Instrumentation and Features Selection Using a Realistic Car Simulator in Order to Perform Efficient Single-User Drunkenness Analysis

Audrey Robinel 1, * Didier Puzenat 2
* Corresponding author
1 LAMIA - Laboratoire de Mathématiques Informatique et Applications
2 GRIMAAG - Groupe de Recherche en Informatique et Mathématiques Appliquées Antilles-Guyane
Abstract : We instrumented a car simulator by gathering low level data and fed it to an artificial neural network in order to perform blood alcohol content (BAC) estimations. The results depend on the quality of the data extraction and processing, and also on the selected inputs. We explain our data extraction and processing methodology, and how we used it to generate reliable and comparable features. At last, we describe the performances of individual features and how they combine. In the end, the prototype was able to accurately estimate the BAC value of a subject after being trained with driving samples of this subject with various BAC values.
Keywords : Blood Alcohol Content Driving Interface Artificial Neural Networks Intelligent systems Machine learning Instrumentation
Document type :
Conference papers
Liste complète des métadonnées
https://hal.archives-ouvertes.fr/hal-00850137
Contributor : Audrey Robinel <>
Submitted on : Saturday, August 3, 2013 - 10:33:22 PM
Last modification on : Wednesday, July 18, 2018 - 8:11:27 PM

Identifiers

  • HAL Id : hal-00850137, version 1

Collections

UNIV-AG | BNRMI

Citation

Audrey Robinel, Didier Puzenat. Instrumentation and Features Selection Using a Realistic Car Simulator in Order to Perform Efficient Single-User Drunkenness Analysis. ACHI 2013, The Sixth International Conference on Advances in Computer-Human Interactions, Feb 2013, Nice, France. pp.407-421. ⟨hal-00850137⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

95

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD