Search research articles

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

The impact of prenatal and postnatal acoustic experience to the discrimination of native versus non-native linguistic rules in the brain: insights from combined electrophysiological and vascular signals in 3-month-olds.

Developmental cognitive neuroscience·2026

Same author

Deep learning for early detection of Zenker's diverticulum based on swallowing sound analysis.

International journal of computer assisted radiology and surgery·2026

Same author

Pre-Stimulus Head Position and Its Effect on Sound Localization Metrics in Children.

Audiology research·2026

Same author

Antidepressant Intake and Recovery of Dysphagia After Acute Ischemic Stroke.

Stroke·2026

Same author

Relation between open-field stapedius reflex thresholds and speech perception in CI users.

International journal of audiology·2026

Same author

Spectral Analysis of Extrahepatic Bile Ducts During Normothermic Liver Machine Perfusion.

Bioengineering (Basel, Switzerland)·2025

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

Search research articles

Related Experiment Video

Updated: May 30, 2025

How to Find Effects of Stimulus Processing on Event Related Brain Potentials of Close Others when Hyperscanning Partners

How to Find Effects of Stimulus Processing on Event Related Brain Potentials of Close Others when Hyperscanning Partners

Published on: May 31, 2018

Beyond averaging: A transformer approach to decoding event related brain potentials.

Philipp Zelger¹, Manuel Arnold², Sonja Rossi¹

¹University Hospital for Hearing, Speech & Voice Disorders, Medical University of Innsbruck, Anichstrasse 35, Innsbruck, 6020, Austria; ICONE - Innsbruck Cognitive Neuroscience, Medical University of Innsbruck, Anichstrasse 35, Innsbruck, 6020, Austria.

|January 26, 2025

Summary

This summary is machine-generated.

Transformer deep learning with attention maps offers deeper insights into electroencephalographic (EEG) event-related potentials (ERPs) than traditional averaging. This approach reveals crucial neural signal timings, enhancing ERP analysis.

Keywords:

Deep learning EEG Event related potentials Loudness perception Transformer

More Related Videos

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy

Published on: June 27, 2013

Infant Auditory Processing and Event-related Brain Oscillations

Infant Auditory Processing and Event-related Brain Oscillations

Published on: July 1, 2015

Related Experiment Videos

Last Updated: May 30, 2025

How to Find Effects of Stimulus Processing on Event Related Brain Potentials of Close Others when Hyperscanning Partners

How to Find Effects of Stimulus Processing on Event Related Brain Potentials of Close Others when Hyperscanning Partners

Published on: May 31, 2018

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy

Published on: June 27, 2013

Infant Auditory Processing and Event-related Brain Oscillations

Infant Auditory Processing and Event-related Brain Oscillations

Published on: July 1, 2015

Area of Science:

Neuroscience
Machine Learning
Signal Processing

Background:

Traditional analysis of electroencephalographic (EEG) data for event-related potentials (ERPs) relies on signal averaging, which can obscure important neural information.
Deep learning, particularly transformer networks with attention mechanisms, presents a novel approach to analyze complex EEG data.

Purpose of the Study:

To evaluate the efficacy of a transformer-based deep learning model in analyzing ERPs derived from EEG data.
To compare the insights gained from transformer attention maps against traditional averaging methods for ERP analysis.
To investigate neural responses related to loudness perception using advanced deep learning techniques.

Main Methods:

A convolutional transformer model was trained on EEG data from 29 participants during a loudness perception experiment.
Participants rated acoustic stimuli (65-95 dB) as 'too loud' or 'not too loud' while their EEG was recorded.
Attention maps were generated from the trained transformer to identify relevant time windows in the EEG data.

Main Results:

The transformer model achieved high classification accuracy (>86%) and an Area Under the Curve (AUC) of up to 0.95 for distinguishing loudness categories.
Attention maps highlighted specific time windows (around 150-200 ms) crucial for classification, which were not evident in traditional averaging analyses.
These findings suggest that attention maps can reveal subtle neural patterns missed by conventional methods.

Conclusions:

Transformer-based deep learning, utilizing attention maps, provides a powerful and nuanced method for analyzing ERPs from EEG data.
This approach offers superior insights into neural processing compared to traditional averaging techniques, particularly in identifying key temporal dynamics.
Attention maps demonstrate significant potential as a tool for deeper and more comprehensive ERP analysis in neuroscience research.