Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Cortical activity during narrative discourse production in individuals with post-stroke aphasia and controls measured via functional near-infrared spectroscopy.

medRxiv : the preprint server for health sciences·2026

Same author

Visual gamma stimulation causes prolonged enhancement of low-frequency blood flow oscillations across cortical regions in mice.

bioRxiv : the preprint server for biology·2026

Same author

fNIRS single-trial decoding improves systematically with higher optode density, model-based noise regression, and image reconstruction.

Journal of neural engineering·2026

Same author

Comparative validation of speckle contrast optical spectroscopy against diffuse correlation spectroscopy for monitoring human cerebral blood flow.

Neurophotonics·2026

Same author

Mapping Slow Speckle Dynamics to Probe Cellular Metabolic Activity In Vivo using Laser Speckle Contrast Imaging.

bioRxiv : the preprint server for biology·2026

Same author

The neurovascular impulse response function differentially reflects intrinsic neuromodulation across cortical regions.

Nature neuroscience·2026

Search research articles

Related Experiment Video

Updated: Dec 27, 2025

Simultaneous Data Collection of fMRI and fNIRS Measurements Using a Whole-Head Optode Array and Short-Distance Channels

Simultaneous Data Collection of fMRI and fNIRS Measurements Using a Whole-Head Optode Array and Short-Distance Channels

Published on: October 20, 2023

Using the General Linear Model to Improve Performance in fNIRS Single Trial Analysis and Classification: A

Alexander von Lühmann^1,2, Antonio Ortega-Martinez¹, David A Boas¹

¹Neurophotonics Center, Biomedical Engineering, Boston University, Boston, MA, United States.

Frontiers in Human Neuroscience

|March 6, 2020

Summary

This study introduces the General Linear Model (GLM) for functional Near Infrared Spectroscopy (fNIRS) signal preprocessing in Brain Computer Interfaces (BCI). Applying GLM improves brain signal analysis, enhancing classification accuracy for evoked brain activity.

Keywords:

BCI GLM HRF classification fNIRS nuisance regression preprocessing short-separation

More Related Videos

A Protocol for the Administration of Real-Time fMRI Neurofeedback Training

A Protocol for the Administration of Real-Time fMRI Neurofeedback Training

Published on: August 24, 2017

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques

Published on: June 30, 2020

Related Experiment Videos

Last Updated: Dec 27, 2025

Simultaneous Data Collection of fMRI and fNIRS Measurements Using a Whole-Head Optode Array and Short-Distance Channels

Simultaneous Data Collection of fMRI and fNIRS Measurements Using a Whole-Head Optode Array and Short-Distance Channels

Published on: October 20, 2023

A Protocol for the Administration of Real-Time fMRI Neurofeedback Training

A Protocol for the Administration of Real-Time fMRI Neurofeedback Training

Published on: August 24, 2017

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques

Measuring Statistical Learning Across Modalities and Domains in School-Aged Children Via an Online Platform and Neuroimaging Techniques

Published on: June 30, 2020

Area of Science:

Neuroscience
Biomedical Engineering
Signal Processing

Background:

Functional Near Infrared Spectroscopy (fNIRS) is increasingly used for Brain Computer Interfaces (BCI).
Current fNIRS preprocessing for single-trial analysis often uses simplistic methods, neglecting advanced techniques from neuroscience.
Established neuroimaging methods like fMRI and fNIRS utilize the General Linear Model (GLM) for robust analysis of evoked brain activity.

Purpose of the Study:

To integrate the General Linear Model (GLM) into fNIRS preprocessing pipelines for Brain Computer Interfaces (BCI).
To evaluate the effectiveness of GLM-based preprocessing in improving single-trial fNIRS signal analysis and classification accuracy.
To introduce a novel feature type derived from GLM-estimated hemodynamic responses.

Main Methods:

Incorporation of the General Linear Model (GLM) into a standard BCI preprocessing workflow and cross-validation.
Comparison of fNIRS features extracted from conventionally preprocessed signals versus GLM-preprocessed signals using synthetic ground truth data.
Utilizing physiological nuisance regressors alongside GLM for enhanced signal cleaning.

Main Results:

GLM-based preprocessing yields superior single-trial estimates of brain activity compared to conventional methods.
A new feature type, the weight of the hemodynamic response function (HRF) regressor, was identified.
Features derived from GLM-preprocessed signals demonstrated significantly higher separability, leading to an average +7.4% increase in binary classification accuracy across subjects.

Conclusions:

The General Linear Model (GLM) offers a significant improvement for fNIRS signal preprocessing in Brain Computer Interface (BCI) applications.
Adapting established neuroscience techniques like GLM can enhance the performance of single-trial evoked brain activity classification.
This approach is recommended for BCI systems requiring robust classification of evoked brain activity from fNIRS data.