Phase Fluctuation Analysis in Functional Brain Networks of Scaling EEG for Driver Fatigue Detection
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 challenge of characterizing complex electroencephalogram (EEG) patterns to distinguish between driver fatigue and alert states. Driver fatigue significantly impairs cognitive capacity and situational alertness, posing a major risk to driving safety. While EEG is a reliable indicator of human cognitive states, its non-linear and complex dynamics make pattern characterization difficult. The authors propose an instantaneous phase-based method to extract discriminatory information from EEG measurements that existing non-phase-based methods may overlook. The primary objective is to demonstrate that phase fluctuations, analyzed through functional brain networks, can effectively distinguish between fatigued and rested states in professional drivers. The experimental data were collected from seven professional male taxi drivers (ages 30–40) who had driven for more than five hours. EEG signals were recorded using an Emotiv EEG recorder with 12 channels (AF3, F7, F3, FC5, P7, O1, O2, P8, FC6, F4, F8, AF4) at a sampling rate of 128 Hz. The protocol involved recording three minutes of EEG data immediately after driving, labeled as the "fatigue" state, followed by a ten-minute rest period. A subsequent three-minute recording was taken after the rest, labeled as the "post-relax" state. To handle the complexity of the raw EEG signals, the authors employed Empirical Mode Decomposition (EMD) to decompose the signals into Intrinsic Mode Functions (IMFs). The third IMF, corresponding to the alpha band (8–13 Hz), was selected for analysis as it contained proper phase rotations free from low-frequency noise. Instantaneous phases were calculated using the Hilbert transform. Functional brain networks were then constructed by computing the magnitude squared coherence between channel pairs to form adjacency matrices. The results indicate distinct structural differences in the functional brain networks between the two states. In the fatigue state, the brain networks exhibited lower connectivity between node pairs. Conversely, after rest, the networks showed higher connectivity, forming a structure of highly connected nodes. This difference was quantified using node degree distributions, which represent the number of connections per node. For the fatigued state, the node degree with the highest occurrence rate was seven. In the post-relax state, this peak shifted to eleven. This trend, where the probability distribution of node degrees moves from smaller to larger values upon recovery, was consistent across most participants. The scaling analysis confirmed that the relationship between network structure and function allows for the extrapolation of scaling exponents from phase fluctuations, effectively distinguishing the two mental states. The significance of this work lies in demonstrating the effectiveness of combining EMD with functional brain network analysis for driver fatigue detection. By focusing on phase fluctuations and network topology, the method captures robust scaling behaviors hidden in EEG data. The distinct degree distributions provide a clear metric for differentiating between fatigue and alertness, suggesting that this approach offers a reliable tool for monitoring driver states and enhancing transportation safety.
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 | pdftotext | — | — | 4 | 2026-08-10 |
| clean | success | clean | — | — | 2 | 2026-08-10 |
| chunk | success | chunk | — | — | 2 | 2026-08-10 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 2 | 2026-08-10 |
| promote | success | — | — | — | 1 | 2026-08-09 |
| summarize | success | llm | qwen3.6-27b-nvidia | summ-v5 | 2 | 2026-08-10 |
| tag | success | vector_similarity | — | — | 17 | 2026-08-11 |
| verify | success | — | — | — | 2 | 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