EEG noise before feeding the data into Neural Networks (NNs) [2], [3]. In contrast, others do not explicitly mention the preprocessing performed.File in questo prodotto:
Non ci sono file associati a questo prodotto.
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
