Related Experiment Video
Updated: Jul 8, 2025
07:25
Driving Under the Influence: How Music Listening Affects Driving Behaviors
Published on: March 27, 2019
12.4K
Evaluation of Intoxication Level with EOG Analysis and Machine Learning: A Study on Driving Simulator
Summary
Detecting alcohol intoxication is crucial for road safety. Electrooculography (EOG) combined with machine learning accurately estimates intoxication levels in simulated driving, achieving over 94% accuracy.
Area of Science:
- Neuroscience
- Biomedical Engineering
- Machine Learning
Background:
- Alcohol consumption impairs driving abilities, increasing accident risks.
- Accurate intoxication detection methods are vital for road safety.
- Electrooculography (EOG), measuring eye movements, shows potential for intoxication assessment.
Purpose of the Study:
- To evaluate the effectiveness of EOG analysis and machine learning in estimating alcohol intoxication levels.
- To assess intoxication in a simulated driving environment.
Main Methods:
- EOG signals were recorded using JINS MEME_R smart glasses.
- Simulated intoxication was induced using drunk vision goggles.
- Signal processing, feature engineering, and boosted decision trees were applied for classification.
Main Results:
- A prediction accuracy exceeding 94% was achieved for a four-class intoxication level classification.
- The study demonstrated the feasibility of using EOG and machine learning for intoxication estimation.
Conclusions:
- EOG analysis coupled with machine learning provides a reliable method for accurately estimating intoxication levels.
- This approach holds promise for enhancing road safety by detecting impaired drivers.
