Please use this identifier to cite or link to this item: http://dx.doi.org/10.14279/depositonce-9920
For citation please use:
Main Title: Using the General Linear Model to Improve Performance in fNIRS Single Trial Analysis and Classification: A Perspective
Author(s): von Lühmann, Alexander
Ortega-Martinez, Antonio
Boas, David A.
Yücel, Meryem Ayşe
Type: Article
Language Code: en
Abstract: Within a decade, single trial analysis of functional Near Infrared Spectroscopy (fNIRS) signals has gained significant momentum, and fNIRS joined the set of modalities frequently used for active and passive Brain Computer Interfaces (BCI). A great variety of methods for feature extraction and classification have been explored using state-of-the-art Machine Learning methods. In contrast, signal preprocessing and cleaning pipelines for fNIRS often follow simple recipes and so far rarely incorporate the available state-of-the-art in adjacent fields. In neuroscience, where fMRI and fNIRS are established neuroimaging tools, evoked hemodynamic brain activity is typically estimated across multiple trials using a General Linear Model (GLM). With the help of the GLM, subject, channel, and task specific evoked hemodynamic responses are estimated, and the evoked brain activity is more robustly separated from systemic physiological interference using independent measures of nuisance regressors, such as short-separation fNIRS measurements. When correctly applied in single trial analysis, e.g., in BCI, this approach can significantly enhance contrast to noise ratio of the brain signal, improve feature separability and ultimately lead to better classification accuracy. In this manuscript, we provide a brief introduction into the GLM and show how to incorporate it into a typical BCI preprocessing pipeline and cross-validation. Using a resting state fNIRS data set augmented with synthetic hemodynamic responses that provide ground truth brain activity, we compare the quality of commonly used fNIRS features for BCI that are extracted from (1) conventionally preprocessed signals, and (2) signals preprocessed with the GLM and physiological nuisance regressors. We show that the GLM-based approach can provide better single trial estimates of brain activity as well as a new feature type, i.e., the weight of the individual and channel-specific hemodynamic response function (HRF) regressor. The improved estimates yield features with higher separability, that significantly enhance accuracy in a binary classification task when compared to conventional preprocessing—on average +7.4% across subjects and feature types. We propose to adapt this well-established approach from neuroscience to the domain of single-trial analysis and preprocessing wherever the classification of evoked brain activity is of concern, for instance in BCI.
URI: https://depositonce.tu-berlin.de/handle/11303/11032
http://dx.doi.org/10.14279/depositonce-9920
Issue Date: 18-Feb-2020
Date Available: 27-Apr-2020
DDC Class: 610 Medizin und Gesundheit
Subject(s): fNIRS
BCI
GLM
preprocessing
classification
HRF
short-separation
nuisance regression
License: https://creativecommons.org/licenses/by/4.0/
Journal Title: Frontiers in Human Neuroscience
Publisher: Frontiers Media S.A.
Publisher Place: Lausanne
Volume: 14
Article Number: 30
Publisher DOI: 10.3389/fnhum.2020.00030
EISSN: 1662-5161
Appears in Collections:FG Maschinelles Lernen » Publications

Files in This Item:
fnhum-14-00030.pdf
Format: Adobe PDF | Size: 17.2 MB
DownloadShow Preview
Thumbnail
fnhum-14-00030-g0001.tif
Format: TIFF | Size: 133.35 kB
Download
Thumbnail
fnhum-14-00030-g0002.tif
Format: TIFF | Size: 420.98 kB
Download
Thumbnail
fnhum-14-00030-g0003.tif
Format: TIFF | Size: 173.06 kB
Download
Thumbnail
fnhum-14-00030-g0004.tif
Format: TIFF | Size: 636.43 kB
Download
Thumbnail
fnhum-14-00030-g0005.tif
Format: TIFF | Size: 245.12 kB
Download
Thumbnail
fnhum-14-00030-g0006.tif
Format: TIFF | Size: 632.28 kB
Download
Thumbnail
fnhum-14-00030-g0007.tif
Format: TIFF | Size: 280.07 kB
Download
Thumbnail
fnhum-14-00030-g0008.tif
Format: TIFF | Size: 185.39 kB
Download
Thumbnail
fnhum-14-00030-g0009.tif
Format: TIFF | Size: 337.36 kB
Download
Thumbnail
fnhum-14-00030-g0010.tif
Format: TIFF | Size: 179.22 kB
Download
Thumbnail
fnhum-14-00030-g0011.tif
Format: TIFF | Size: 631.25 kB
Download
Thumbnail
fnhum-14-00030-g0012.tif
Format: TIFF | Size: 861.5 kB
Download
Thumbnail
Table_1.XLSX
Format: Microsoft Excel XML | Size: 37.51 kB
Download

Item Export Bar

This item is licensed under a Creative Commons License Creative Commons