Illustration of the proposed CLEEGN model architecture and the model training flow.

Illustration of the proposed CLEEGN model architecture and the model training flow.

Source publication
Preprint
Full-text available
Human electroencephalography (EEG) is a brain monitoring modality that senses cortical neuroelectrophysiological activity in high-temporal resolution. One of the greatest challenges posed in applications of EEG is the unstable signal quality susceptible to inevitable artifacts during recordings. To date, most existing techniques for EEG artifact re...

Contexts in source publication

Context 1
... is designed to map multi-channel noisy EEG into a latent space and reconstruct it into noiseless EEG signals. The architecture of CLEEGN is shown in Figure 1. The architecture of the encoder is inspired by an existing CNN model designed for EEG recognition ( Wei et al., 2019) and incorporates convolutional blocks that capture spatiotemporal characteristics of EEG data. ...
Context 2
... illustrated in Figure 1, the objective of the proposed method is to minimize the difference between noiseless signals, Y , and the model output, ˆ Y . The recording EEG data, X, is the combination of brain signals, Y , and the signals from multiple noise sources, N . ...
Context 3
... use the power spectrum density (PSD) to interpret the result of decoding performance. Figure 10 shows the PSD of EEG event data in each class denoised by different methods. We can see the reconstructed EEG spectrum from CLEEGN in each class is similar to the reference. ...

Similar publications

Article
Full-text available
The current study aims to explore the factors that could affect people’s description of a motion event endpoint. The study conducted by Liao, Dijkstra, and Zwaan (2021, Language and Cognition, 13[2], 161–190) found that two non-linguistic factors (i.e., the actor’s goal and the interlocutor’s social status) affect people’s choice between two Dutch...