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

Montefiore Einstein Robust Geriatric Normative Project (MERGER-NP): standardized regression-based formulas and multivariate base rates for evaluating cognitive change.

Archives of clinical neuropsychology : the official journal of the National Academy of Neuropsychologists·2026

Same author

Assessment of Abbreviated Neurocognitive Tasks via a Custom-Built Mobile Platform.

Scientific reports·2026

Same author

A Pocket Laboratory for Functional Neuroimaging Research Using Mobile Visual Oddball, Multimodal Electroencephalography, and Functional Near-Infrared Spectroscopy Imaging: Instrument Validation Study.

JMIR neurotechnology·2026

Same author

Multimodal neurocognitive assessment of internet gaming disorder using ERP and fNIRS during an oddball paradigm: A machine learning-based classification.

Behavioural brain research·2026

Same author

Induced current effects on functional magnetic resonance imaging interpretability during monopolar deep brain stimulation.

Journal of neurosurgery·2026

Same author

Graph-Based Deep Learning Models for Predicting p<i>K</i><sub>a</sub> Values of Protein-Ionizable Residues via Physically Inspired Feature Engineering.

Journal of chemical information and modeling·2026

Same journal

Pathology-Informed Augmentation Improves Cross-Cohort IMU-to-vGRF Estimation Between Healthy Adults and Adults With Osteoarthritis.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2026

Same journal

Effects of task-driven head orientations on gait and balance during walking in virtual reality.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2026

Same journal

Wearable sensor-based Mild Cognitive Impairment Identification: A Multi-Domain Gait Analysis Approach with Association Rule Mining.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2026

Same journal

Semi-implantable Micro-cooler for Dorsal Root Ganglion Enables Targeted, Sustained, and Cumulative Pain Relief.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2026

Same journal

Auditory Cue Integration for a Power-Assisted Gait Training System Based on Neurodevelopmental Treatment Principles.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2026

Same journal

Quantifying the dynamics that link leg tendon vibration to induced periodic postural oscillations in young subjects Differential effects of light touch on the induced sway.

IEEE transactions on neural systems and rehabilitation engineering : a publication of the IEEE Engineering in Medicine and Biology Society·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Jul 19, 2025

Using Fiberless, Wearable fNIRS to Monitor Brain Activity in Real-world Cognitive Tasks

Using Fiberless, Wearable fNIRS to Monitor Brain Activity in Real-world Cognitive Tasks

Published on: December 2, 2015

Deep Learning Based Walking Tasks Classification in Older Adults Using fNIRS.

Dongning Ma, Meltem Izzetoglu, Roee Holtzer

IEEE Transactions on Neural Systems and Rehabilitation Engineering : a Publication of the IEEE Engineering in Medicine and Biology Society

|August 18, 2023

Summary

This summary is machine-generated.

This study introduces a deep learning method to automatically classify attentional states during walking in older adults. The approach accurately distinguishes between low and high attention states, aiding in fall risk assessment.

More Related Videos

Revised and Neuroimaging-Compatible Versions of the Dual Task Screen

Revised and Neuroimaging-Compatible Versions of the Dual Task Screen

Published on: October 5, 2020

fMRI Validation of fNIRS Measurements During a Naturalistic Task

fMRI Validation of fNIRS Measurements During a Naturalistic Task

Published on: June 15, 2015

Related Experiment Videos

Last Updated: Jul 19, 2025

Using Fiberless, Wearable fNIRS to Monitor Brain Activity in Real-world Cognitive Tasks

Using Fiberless, Wearable fNIRS to Monitor Brain Activity in Real-world Cognitive Tasks

Published on: December 2, 2015

Revised and Neuroimaging-Compatible Versions of the Dual Task Screen

Revised and Neuroimaging-Compatible Versions of the Dual Task Screen

Published on: October 5, 2020

fMRI Validation of fNIRS Measurements During a Naturalistic Task

fMRI Validation of fNIRS Measurements During a Naturalistic Task

Published on: June 15, 2015

Area of Science:

Neuroscience
Biomedical Engineering
Gerontology

Background:

Gait decline in older adults is linked to increased disability and mortality.
Dual task walking (DTW) exacerbates gait and cognitive deficits, correlating with falls history.
Cortical activity in the pre-frontal cortex (PFC) during DTW is measurable via functional near-infrared spectroscopy (fNIRS).

Purpose of the Study:

To develop an automatic classification system for low (single task walking - STW) and high (DTW) attentional walking states in older adults.
To leverage deep learning for classifying cognitive activations during different walking conditions.
To enhance classification accuracy by incorporating fNIRS data, gender, and cognitive status.

Main Methods:

Formulated STW as a low attentional state and DTW as a high attentional state.
Analyzed fNIRS data, focusing on differences between HbO2 and Hb values as features.
Engineered fNIRS features into 3-channel images and applied data augmentation for deep learning models.
Fine-tuned pre-trained deep learning models with the fNIRS dataset, gender, and cognitive status.

Main Results:

Achieved approximately 81% classification accuracy, outperforming traditional machine learning by ~10%.
Demonstrated the effectiveness of using HbO2 - Hb as a third channel in the input image.
Identified that using a pre-trained model and all voxel locations yields the best classification performance.

Conclusions:

Deep learning models can effectively classify attentional states during walking in older adults using fNIRS data.
The proposed method offers a promising approach for objective assessment of cognitive load during gait.
Findings support the potential for improved fall risk prediction and intervention strategies.