Applying Dimensionality Reduction Techniques in Source-Space Electroencephalography via Template and Magnetic Resonance Imaging-Derived Head Models to Continuously Decode Hand Trajectories
Several studies showed evidence supporting the possibility of hand trajectory decoding from low-frequency electroencephalography (EEG). However, the decoding in the source space via source localization is scarcely investigated. In this study, we tried to tackle the problem of collinearity due to the...
Main Authors: | , |
---|---|
Format: | Article |
Language: | English |
Published: |
Frontiers Media S.A.
2022-03-01
|
Series: | Frontiers in Human Neuroscience |
Subjects: | |
Online Access: | https://www.frontiersin.org/articles/10.3389/fnhum.2022.830221/full |
_version_ | 1811332443512242176 |
---|---|
author | Nitikorn Srisrisawang Gernot R. Müller-Putz Gernot R. Müller-Putz |
author_facet | Nitikorn Srisrisawang Gernot R. Müller-Putz Gernot R. Müller-Putz |
author_sort | Nitikorn Srisrisawang |
collection | DOAJ |
description | Several studies showed evidence supporting the possibility of hand trajectory decoding from low-frequency electroencephalography (EEG). However, the decoding in the source space via source localization is scarcely investigated. In this study, we tried to tackle the problem of collinearity due to the higher number of signals in the source space by two folds: first, we selected signals in predefined regions of interest (ROIs); second, we applied dimensionality reduction techniques to each ROI. The dimensionality reduction techniques were computing the mean (Mean), principal component analysis (PCA), and locality preserving projections (LPP). We also investigated the effect of decoding between utilizing a template head model and a subject-specific head model during the source localization. The results indicated that applying source-space decoding with PCA yielded slightly higher correlations and signal-to-noise (SNR) ratios than the sensor-space approach. We also observed slightly higher correlations and SNRs when applying the subject-specific head model than the template head model. However, the statistical tests revealed no significant differences between the source-space and sensor-space approaches and no significant differences between subject-specific and template head models. The decoder with Mean and PCA utilizes information mainly from precuneus and cuneus to decode the velocity kinematics similarly in the subject-specific and template head models. |
first_indexed | 2024-04-13T16:37:13Z |
format | Article |
id | doaj.art-54266c66d7674c2db710f9a940e9c068 |
institution | Directory Open Access Journal |
issn | 1662-5161 |
language | English |
last_indexed | 2024-04-13T16:37:13Z |
publishDate | 2022-03-01 |
publisher | Frontiers Media S.A. |
record_format | Article |
series | Frontiers in Human Neuroscience |
spelling | doaj.art-54266c66d7674c2db710f9a940e9c0682022-12-22T02:39:24ZengFrontiers Media S.A.Frontiers in Human Neuroscience1662-51612022-03-011610.3389/fnhum.2022.830221830221Applying Dimensionality Reduction Techniques in Source-Space Electroencephalography via Template and Magnetic Resonance Imaging-Derived Head Models to Continuously Decode Hand TrajectoriesNitikorn Srisrisawang0Gernot R. Müller-Putz1Gernot R. Müller-Putz2Institute of Neural Engineering, Graz University of Technology, Graz, AustriaInstitute of Neural Engineering, Graz University of Technology, Graz, AustriaBioTechMed Graz, Graz, AustriaSeveral studies showed evidence supporting the possibility of hand trajectory decoding from low-frequency electroencephalography (EEG). However, the decoding in the source space via source localization is scarcely investigated. In this study, we tried to tackle the problem of collinearity due to the higher number of signals in the source space by two folds: first, we selected signals in predefined regions of interest (ROIs); second, we applied dimensionality reduction techniques to each ROI. The dimensionality reduction techniques were computing the mean (Mean), principal component analysis (PCA), and locality preserving projections (LPP). We also investigated the effect of decoding between utilizing a template head model and a subject-specific head model during the source localization. The results indicated that applying source-space decoding with PCA yielded slightly higher correlations and signal-to-noise (SNR) ratios than the sensor-space approach. We also observed slightly higher correlations and SNRs when applying the subject-specific head model than the template head model. However, the statistical tests revealed no significant differences between the source-space and sensor-space approaches and no significant differences between subject-specific and template head models. The decoder with Mean and PCA utilizes information mainly from precuneus and cuneus to decode the velocity kinematics similarly in the subject-specific and template head models.https://www.frontiersin.org/articles/10.3389/fnhum.2022.830221/fullelectroencephalography (EEG)magnetic resonance imaging (MRI)source localizationpartial least squares regressionunscented Kalman filterfrontoparietal network |
spellingShingle | Nitikorn Srisrisawang Gernot R. Müller-Putz Gernot R. Müller-Putz Applying Dimensionality Reduction Techniques in Source-Space Electroencephalography via Template and Magnetic Resonance Imaging-Derived Head Models to Continuously Decode Hand Trajectories Frontiers in Human Neuroscience electroencephalography (EEG) magnetic resonance imaging (MRI) source localization partial least squares regression unscented Kalman filter frontoparietal network |
title | Applying Dimensionality Reduction Techniques in Source-Space Electroencephalography via Template and Magnetic Resonance Imaging-Derived Head Models to Continuously Decode Hand Trajectories |
title_full | Applying Dimensionality Reduction Techniques in Source-Space Electroencephalography via Template and Magnetic Resonance Imaging-Derived Head Models to Continuously Decode Hand Trajectories |
title_fullStr | Applying Dimensionality Reduction Techniques in Source-Space Electroencephalography via Template and Magnetic Resonance Imaging-Derived Head Models to Continuously Decode Hand Trajectories |
title_full_unstemmed | Applying Dimensionality Reduction Techniques in Source-Space Electroencephalography via Template and Magnetic Resonance Imaging-Derived Head Models to Continuously Decode Hand Trajectories |
title_short | Applying Dimensionality Reduction Techniques in Source-Space Electroencephalography via Template and Magnetic Resonance Imaging-Derived Head Models to Continuously Decode Hand Trajectories |
title_sort | applying dimensionality reduction techniques in source space electroencephalography via template and magnetic resonance imaging derived head models to continuously decode hand trajectories |
topic | electroencephalography (EEG) magnetic resonance imaging (MRI) source localization partial least squares regression unscented Kalman filter frontoparietal network |
url | https://www.frontiersin.org/articles/10.3389/fnhum.2022.830221/full |
work_keys_str_mv | AT nitikornsrisrisawang applyingdimensionalityreductiontechniquesinsourcespaceelectroencephalographyviatemplateandmagneticresonanceimagingderivedheadmodelstocontinuouslydecodehandtrajectories AT gernotrmullerputz applyingdimensionalityreductiontechniquesinsourcespaceelectroencephalographyviatemplateandmagneticresonanceimagingderivedheadmodelstocontinuouslydecodehandtrajectories AT gernotrmullerputz applyingdimensionalityreductiontechniquesinsourcespaceelectroencephalographyviatemplateandmagneticresonanceimagingderivedheadmodelstocontinuouslydecodehandtrajectories |