Driver Fatigue Eeg Fuzzy Entropy Feature Analysis Based on Sliding Window
DOI: 10.2991/meici-17.2017.100
archive: archived pipeline: cataloged verified
Get this paper ↗ (DOI — opens at the source; we link to it, we don't host it)
Summary
This study addresses the limitations of existing driver fatigue detection methods, which typically rely on piecewise independent samples to distinguish between normal and extreme fatigue states. Such binary approaches fail to capture the gradual, continuous nature of fatigue onset, potentially leading to inaccurate assessments. To overcome this, the authors propose a method using fuzzy entropy feature analysis based on a sliding window technique to dynamically describe the progressive process of driver fatigue through Electroencephalogram (EEG) signals. The experimental data were collected from 12 university students (8 male, 4 female, average age 21.5) who underwent a 40-minute driving session without breaks. Prior to the experiment, subjects were required to abstain from caffeine and ensure eight hours of sleep. EEG signals were recorded using a 32-electrode Neuroscan device following the international 10–20 system, digitized at 1000 Hz. Data preprocessing involved filtering with a 50 Hz notch filter and a 0.15–45 Hz band-pass filter to remove noise. Subjective fatigue levels were verified using Li’s subjective fatigue scale and Borg’s CR-10 scale. The core methodology involves calculating fuzzy entropy using a sliding window approach. The window size was set to 1000 sampling points, with a step size of 100 sampling points (1/10 of the cycle). The fuzzy entropy algorithm utilized phase-space reconstruction with parameters m=2, n=4, and similarity tolerance s=0.2 * SD (standard deviation). This continuous analysis allows for the dynamic measurement of EEG signal complexity over time, rather than relying on static, segmented samples. The results indicate that fuzzy entropy features exhibit a general upward trend as driving time increases, correlating with the gradual onset of driver fatigue. Although the EEG signals are non-stationary and show some jitter, the sliding window analysis successfully captures the overall progression of fatigue. The study concludes that this method effectively describes the continuous process of fatigue development, offering a more nuanced and practical approach for real-time driver monitoring compared to traditional binary classification methods. This contributes to the field by providing a robust feature extraction technique for non-stationary biological signals in safety-critical applications.
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 |
| 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 | success | — | — | — | 1 | 2026-08-10 |
Summary generated by qwen3.6-27b-nvidia on 2026-08-10; verification: verified.
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
- Methodological Resource: tool software