Title :
A fuzzy diagnosis process for the detection of evolution of a car driver´s behavior
Author :
Peltier, Marie-Agnès ; Lajon, Marc
Author_Institution :
ECP/EPAP, Chatenay Malabry, France
Abstract :
This paper describes a monitoring and diagnosis process for the detection of evolution of a car driver´s behavior. This is an adaptive fuzzy pattern recognition algorithm that achieves progressive and online learning of the driver´s characteristics. A neural net based architecture associated with a real-time algorithm for the detection of abrupt changes provides a diagnosis of evolution that may also be predictive. Promising results on real data are reported.
Keywords :
behavioural sciences computing; computerised monitoring; fuzzy set theory; learning (artificial intelligence); neural nets; pattern recognition; traffic engineering computing; adaptive fuzzy pattern recognition algorithm; car driver´s behavior evolution detection; fuzzy diagnosis; neural net; online learning; progressive learning; Biomedical monitoring; Electroencephalography; Electrooculography; Fatigue; Neural networks; Pattern recognition; Rain; Road accidents; Vehicle driving; Wheels;
Conference_Titel :
Intelligent Vehicles '94 Symposium, Proceedings of the
Print_ISBN :
0-7803-2135-9
DOI :
10.1109/IVS.1994.639463
