Driving under the influence of alcohol (DUI) remains a leading cause of accidents globally, with accident risk rising exponentially with blood alcohol concentration (BAC). This study aims to distinguish between sober and intoxicated drivers using driving behavior analysis and driver monitoring system (DMS), technologies that align with emerging EU regulations. In a driving simulator, twenty-three participants (average age: 32) completed five drives (one practice and two each while sober and intoxicated) on separate days across city, rural, and highway settings. Each 30-minute drive was analyzed using eye-tracking and driving behavior data. We applied significance testing and classification models to assess the data. Our study goes beyond the state of the art by a) combining data from various sensors and b) not only examining the effects of alcohol on driving behavior but also using these data to classify driver impairment. Fusing gaze and driving behavior data improved classification accuracy, with models achieving over 70% accuracy in city and rural conditions and a Long Short-Term Memory (LSTM) network reaching up to 80% on rural roads. Although the detection rate is, of course, still far too low for a productive system, the results nevertheless provide valuable insights for improving DUI detection technologies and enhancing road safety.

Driving under the influence of alcohol (DUI) remains a major contributor to fatal traffic crashes worldwide. With increasing regulatory pressure, such as requirements by Euro NCAP for in-vehicle impairment detection, there is a growing need for reliable, real-time monitoring solutions. While traditional DUI detection approaches focus on driving behavior or eye movement analysis, this study explores the potential of thermal imaging as a noninvasive alternative for detecting alcohol impairment. We conducted a large-scale experimental study with 120 participants in a high-fidelity driving simulator, capturing thermal facial data under both non-impaired and alcohol-impaired conditions. A novel temperature extraction method was developed based on facial landmarks, incorporating multiple frames to reduce noise and improve temporal stability. Ambient cabin temperature was also recorded to normalize facial temperature readings and control for environmental influences. Several machine learning classifiers, including Logistic Regression, Random Forest, Support Vector Machine (SVM), and Gradient-Boosting Models, were trained using five facial temperature features (cheek, temple, ear, forehead, and nasal tip) and evaluated via five-fold subject-wise cross-validation. Significant temperature changes were observed in specific facial regions (particularly the cheek, ear, temple, and nasal tip) under alcohol influence. Among the evaluated models, Logistic Regression achieved the highest average classification accuracy (62%), while SVM demonstrated the most stable performance across folds. The model showed a slight conservative bias toward predicting the baseline (non-impaired) class, thereby reducing the risk of false positive classifications. Environmental conditions, including cabin temperature, were verified to be stable across both driving sessions, ensuring the validity of the physiological measurements. This study demonstrates the feasibility of using thermal imaging for in-vehicle DUI detection under realistic conditions. Our contributions include the development of a robust facial temperature processing pipeline, the creation of a unique dataset collected under ecologically valid conditions, and a comprehensive comparison of seven state-of-the-art classification models. Thermal imaging represents a promising complementary modality for future driver monitoring systems focused on safety and impairment detection.

Impairment detection is a crucial step towards safer road traffic. To collect data for the development of an alcoholrelated impairment detection, a comprehensive study was conducted in a dynamic driving simulator with 105 participants successfully participating with breath alcohol concentrations of up to $\mathbf{1. 0 \% o}$. Uniquely, the study recorded not only driving behavior but also data from multimodal in-cabin sensors (IR-camera, radar, thermal-camera, etc.) in a realistic driving environment. Further, in addition to periodic measurements of the breath alcohol concentration, impairment tests were conducted to not only obtain intoxication levels but objective impairment indicators. This paper describes the study design and addresses the technical, ethical, and organizational considerations and challenges encountered in planning and conducting such an extensive and complex study, aiming to support the scientific community as a foundation for further research.

This study introduces a novel machine learning framework for detecting alcohol-induced driving impairment based on multimodal behavioral signals collected in a high-fidelity driving simulator. With 120 participants, the largest sample size in this field to date, the experiment captured both vehicle dynamics and eye-tracking data under sober and intoxicated conditions. To preserve temporal dependencies, a MiniRocket time-series classifier was employed, outperforming conventional feature-based models. A systematic signal-wise analysis identified steering behavior and drowsiness as the most informative indicators. Signal combinations further enhanced classification performance, achieving up to 85.2 % accuracy on unseen test data. While scenario-specific models (urban, rural, highway) provided only marginal improvements, a time window analysis revealed that just three minutes of driving data were sufficient for reliable detection. As the first study to integrate gaze and driving behavior in a scalable, signal-based approach, this work demonstrates the practical potential of multimodal time-series classification for real-time, in-vehicle driver monitoring.