MétaCan
Menu
Back to cohort

Deep Convolutional Architecture with discriminative feature visualization for analysis of EEG data

2018· article· en· W2966612705 on OpenAlexaff
Arna Ghosh, Fabien Dal Maso, Georgios D. Mitsis, Marie‐Hélène Boudrias

Bibliographic record

VenueFaculty of 1000 Research Ltd · 2018
Typearticle
Languageen
FieldNeuroscience
TopicEEG and Brain-Computer Interfaces
Canadian institutionsMcGill University
Fundersnot available
KeywordsOpen peer reviewDiscriminative modelPlant biologyConvolutional neural networkFeature (linguistics)Computer scienceArchitectureElectroencephalographyNeuroscienceVisualizationArtificial intelligencePattern recognition (psychology)Computational biologyPsychologyBiologyGeography

Abstract

fetched live from OpenAlex

Analysis of Electroencephalography (EEG) data to improve understanding of underlying neural activity is typically hypothesis-driven and requires the investigator to quantify certain features of the EEG time-series. However, this could lead to sub-optimal feature selection. Data-driven approaches like deep learning (DL) allow discovery of the optimal feature set from available data. Convolutional Neural Networks (CNNs) have been recently used for classification tasks in neuroscience[1]. To visualize discriminative features that guide the network's decision, we use a method called cue-combination for Class Activation Map (ccCAM) which is inspired by existing methods in literature[2] and adapted for neuroscience applications. Specifically, a deep CNN architecture, combined with ccCAM is applied on EEG data collected from human subjects to study the effect of exercise on motor learning. Our results reveal discriminative features within specific frequency band (19-31 Hz) that is a subset of the beta-band, which has been found to be significantly modulated by exercise in previous studies[3]. They also reveal that activity in this frequency band propagates across different regions of the cortex while performing a fixed force hand-grip task. Collectively, our results demonstrate the potential of DL frameworks for identifying a more informative feature space in neuroimaging data in a completely data-driven manner, which can in turn yield a better understanding of brain function.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.001
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.009
Threshold uncertainty score0.018

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0000.001
Meta-epidemiology (narrow)0.0010.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.001
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0030.001

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.113
GPT teacher head0.430
Teacher spread0.317 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2018
Admission routes1
Has abstractno

Explore more

Same venueFaculty of 1000 Research LtdSame topicEEG and Brain-Computer InterfacesFrench-language works237,207