Driver’s State Alert Function by Using Facial Expression Classification in Cooperation with Artificial Intelligence

Driver’s non-normal psychosomatic states such as drowsiness and anger may cause severe traffic accidents. Driver's psychosomatic state adaptive driving support safety function may play important role to prevent being involved in a traffic accident. Therefore, detection technology of both drowsi...

Full description

Saved in:
Bibliographic Details
Published inInternational Journal of Advanced Studies in Computers, Science and Engineering Vol. 6; no. 5; p. 13
Main Author Miyaji, Masahiro
Format Journal Article
LanguageEnglish
Published Gothenburg International Journal of Advanced Studies in Computers, Science and Engineering 01.01.2017
Subjects
Anger
Artificial intelligence
Automation
Autonomous vehicles
Classification
Cooperation
Driver behavior
Expert systems
Fatalities
Internet
Neural networks
Product development
Statistical analysis
Studies
Traffic accidents
Traffic accidents & safety
Traffic congestion
Traffic flow
Traffic safety
Traffic surveys
Online AccessGet full text

Cover

More Information
Summary:Driver’s non-normal psychosomatic states such as drowsiness and anger may cause severe traffic accidents. Driver's psychosomatic state adaptive driving support safety function may play important role to prevent being involved in a traffic accident. Therefore, detection technology of both drowsiness and anger is highly expected to enhance performance of the safety function. When driver's psychosomatic state adaptive driving support safety function detects driver's non-normal states in cooperation with artificial intelligence, the safety system delivers notice or alert of imminent risk of a traffic accident to a driver to prevent being involved in traffic accident in advance. This research firstly identified root cause of traffic incidents by means of refining data done by Internet survey. From statistical analysis of traffic incidents experiences, major psychosomatic state just before traffic incidents were haste, distraction, drowsiness and anger. This research focused both drowsiness and anger of a driver while driving. Facial expression was used as alternative characteristics of both driver's drowsiness and anger states. By means of using Kohonen neural network as classification algorithm, this research created a method to classify both drowsiness and anger states of a driver in high accuracy. Finally, this research proposes driver's psychosomatic state alert function by using facial expression classification in cooperation with artificial intelligence to prevent potential risks of traffic accidents.
ISSN:2278-7917