Community Research and Development Information Service - CORDIS


This study is part of a project in the field of automatic classification of "stages quoting" of human sleep using methods of connectionist pattern recognition to obtain a real-time exploitation of sleep signals. In order to reduce the computation time required by the artificial neural network techniques, the neuronal algorithm had to be parallelised, taking into account hardware and software constraints. This was done on a pipeline of N-transputers T800.

Additional information

Authors: PINTI A, Université de Mulhouse, Faculté des Sciences et Techniques, TROP, Mulhouse (FR);GROSSETIE J, JRC Ispra (IT)
Bibliographic Reference: Paper presented: 2nd International Conference on Software for Multiprocessors and Supercomputers, Moscow (RU), September 21-23, 1994
Availability: Available from (1) as Paper EN 38405 ORA
Record Number: 199410910 / Last updated on: 1994-11-28
Original language: en
Available languages: en