EEG familiarity benchmark dataset and evaluation framework (3960 samples, 23 participants, two validation protocols)¶
Product or Programme · All products and programmes
Evidence · 5 claims (2 for, 3 mixed) · 1 study (1 associational),q2· 0 of 1 report an effect size · 5 claims rest on one study
Description¶
A dataset and benchmarking framework released by Isuru Nanayakkara et al. containing EEG-derived features for familiar-versus-unfamiliar face and mathematical-equation classification, with leakage-aware validation protocols and permutation testing.
Components¶
Claims¶
- Temporal leakage from shuffled neighboring epochs inflates EEG familiarity classification, with peak weighted F1 dropping from 0.9853 (CNN, stratified) to 0.6038 (CNN, Group K-Fold) [+M]
- Trial-independent EEG familiarity classification remains statistically significantly above chance for the 4-class, equations-only, and faces-only tasks under Bonferroni-corrected permutation tests [+M]
- Trial-level spectral features robustly differentiate stimulus domains (faces vs. equations) but no familiarity-driven spectral shift survives FDR correction [~W]
- Familiarity recognition is represented by a distributed multivariate spatial-spectral pattern rather than localized single-feature shifts, necessitating multivariate machine learning [~W]
- Random Forest and SHAP analyses identify Gamma and Beta band power at temporal and frontal channels (T3, P3, F7, T4, T4, F8, F7) as the most critical features for EEG familiarity classification [~W]
Related Products and Programmes¶
- The Pedagogy Benchmark
- Openly available EEG and behavioral datasets and replicable experimental framework for human-AI interaction studies
Key Sources¶
- Isuru Nanayakkara and Thilina Halloluwa. (2026). Automating Learner Assessment: Benchmarking Machine Learning and Deep Learning Models for EEG-Based Familiarity Prediction. https://arxiv.org/abs/2608.16541
Page metadata
| Field | Value |
|---|---|
type |
product |
id |
eeg-familiarity-benchmark-dataset-and-evaluation-framework-3960-samples-23-participants-tw |
title |
EEG familiarity benchmark dataset and evaluation framework (3960 samples, 23 participants, two validation protocols) |
description |
A dataset and benchmarking framework released by Isuru Nanayakkara et al. |
status |
review |
product_kind |
dataset |
generated |
by process:settle-candidates on 2026-10-10 |
trust |
unverified — no one has confirmed this page's content |
Frontmatter is the page's machine-readable record — see the Schema & Guide.