Scalogram-Based Blink Detection in EEG with GoogLeNet, Gaussian Naive Bayes and Majority Voting Using meBaL Dataset
Bibliographic record
Abstract
Low mobility is a significant global issue, affecting over 16% of the world's population, or one in every six persons. It impacts the quality of life and daily routines of those affected. To address this issue, we initiated a project to command a robotic wheelchair using the NeuroSky MindWave headset. The first step was to develop an eye-blink detection algorithm using the meBaL open dataset which is widely used to analyze eye-blink behavior and measure the user's level of attention. However, the main challenge in using only EEG data is distinguishing between blink and non-blink states. Accurate detection of blink behavior in EEG data is crucial for understanding how the brain reacts to different situations. This understanding can provide valuable insights for developing assistive technologies that adapt to the user's cognitive state, improving their quality of life. This paper proposes a hybrid approach for recognizing eye blinks in EEG data. In this study we utilized EEG signal scalograms-a time-frequency representation, combined with Gaussian Naive Bayes for classification with majority voting and GoogLeNet for feature extraction, achieving an impressive accuracy of 95.15%. This research aims to contribute to the growing field of neurophysiological studies and pave the way for future innovations, particularly assistive technologies for people with limited mobility.
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 imitationNot 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.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.003 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.002 |
| Bibliometrics | 0.004 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.002 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".