Community Research and Development Information Service - CORDIS

Abstract

This paper presents first results of an adaptive brain interface suitable for deployment outside controlled laboratory settings. It robustly recognizes three purely mental states from on-line spontaneous EEG signals and has them associated to simple commands. Three commands allow to interact intelligently with a computer based system through task decomposition. Our approach seeks to develop individual interfaces since not two people are the same physiologically or psychologically. Thus the interface adapts to its owner as its neural classifier learns user-specific filters.

Additional information

Authors: MILLAN J del R, Institute for Systems, Informatics and Safety, Software Technologies and Automation Unit (IT);MOURINO J, Institute for Systems, Informatics and Safety, Software Technologies and Automation Unit (IT);MARCIANI M G, Ospedale di Riabilitazione Saint-Lucia, Roma (IT);BABILONI F, Ospedale di Riabilitazione Saint-Lucia, Roma (IT);TOPANI F, Fase Sistemi Srl, Roma (IT);CANALE I, Fase Sistemi Srl, Roma (IT);HEIKKONEN J, Helsinki University of Technology (IS);KASKI K, Helsinki University of Technology (IS)
Bibliographic Reference: Paper presented: 20th Annual International Conference of IEEE Engineering in Medicine and Biology Society, The Chinese University of HongKong, HongKong (CN), October 29th-November 1st, 1998
Availability: Available from DG XIII D-2 as Paper EN 41841 ORA
Record Number: 199910196 / Last updated on: 1999-03-12
Category: PUBLICATION
Original language: en
Available languages: en