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

Downsampling01:20

Downsampling

458
When considering a sampled sequence with zero values between sampling instants, one can replace it by taking every N-th value of the sequence. At these integer multiples of N, the original and sampled sequences coincide. This process, known as decimation, involves extracting every N-th sample from a sequence, thereby creating a more efficient sequence.
The Fourier transform of the decimated sequence reveals a combination of scaled and shifted versions of the original spectrum. This...
458

You might also read

Related Articles

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

Sort by
Same author

Practice beyond performance stabilization increases the use of online adjustments to unpredictable perturbations in an interceptive task.

PloS one·2025
Same author

Idiosyncratic multisensory reweighting as the common cause for motion sickness susceptibility and adaptation to postural perturbation.

PloS one·2021
Same author

Real and visually-induced body inclination differently affect the perception of object stability.

PloS one·2017
Same author

Fearful but not happy expressions boost face detection in human infants.

Proceedings. Biological sciences·2017
Same author

Behavioral evidence for a differential modulation of semantic processing and lexical production by aging: a full linear mixed-effects modeling approach.

Neuropsychology, development, and cognition. Section B, Aging, neuropsychology and cognition·2016

Related Experiment Video

Updated: Nov 23, 2025

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms
08:51

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

5.9K

A dimension reduction technique applied to regression on high dimension, low sample size neurophysiological data

Adrielle C Santana1,2,3, Adriano V Barbosa4,5, Hani C Yehia4,5

  • 1Graduate Program in Electrical Engineering, Universidade Federal de Minas Gerais, Av. Pres. Antônio Carlos 6627, 31270-901, Belo Horizonte, Brazil. adrielle@ufop.edu.br.

BMC Neuroscience
|January 5, 2021
PubMed
Summary

We developed RoLDSIS, a novel regression technique for analyzing high-dimensional neurophysiological data without regularization parameters. This method reliably estimates neurophysiological correlates of phonemic categorization from EEG data, offering interpretable results.

Keywords:
Dimension reductionDiscrete wavelet transformElectroencephalographyEvent-related potentialsHigh dimension low sample size problemLinear regressionPhonemic categorization

More Related Videos

Simultaneous Data Collection of fMRI and fNIRS Measurements Using a Whole-Head Optode Array and Short-Distance Channels
08:19

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

Published on: October 20, 2023

1.4K
Author Spotlight: Methodologies and Advancements of Chronic Pain Management Research
08:33

Author Spotlight: Methodologies and Advancements of Chronic Pain Management Research

Published on: January 5, 2024

1.5K

Related Experiment Videos

Last Updated: Nov 23, 2025

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms
08:51

Statistical Modelling of Cortical Connectivity Using Non-invasive Electroencephalograms

Published on: November 1, 2019

5.9K
Simultaneous Data Collection of fMRI and fNIRS Measurements Using a Whole-Head Optode Array and Short-Distance Channels
08:19

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

Published on: October 20, 2023

1.4K
Author Spotlight: Methodologies and Advancements of Chronic Pain Management Research
08:33

Author Spotlight: Methodologies and Advancements of Chronic Pain Management Research

Published on: January 5, 2024

1.5K

Area of Science:

  • Neuroscience
  • Signal Processing
  • Machine Learning

Background:

  • Extracting meaningful information from high-dimensional, low-sample-size (HDLSS) neurophysiological data is challenging.
  • Existing methods often require regularization parameters, complicating the analysis.
  • A new regression technique, RoLDSIS (regression on low-dimension spanned input space), is proposed.

Purpose of the Study:

  • To introduce and validate RoLDSIS for neurophysiological signal processing.
  • To apply RoLDSIS to EEG data from a phonemic identification experiment.
  • To infer neurophysiological correlates of phonemic categorization.

Main Methods:

  • RoLDSIS utilizes dimensionality reduction, constraining solutions to the subspace of observations.
  • EEG data from a /da/-/ta/ morphed syllable identification experiment were analyzed.
  • Discrete wavelet transform was used for time-frequency feature extraction.
  • RoLDSIS inferred neurophysiological axes associated with stimulus attributes.

Main Results:

  • RoLDSIS reliably estimated neurophysiological axes in the time-frequency domain.
  • The separation of these axes correlated with individual phonemic categorization strength.
  • Prediction errors were comparable to Ridge Regression and better than LASSO/SPLS.

Conclusions:

  • RoLDSIS effectively processes and interprets neurophysiological signals without regularization parameters.
  • The method avoids cross-validation, preserving signal-to-noise ratio.
  • RoLDSIS offers a simple yet powerful approach for analyzing complex neurophysiological data.