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

Neural correlates of recognition memory obtained after encoding under conventional laboratory, virtual, and real-life conditions reveal modality-specific mnemonic processing.

Acta psychologica·2026
Same author

Working memory load and search efficiency in conventional monitor-based 2D versus 3D virtual settings: analysis of response times and parietal induced alpha activity in a modified Sternberg task.

Experimental brain research·2026
Same author

Beyond Context-Transfer Effects: Attenuated Familiarity During Virtual Reality-Based Retrieval Across Different Encoding Modalities.

The European journal of neuroscience·2026
Same author

Encoding of modality-specific face engrams promotes distinct recruitment of mnemonic processing mechanisms: A mobile-EEG study comparing encoding and retrieval of 2D and 3D avatars under virtual reality conditions.

NeuroImage·2026
Same author

NR2F6 deletion revives CAR-T cell function and induces antigen-agnostic immune memory in solid tumors.

Nature communications·2026
Same author

Inhibition of <i>PKCθ</i> Abrogates CD8<sup>+</sup> T Cell-Mediated Neurotoxicity in Murine Cerebral Malaria.

Biomedicines·2025

Related Experiment Video

Updated: Jul 1, 2025

Author Spotlight: IntelliSleepScorer &#8212; A High-Accuracy, Accessible GUI Software for Automated Sleep Stage Scoring in Mice and its Application in Psychiatric Research
04:54

Author Spotlight: IntelliSleepScorer — A High-Accuracy, Accessible GUI Software for Automated Sleep Stage Scoring in Mice and its Application in Psychiatric Research

Published on: November 8, 2024

511

SHAP value-based ERP analysis (SHERPA): Increasing the sensitivity of EEG signals with explainable AI methods.

Sophia Sylvester1,2, Merle Sagehorn3, Thomas Gruber3

  • 1Institute of Computer Science, Osnabrück University, Osnabrück, Germany.

Behavior Research Methods
|March 7, 2024
PubMed
Summary

We introduce SHERPA, a novel explainable artificial intelligence (XAI) method for analyzing electroencephalography (EEG) data. SHERPA objectively identifies relevant neural signals, improving the precision of event-related potential (ERP) analysis.

Keywords:
Deep learningEEGERP analysisExplainable AIFeature importanceSHAP

More Related Videos

Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy
11:15

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

Published on: June 27, 2013

33.7K
Investigating the Effects of Antipsychotics and Schizotypy on the N400 Using Event-Related Potentials and Semantic Categorization
12:00

Investigating the Effects of Antipsychotics and Schizotypy on the N400 Using Event-Related Potentials and Semantic Categorization

Published on: November 19, 2014

12.9K

Related Experiment Videos

Last Updated: Jul 1, 2025

Author Spotlight: IntelliSleepScorer &#8212; A High-Accuracy, Accessible GUI Software for Automated Sleep Stage Scoring in Mice and its Application in Psychiatric Research
04:54

Author Spotlight: IntelliSleepScorer — A High-Accuracy, Accessible GUI Software for Automated Sleep Stage Scoring in Mice and its Application in Psychiatric Research

Published on: November 8, 2024

511
Applications of EEG Neuroimaging Data: Event-related Potentials, Spectral Power, and Multiscale Entropy
11:15

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

Published on: June 27, 2013

33.7K
Investigating the Effects of Antipsychotics and Schizotypy on the N400 Using Event-Related Potentials and Semantic Categorization
12:00

Investigating the Effects of Antipsychotics and Schizotypy on the N400 Using Event-Related Potentials and Semantic Categorization

Published on: November 19, 2014

12.9K

Area of Science:

  • Neuroscience
  • Cognitive Science
  • Artificial Intelligence

Background:

  • Traditional event-related potential (ERP) analysis requires researchers to pre-select time points and sensors, risking bias and missed discoveries.
  • Existing data-driven methods struggle with the multiple comparison problem, impacting analytical sensitivity and specificity.

Purpose of the Study:

  • To present SHERPA, a novel explainable artificial intelligence (XAI) approach for objective and sensitive electroencephalography (EEG) analysis.
  • To overcome limitations of conventional and data-driven ERP analysis by integrating convolutional neural networks (CNNs) and SHapley Additive exPlanations (SHAP).

Main Methods:

  • Developed SHERPA, combining a CNN for condition classification with SHAP for identifying crucial spatiotemporal features in EEG data.
  • Validated SHERPA using a face perception experiment, comparing its performance against traditional researcher- and data-driven methods.

Main Results:

  • SHERPA successfully identified an expected occipital N170 effect cluster.
  • The method generated an "importance score" to quantify the relevance of ERPs for psychological mechanisms.
  • SHERPA indicated a negative selection process during early and late processing stages.

Conclusions:

  • SHERPA provides an objective, data-driven method for ERP analysis, particularly useful when prior knowledge is limited.
  • The approach enhances sensitivity for distinguishing neural processes with high precision, offering a valuable tool for EEG research.