In-Vehicle Stress Monitoring Based on EEG Signal
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 addresses the challenge of monitoring driver stress in real-time to improve road safety, focusing on the limitations of existing systems that struggle with individual variations and the complex, dynamic in-vehicle environment. The authors propose an individual-focused computational system that uses electroencephalography (EEG) signals to automatically classify drivers as "stressed" or "relaxed." The study aims to overcome the difficulty of analyzing noisy EEG data in moving vehicles and to provide short-term monitoring capabilities, specifically at one-minute intervals, which is critical for immediate safety interventions. The methodology involves data collection from eight healthy participants (seven male, one female) in both laboratory settings and real-road driving scenarios. In the lab, a 15-minute psychophysiological stress profiling protocol established individual baselines. During real-road driving, participants navigated a 3.5 km route with heavy traffic. EEG signals were recorded using a wireless system with electrodes placed at Fp1, Fp2, Cz, A1, and A2. To handle artifacts from movement and muscle activity, the system applied Independent Component Analysis (ICA) followed by double-density wavelet denoising. Feature extraction utilized three methods: Discrete Wavelet Transform (DWT) for alpha, beta, theta, and delta band power; Modified Covariance for statistical features; and the Largest Lyapunov Exponent (LLE) to quantify chaotic dynamics in the EEG signals. These features were fed into a hybrid classification system using Case-Based Reasoning (CBR) and Fuzzy-CBR. The Fuzzy-CBR approach specifically used triangular membership functions to fuzzify LLE values, allowing for unsupervised classification of short-time intervals without requiring real-time expert labeling. The results demonstrate that the proposed system can effectively handle individual variations and provide decisions every minute. When comparing the automated classification against the assessments of a human expert with over 20 years of experience, the system achieved a classification accuracy of 79% for short-time intervals. The study also compared EEG performance against other physiological signals, including Electrocardiography (ECG), finger temperature, skin conductance, and respiration, highlighting EEG's reliability for detecting mental states like stress and fatigue. The CBR system using extracted features showed varying accuracy depending on the feature set and retrieval method, with the Fuzzy-CBR approach proving effective for minute-by-minute analysis. The significance of this work lies in its demonstration that EEG-based monitoring can be robust enough for real-world driving conditions, addressing the gap between lab-based studies and practical application. By enabling individual-focused, short-term stress detection, the system offers a viable path for intelligent driver assistance systems. The integration of chaotic analysis (LLE) with fuzzy logic provides a novel approach to interpreting complex EEG dynamics, potentially reducing false positives caused by environmental noise. This research supports the development of more accurate, multi-sensor fusion systems for enhancing driver safety and preventing accidents caused by mental fatigue and stress.
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 | 2026-06-25 |
| archive | success | canonical_url | — | — | 1 | 2026-06-26 |
| extract | success | cached | — | — | 2 | 2026-06-26 |
| clean | success | clean | — | — | 1 | 2026-06-26 |
| chunk | success | chunk | — | — | 1 | 2026-06-26 |
| embed | success | embed | Qwen/Qwen3-Embedding-8B | — | 1 | 2026-06-26 |
| enrich | success | openalex | — | — | 1 | 2026-06-26 |
| promote | success | — | — | — | 1 | 2026-06-25 |
| summarize | success | llm | qwen3.6-27b-prismaquant | summ-v5 | 1 | 2026-06-26 |
| tag | success | vector_similarity | — | — | 6 | 2026-06-26 |
| verify | partial | — | — | — | 1 | 2026-06-26 |
Summary generated by qwen3.6-27b-prismaquant on 2026-06-26; 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
- Methodological Resource: validation psychometrics, tool software