Machine learning models classify the three learning stages from EEG features with over 80% test accuracy, SVM highest at 82.6%¶
Claim · All claims
Evidence · 1 study · associationalr1·q2
Currency · newest study 2025 · checked against its sources 2026-10-26 (automated, 1 of 1 entry) · not reviewed by a person
Subclaims¶
Reading the evidence codes
q is the design tier, i the impact, n the sample, and the kind with its r
the rigour judged within that kind: what each code means.
This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.
q2 i? SVM and neural network models classified the three learning stages with testing accuracies of 82.6% and 81.8% from 84 EEG features. → Hui Xie 2025
Evidence¶
Hui Xie 2025¶
Hui Xie, Chunli Jia, Yanxia Luo, Jiangshan He, Zexiao Dong, Dan Liang, Ziqi Ren, Mingzhe Jiang, Xinbo Gao & Xueli Chen. (2025). EEG analysis of brain dynamics in a simulated multi-task and multi-stage learning environment. npj Science of Learning. https://doi.org/10.1038/s41539-025-00376-5
q2 · i? · associational · r1
Classification of learning stage from 10-s EEG segments (84 relative-PSD features, 14 channels, six bands; 7,544 samples), trained in MATLAB with 10-fold cross-validation. Five models were compared; KNN reached 80.4% test accuracy.
"The two models with better classification results are the support vector machine (SVM) and neural network (NN) models, with testing accuracies of 82.6% and 81.8%."
Discussion¶
Related Claims¶
- EEG average amplitude differs significantly across learning stages within each task, and across tasks at Stages 1 and 3, during a semester-long course — related
- Decision trees achieve competitive accuracy with black-box models (LR, RF, SVM), which performed slightly better but lack interpretability — related
- A support vector machine classifier outperformed decision tree and random forest models in predicting cognitive engagement levels of online discussion posts — related
- Relative PSD shows stage- and task-specific band patterns, including higher high-beta in Stage 3 of labs and quizzes — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
eeg-stage-classification-over-80 |
title |
Machine learning models classify the three learning stages from EEG features with over 80% test accuracy, SVM highest at 82.6% |
description |
Machine learning models classify the three learning stages from EEG features with over 80% test accuracy, SVM highest at 82.6% |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2025 |
source_checked |
2026-10-26 |
generated |
by process:wiki-ingest on 2026-10-26 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — hui-xie-2025 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.