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

Working Memory

Working Memory

Working memory refers to a combination of components, including short-term memory and attention, that allow an individual to hold information temporarily as we perform cognitive tasks. It is an essential cognitive function that enables the execution of complex tasks such as problem-solving, comprehension, and reasoning. Unlike short-term memory, which simply involves the storage of information for a brief period, working memory involves the active manipulation and processing of this...

You might also read

Related Articles

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

Sort by

Same author

Fresh-State Characteristics of Geopolymer Mortars for 3D Printing: Mix Design, Rheology and Early-Age Performance.

Polymers·2026

Same author

Boron supplementation enhances yield, photosynthetic efficiency, enzyme activity, and mineral content in Persian clover (Trifolium resupinatum L.).

Die Naturwissenschaften·2026

Same author

Quantitative assessment of thoracolumbosacral orthosis efficacy on the temporal features of gait using inertial measurement unit sensors.

Scientific reports·2026

Same author

Investigating cognitive fatigue recovery through mechanical massage and binaural beats: An AI-driven fNIRS study.

Journal of bodywork and movement therapies·2026

Same author

Negative pressure intrusion cementation versus tourniquet use in total knee arthroplasty: optimising cement mantle thickness.

European journal of orthopaedic surgery & traumatology : orthopedie traumatologie·2026

Same author

Decoding the Role of Nutrition and Foods in Augmenting Athletes Performance: A Review.

Current drug research reviews·2026

Same journal

Relationship between spontaneous EEG oscillations at 7 and 45 days of acute plateau exposure and the plateau acclimatization index.

Frontiers in neuroscience·2026

Same journal

Neuroprotective effects of paederoside against mitochondrial dysfunction in rotenone-induced cell models of Parkinson's disease.

Frontiers in neuroscience·2026

Same journal

Covariance-based analysis of spindle-band EEG during declarative and non-declarative odor cueing in sleep.

Frontiers in neuroscience·2026

Same journal

Correction: Physiological determinants of cortical P100 responses in pattern visual evoked potentials: a scoping review.

Frontiers in neuroscience·2026

Same journal

Transcranial magnetic stimulation and motor overflow: a systematic review in neurological disorders.

Frontiers in neuroscience·2026

Same journal

Editorial: Advancing neurodegenerative disease biomarkers: the role of neuroimaging in TDP-43 and tau proteinopathies.

Frontiers in neuroscience·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Dec 15, 2025

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation

Published on: September 8, 2023

Enhanced Accuracy for Multiclass Mental Workload Detection Using Long Short-Term Memory for Brain-Computer Interface.

Umer Asgher¹, Khurram Khalil¹, Muhammad Jawad Khan¹

¹School of Mechanical and Manufacturing Engineering (SMME), National University of Sciences and Technology (NUST), Islamabad, Pakistan.

Frontiers in Neuroscience

|July 14, 2020

Summary

This summary is machine-generated.

Deep learning models, specifically Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNN), accurately decode mental workload (MWL) levels using functional near-infrared spectroscopy (fNIRS) brain data for brain-computer interfaces (BCI). These advanced methods significantly outperform traditional machine learning techniques in classifying cognitive states.

Keywords:

brain–computer interface convolutional neural network deep learning deep neural networks functional near-infrared spectroscopy long short-term memory mental workload

More Related Videos

Assessment and Communication for People with Disorders of Consciousness

Assessment and Communication for People with Disorders of Consciousness

Published on: August 1, 2017

A Single-Channel and Non-Invasive Wearable Brain-Computer Interface for Industry and Healthcare

A Single-Channel and Non-Invasive Wearable Brain-Computer Interface for Industry and Healthcare

Published on: July 7, 2023

Related Experiment Videos

Last Updated: Dec 15, 2025

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation

P300-Based Brain-Computer Interface Speller Performance Estimation with Classifier-Based Latency Estimation

Published on: September 8, 2023

Assessment and Communication for People with Disorders of Consciousness

Assessment and Communication for People with Disorders of Consciousness

Published on: August 1, 2017

A Single-Channel and Non-Invasive Wearable Brain-Computer Interface for Industry and Healthcare

A Single-Channel and Non-Invasive Wearable Brain-Computer Interface for Industry and Healthcare

Published on: July 7, 2023

Area of Science:

Neuroergonomics
Human-Machine Interaction (HMI)
Cognitive Neuroscience

Background:

Accurate assessment of cognitive and mental workload (MWL) is crucial for human-machine interaction and neuroergonomics.
Neuroimaging techniques are vital for monitoring brain activity and evaluating cognitive states.
Existing machine learning (ML) methods show moderate success in classifying MWL.

Purpose of the Study:

To decode four classes of MWL using advanced deep learning (DL) frameworks.
To compare the performance of DL models against traditional ML techniques for MWL classification.
To assess the efficacy of functional near-infrared spectroscopy (fNIRS) for real-time MWL monitoring.

Main Methods:

Acquired functional near-infrared spectroscopy (fNIRS) data from the prefrontal cortex (PFC) of 15 participants during a supervised MWL experiment with four distinct levels.
Classified MWL states using traditional ML algorithms: Support Vector Machine (SVM), k-Nearest Neighbor (k-NN), and Artificial Neural Network (ANN).
Developed and applied novel DL frameworks, including Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM), for MWL classification.

Main Results:

Deep learning models achieved significantly higher average accuracies: CNN at 87.45% and LSTM at 89.31%.
Traditional ML algorithms yielded lower average accuracies: SVM (54.33%), k-NN (54.31%), and ANN (69.36%).
Statistical analyses (t-test, ANOVA) confirmed the significant improvement in classification performance with DL algorithms over ML algorithms.

Conclusions:

Novel deep learning frameworks (CNN and LSTM) demonstrate superior performance in classifying multi-level cognitive states compared to conventional ML methods.
fNIRS combined with DL offers a promising approach for accurate, real-time assessment of mental workload in brain-computer interface applications.
The findings highlight the potential of neuroergonomics and advanced computational techniques to enhance human-machine interaction.