Gate Control Mechanisms of Autoencoders for EEG Signal Reconstruction

Electroencephalography (EEG) is a non-invasive and portable way to capture neurophysiological activity, which provides the basis for brain–computer interface systems and more innovative applications, from entertainment to security. However, the acquisition of EEG signals often suffers from noise con...

Full description

Saved in:
Bibliographic Details
Main Authors: Kangjing Li, Heba El-Fiqi, Min Wang
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Sensors
Subjects:
Online Access:https://www.mdpi.com/1424-8220/25/11/3389
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849722480051093504
author Kangjing Li
Heba El-Fiqi
Min Wang
author_facet Kangjing Li
Heba El-Fiqi
Min Wang
author_sort Kangjing Li
collection DOAJ
description Electroencephalography (EEG) is a non-invasive and portable way to capture neurophysiological activity, which provides the basis for brain–computer interface systems and more innovative applications, from entertainment to security. However, the acquisition of EEG signals often suffers from noise contamination and even signal interruption problems due to poor contact of the electrodes, body movement, or heavy noise. Such heavily contaminated and lost signal segments are usually removed manually, which can hinder practical system deployment and application performance, especially in scenarios where continuous signals are required. In our previous work, we proposed the weighted gate layer autoencoder (WGLAE) and demonstrated its effectiveness in learning dependencies in EEG time series and encoding relationships among EEG channels. The WGLAE adopts a gate layer to encourage the AE to approximate multiple relationships simultaneously by controlling the data flow of each input variable. However, it only applies a sequential control scheme without taking into account the physical meaning of EEG channel locations. In this study, we investigate the gating mechanism for WGLAE and validate the importance of having a proper gating scheme for learning relationships between EEG channels. To this end, several gate control mechanisms are designed that embed EEG channel locations and their corresponding underlying physical meanings. The influences introduced by the proposed gate control mechanisms are examined on an open dataset with different scales and associated with various stimuli. The experimental results suggest that the gating mechanisms have varying influences on reconstructing EEG signals.
format Article
id doaj-art-98cd8fdd07d049cf8ddebe64392fa65a
institution DOAJ
issn 1424-8220
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Sensors
spelling doaj-art-98cd8fdd07d049cf8ddebe64392fa65a2025-08-20T03:11:20ZengMDPI AGSensors1424-82202025-05-012511338910.3390/s25113389Gate Control Mechanisms of Autoencoders for EEG Signal ReconstructionKangjing Li0Heba El-Fiqi1Min Wang2School of Systems and Computing, University of New South Wales, Canberra, ACT 2612, AustraliaSchool of Systems and Computing, University of New South Wales, Canberra, ACT 2612, AustraliaSchool of Systems and Computing, University of New South Wales, Canberra, ACT 2612, AustraliaElectroencephalography (EEG) is a non-invasive and portable way to capture neurophysiological activity, which provides the basis for brain–computer interface systems and more innovative applications, from entertainment to security. However, the acquisition of EEG signals often suffers from noise contamination and even signal interruption problems due to poor contact of the electrodes, body movement, or heavy noise. Such heavily contaminated and lost signal segments are usually removed manually, which can hinder practical system deployment and application performance, especially in scenarios where continuous signals are required. In our previous work, we proposed the weighted gate layer autoencoder (WGLAE) and demonstrated its effectiveness in learning dependencies in EEG time series and encoding relationships among EEG channels. The WGLAE adopts a gate layer to encourage the AE to approximate multiple relationships simultaneously by controlling the data flow of each input variable. However, it only applies a sequential control scheme without taking into account the physical meaning of EEG channel locations. In this study, we investigate the gating mechanism for WGLAE and validate the importance of having a proper gating scheme for learning relationships between EEG channels. To this end, several gate control mechanisms are designed that embed EEG channel locations and their corresponding underlying physical meanings. The influences introduced by the proposed gate control mechanisms are examined on an open dataset with different scales and associated with various stimuli. The experimental results suggest that the gating mechanisms have varying influences on reconstructing EEG signals.https://www.mdpi.com/1424-8220/25/11/3389autoencoder (AE)gate controldata reconstructionneural networksunsupervised learning
spellingShingle Kangjing Li
Heba El-Fiqi
Min Wang
Gate Control Mechanisms of Autoencoders for EEG Signal Reconstruction
Sensors
autoencoder (AE)
gate control
data reconstruction
neural networks
unsupervised learning
title Gate Control Mechanisms of Autoencoders for EEG Signal Reconstruction
title_full Gate Control Mechanisms of Autoencoders for EEG Signal Reconstruction
title_fullStr Gate Control Mechanisms of Autoencoders for EEG Signal Reconstruction
title_full_unstemmed Gate Control Mechanisms of Autoencoders for EEG Signal Reconstruction
title_short Gate Control Mechanisms of Autoencoders for EEG Signal Reconstruction
title_sort gate control mechanisms of autoencoders for eeg signal reconstruction
topic autoencoder (AE)
gate control
data reconstruction
neural networks
unsupervised learning
url https://www.mdpi.com/1424-8220/25/11/3389
work_keys_str_mv AT kangjingli gatecontrolmechanismsofautoencodersforeegsignalreconstruction
AT hebaelfiqi gatecontrolmechanismsofautoencodersforeegsignalreconstruction
AT minwang gatecontrolmechanismsofautoencodersforeegsignalreconstruction