Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

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

DFU-GCNet: a global context-enhanced inception network for robust and interpretable diabetic foot ulcer classification.

Frontiers in digital health·2026
Same author

EcoStack-Pro: an adaptive federated learning framework for interpretable ESG auditing across heterogeneous industrial sectors.

Frontiers in artificial intelligence·2026
Same author

FedMal-XAI: an explainable federated vision transformer leveraging knowledge distillation for privacy-preserving malaria detection.

Frontiers in public health·2026
Same author

MangoLeafNet-XAI: an attention-enhanced deep learning architecture for accurate and interpretable mango leaf disease classification.

Frontiers in plant science·2026
Same author

Interpretable Network-Level Biomarker Discovery for Alzheimer's Stage Assessment Using Resting-State fNIRS Complexity Graphs.

Brain sciences·2026
Same author

Decoupled Bidirectional Spatio-Temporal Fusion Network for Hybrid EEG-fNIRS Cognitive Task Classification.

Brain sciences·2026

Related Experiment Video

Updated: Mar 13, 2026

Assessment and Communication for People with Disorders of Consciousness
07:37

Assessment and Communication for People with Disorders of Consciousness

Published on: August 1, 2017

9.7K

Analysis of Different Classification Techniques for Two-Class Functional Near-Infrared Spectroscopy-Based

Noman Naseer1, Nauman Khalid Qureshi1, Farzan Majeed Noori1

  • 1Department of Mechatronics Engineering, Air University, Sector E-9, Islamabad 44000, Pakistan.

Computational Intelligence and Neuroscience
|October 12, 2016
PubMed
Summary

Artificial neural networks (ANN) achieved the highest accuracy in classifying mental tasks using functional near-infrared spectroscopy (fNIRS) brain signals. ANN demonstrated superior performance in distinguishing mental arithmetic from rest states.

More Related Videos

Functional Near Infrared Spectroscopy of the Sensory and Motor Brain Regions with Simultaneous Kinematic and EMG Monitoring During Motor Tasks
11:31

Functional Near Infrared Spectroscopy of the Sensory and Motor Brain Regions with Simultaneous Kinematic and EMG Monitoring During Motor Tasks

Published on: December 5, 2014

15.7K
Author Spotlight: Advancing Upper Limb Rehabilitation in Patients with Right Hemisphere Damage Using Assisted Active Exercise
04:43

Author Spotlight: Advancing Upper Limb Rehabilitation in Patients with Right Hemisphere Damage Using Assisted Active Exercise

Published on: February 9, 2024

1.6K

Related Experiment Videos

Last Updated: Mar 13, 2026

Assessment and Communication for People with Disorders of Consciousness
07:37

Assessment and Communication for People with Disorders of Consciousness

Published on: August 1, 2017

9.7K
Functional Near Infrared Spectroscopy of the Sensory and Motor Brain Regions with Simultaneous Kinematic and EMG Monitoring During Motor Tasks
11:31

Functional Near Infrared Spectroscopy of the Sensory and Motor Brain Regions with Simultaneous Kinematic and EMG Monitoring During Motor Tasks

Published on: December 5, 2014

15.7K
Author Spotlight: Advancing Upper Limb Rehabilitation in Patients with Right Hemisphere Damage Using Assisted Active Exercise
04:43

Author Spotlight: Advancing Upper Limb Rehabilitation in Patients with Right Hemisphere Damage Using Assisted Active Exercise

Published on: February 9, 2024

1.6K

Area of Science:

  • Neuroscience
  • Biomedical Engineering
  • Machine Learning

Background:

  • Functional near-infrared spectroscopy (fNIRS) is a neuroimaging technique used to measure brain activity.
  • Distinguishing between different cognitive states, such as mental arithmetic and rest, is crucial for brain-computer interfaces.
  • Previous studies have explored various machine learning algorithms for fNIRS signal classification.

Purpose of the Study:

  • To compare the classification accuracies of six different machine learning algorithms for a two-class mental task (mental arithmetic vs. rest).
  • To evaluate the effectiveness of using oxygenated hemoglobin (HbO) signals from the prefrontal cortex for task classification.
  • To identify the optimal classifier for fNIRS-based mental task recognition.

Main Methods:

  • Acquired fNIRS signals from seven healthy subjects performing mental arithmetic and rest tasks.
  • Extracted six features from oxygenated hemoglobin (HbO) signals after physiological noise removal.
  • Classified tasks using two- and three-dimensional feature combinations with Linear Discriminant Analysis (LDA), Quadratic Discriminant Analysis (QDA), k-Nearest Neighbors (kNN), Naïve Bayes, Support Vector Machine (SVM), and Artificial Neural Networks (ANN).

Main Results:

  • Artificial Neural Networks (ANN) achieved the highest average classification accuracies: 91.4% for 2D features and 96.3% for 3D features.
  • Support Vector Machine (SVM) and k-Nearest Neighbors (kNN) also showed high accuracies, particularly with 3D features (95.2%).
  • Statistical significance tests confirmed ANN's superior performance (p < 0.005) compared to other classifiers.

Conclusions:

  • ANN is a highly effective classifier for distinguishing mental arithmetic from rest states using fNIRS HbO signals.
  • The use of 3D feature combinations generally improved classification accuracy across all tested algorithms.
  • fNIRS combined with advanced machine learning techniques shows significant potential for real-time cognitive state monitoring.