Fatigue driving monitoring system based on the EEG
DOI: 10.5954/icarob.2020.os9-9
archive: archived pipeline: cataloged verified
Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)
Summary
This paper presents the development of a fatigue driving monitoring system based on electroencephalogram (EEG) signal analysis. The research is motivated by the need for effective driver fatigue detection to prevent accidents, contrasting existing methods such as radar-based drowsiness detection, sweat analysis, and steering pressure monitoring. The proposed system aims to acquire EEG signals, extract characteristic rhythms, estimate fatigue levels, and provide voice reminders to drivers. The methodology involves acquiring EEG data using a 16-channel device following the international 10-20 electrode placement standard, with electrodes positioned at Fz, F3, F4, F7, F8, T3, T4, C3, C4, T5, T6, P3, P4, O1, O2, and Pz. Data was collected at a sampling frequency of 250 Hz over a duration of 180 minutes. Preprocessing was conducted using the EEGLAB toolbox in MATLAB. Independent Component Analysis (ICA) via the extended Infomax algorithm was applied to remove artifacts, specifically identifying and eliminating eye movement and electromyographic interference. Feature extraction utilized wavelet packet decomposition with the "db1" wavelet, decomposing signals into seven layers to reconstruct four characteristic rhythm bands: delta (0–4 Hz), theta (4–8 Hz), alpha (8–13 Hz), and beta (14–30 Hz). The relative energy values of these rhythms were calculated as measurement indices. The study analyzed the relative energy changes of these rhythms over six 30-minute segments. Results indicated that during the initial periods (0–60 minutes), the driver’s brain remained active with minimal fatigue symptoms. From 60 to 120 minutes, the relative energy of delta and theta waves increased significantly, while alpha and beta energies decreased, indicating the onset and progression of fatigue and cerebral inhibition. In the fifth segment (120–150 minutes), a temporary relief in fatigue was observed, marked by weakened delta and theta energies and enhanced alpha and beta energies, attributed to a brief reduction in neural inhibition. However, in the final segment (150–180 minutes), delta and theta energies rose again to their highest levels, while alpha and beta energies dropped to their lowest, signifying the most severe fatigue state. The system uses the energy value of the delta wave in channels F3, F4, and C3 to classify fatigue, triggering a voice alert via the computer’s sound card when the threshold reaches 0.4. The significance of this work lies in demonstrating a viable method for real-time fatigue monitoring using non-invasive EEG technology. By correlating specific EEG rhythm energy shifts with fatigue states, the system provides a physiological basis for timely warnings, potentially enhancing road safety. The study confirms that delta and theta wave dominance correlates with increased fatigue, while alpha and beta waves correlate with alertness, offering a clear metric for automated driver assistance systems.
Provenance
The full processing record for this entry. Every stage of this paper's journey through the pipeline is logged — what ran, with which tool and model, how many attempts it took, and when it last completed.
| Stage | Outcome | Tool | Model | Prompt | Attempts | Completed |
|---|---|---|---|---|---|---|
| discover | success | Crossref | — | — | 1 | 2026-08-09 |
| archive | success | canonical_url | — | — | 1 | 2026-08-09 |
| extract | success | cached | — | — | 3 | 2026-08-10 |
| clean | success | clean | — | — | 1 | 2026-08-09 |
| chunk | success | chunk | — | — | 1 | 2026-08-09 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-08-09 |
| enrich | failed | — | — | — | 2 | 2026-08-24 |
| promote | success | — | — | — | 1 | 2026-08-09 |
| summarize | success | llm | qwen3.6-27b-nvidia | summ-v5 | 2 | 2026-08-10 |
| tag | success | vector_similarity | — | — | 10 | 2026-08-11 |
| verify | partial | — | — | — | 1 | 2026-08-10 |
Summary generated by qwen3.6-27b-nvidia on 2026-08-10; verification: verified_with_issues.
Topics
Ranked by relevance to this paper. Hover a topic for its definition.
Information type
What kind of knowledge this paper contributes, grouped by family — independent of topic (what it is about) and method (how it was studied).
- Empirical Findings: physiological data