Action Unit Analysis for Monitoring Drivers’ Emotional States
Bibliographic record
Abstract
With the emergence of intelligent automotive systems, ensuring road safety has become paramount, necessitating the incorporation of sensors such as in-cabin cameras to comprehend drivers’ emotions. While emotion recognition through facial expression has demonstrated remarkable success in controlled laboratory settings, it often struggles to capture the complexities of real-world driving scenarios due to the lack of representative datasets. Facial action coding system (FACS) breaks down facial expressions into a combination of action units (AUs) and offers flexibility for more diverse facial expression categorization. In this study, we present an innovative framework designed to offer a solution to adapt machine learning (ML) models, including random forest (RF), gradient boosting (GB), and long short-term memory (LSTM) as a deep-learning model, originally trained on facial expression recognition (FER) datasets, to real-time monitoring of drivers’ emotional states. Notably, the LSTM model, trained on the CK+ dataset and tested on KMU-FED dataset, achieved the highest accuracy of 52.45%, while the best performance of the RF model reached 50.12% accuracy on the same datasets. The goal of this study is to utilize AUs as descriptors in our framework, aiming to rectify inconsistencies across different datasets. This approach ensures enhanced precision in recognizing drivers’ emotions within the vehicle cabin. Additionally, acknowledging the deployment limitations inherent in on-vehicle systems, our framework is designed to develop compact models, thereby reducing the computational load.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 0.000 |
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 teacher head, 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".