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

A Multimodal Convolutional Neural Network Model for Parkinson's Disease Diagnosis Based on Fused Handwriting Dynamics Signals.

Journal of medical systems·2025
Same author

Combining features on vertical ground reaction force signal analysis for multiclass diagnosing neurodegenerative diseases.

International journal of medical informatics·2024
Same author

P300-Based Asynchronous Brain Computer Interface for Environmental Control System.

IEEE journal of biomedical and health informatics·2017
Same author

Region based Brain Computer Interface for a home control application.

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference·2016

Related Experiment Video

Updated: Dec 18, 2025

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

1.5K

Subject-Specific feature selection for near infrared spectroscopy based brain-computer interfaces.

Eda Akman Aydin1

  • 1Gazi University, Faculty of Technology, Department of Electrical and Electronics Engineering, 06500, Besevler, Ankara, Turkey.

Computer Methods and Programs in Biomedicine
|June 14, 2020
PubMed
Summary
This summary is machine-generated.

Subject-specific feature selection significantly enhances brain-computer interface (BCI) accuracy using functional near-infrared spectroscopy (fNIRS) signals. This method improves classification performance for motor imagery and mental arithmetic tasks while reducing system complexity.

Keywords:
Brain-computer interfacesFeature selectionMental arithmeticMotor imageryNear-infrared spectroscopyReliefF algorithmStepwise regression analysis

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

15.5K
Exploring Cognitive Functions in Babies, Children & Adults with Near Infrared Spectroscopy
12:40

Exploring Cognitive Functions in Babies, Children & Adults with Near Infrared Spectroscopy

Published on: July 28, 2009

20.9K

Related Experiment Videos

Last Updated: Dec 18, 2025

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

1.5K
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

15.5K
Exploring Cognitive Functions in Babies, Children & Adults with Near Infrared Spectroscopy
12:40

Exploring Cognitive Functions in Babies, Children & Adults with Near Infrared Spectroscopy

Published on: July 28, 2009

20.9K

Area of Science:

  • Neuroscience
  • Biomedical Engineering
  • Signal Processing

Background:

  • Brain-computer interfaces (BCIs) translate neural activity into device control.
  • Functional near-infrared spectroscopy (fNIRS) is an emerging non-invasive optical imaging technique for BCIs.
  • Subject-specific feature optimization is crucial for fNIRS-based BCI accuracy and efficiency.

Purpose of the Study:

  • To evaluate the effectiveness of subject-specific feature selection on fNIRS signal classification accuracy.
  • To assess the impact of feature selection on reducing the complexity of fNIRS-based BCI systems.
  • To compare different feature selection methods for fNIRS data.

Main Methods:

  • Employed stepwise regression analysis based on sequential feature selection (SWR-SFS) and ReliefF for optimal feature subset determination.
  • Applied feature selection on time-domain features (mean, slope, peak, skewness, kurtosis) of fNIRS signals.
  • Validated techniques on motor imagery (MI) and mental arithmetic (MA) fNIRS datasets from 29 healthy subjects using LDA, k-NN, and SVM classifiers.

Main Results:

  • Both SWR-SFS and ReliefF significantly improved classification accuracy.
  • SWR-SFS achieved the highest accuracy: 88.67% (HbR) and 86.43% (HbO) for MA; 77.01% (HbR) and 71.32% (HbO) for MI.
  • Feature selection led to substantial feature reduction: 89.50% (HbR) and 93.99% (HbO) for MA; 94.04% (HbR) and 97.73% (HbO) for MI.

Conclusions:

  • Subject-specific feature selection demonstrably enhances classification performance for both MA and MI-based fNIRS signals.
  • The findings highlight the importance of tailored feature selection in optimizing fNIRS BCI systems.
  • SWR-SFS proved particularly effective for improving accuracy and reducing feature dimensionality.