Real time drunkenness analysis in a realistic car simulation

Abstract : This paper describes a blood alcohol content estimation method for car driver, based on a comportment analysis performed within a realistic simulation. An artificial neural network learns how to estimate subject's blood alcohol content. Low-level recording of user actions on the steering wheel and pedals are used to feed a multilayer perceptron, and a breathalyzer is used to build the learning examples set (desired output). Results are compared with a successful previous work based on a simple video game and demonstrate the ''complexity scalability'' of the approach.
Type de document :
Communication dans un congrès
ESANN. European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Apr 2012, Bruges, Belgium. pp.85-90, 2012
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-00850136
Contributeur : Audrey Robinel <>
Soumis le : samedi 3 août 2013 - 22:17:39
Dernière modification le : samedi 3 août 2013 - 22:17:39

Identifiants

  • HAL Id : hal-00850136, version 1

Collections

Citation

Audrey Robinel, Didier Puzenat. Real time drunkenness analysis in a realistic car simulation. ESANN. European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning, Apr 2012, Bruges, Belgium. pp.85-90, 2012. <hal-00850136>

Partager

Métriques

Consultations de la notice

79