Action unit based micro-expression recognition framework for driver emotional state detection
Bibliographic record
Abstract
Understanding a driver's emotional state is critical for ensuring road safety and public well-being. Emotions such as anger, fear, disgust, sadness, or happiness can significantly influence driving behavior and decision-making. Facial micro-expressions reveal genuine feelings that people attempt to mask or conceal, offering valuable cues for detecting these emotional states, as they tend to be universally expressed across cultures. This study presents a micro-expression recognition framework designed to identify emotional variations in drivers by analyzing facial Action Units (AUs) based on the Facial Action Coding System (FACS). FACS decomposes expressions into AU combinations, enabling more accurate and flexible interpretation of emotions. The proposed method combines a Residual Network (ResNet18) for spatial feature extraction with a Bidirectional Long Short-Term Memory (Bi-LSTM) network for temporal pattern learning. In addition, agglomerative clustering of AU combinations was applied to enhance emotion classification. The model was trained and evaluated on two benchmark datasets: SAMM and KMU-FED, achieving recognition accuracies of 96.38% and 95.96%, respectively. Furthermore, case analysis was carried out to detect driver emotional state using the proposed framework, obtaining an accuracy of 91.00%. The experiment indicated that anger, disgust, sadness, and fear are the predominant emotions expressed by drivers while driving. The goal of this study lies in harnessing action units for micro-expression recognition to enhance precision in recognizing the driver's emotional state.
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".