Detecting Drunk Driving Using Off-the-Shelf Smartwatches
Researchers have developed a system using off-the-shelf smartwatches to detect alcohol-impaired driving. The system analyzes wrist accelerometer data and heart rate variability to identify intoxication levels. In a test-track study with 54 participants, a convolutional neural network achieved an AUROC of 0.88 for detecting any alcohol impairment and 0.86 for detecting levels above the WHO limit. This work represents the first demonstration of drunk-driving detection via consumer smartwatches in a real vehicle setting. AI
IMPACT Wearable sensors could offer a scalable solution for real-time monitoring of driver impairment, potentially reducing alcohol-related traffic incidents.