Researchers: Fabio Babiloni, Jukka Heikkonen, Kimmo Kaski, Tommi Nykopp and Markus Varsta of Laboratory of Computational Engineering, Helsinki University of Technology, Finland, José Millan and Josep Mourino of the Joint Research Centre of the European Commission Ispra, Italy, Prof. Maria Marciani of the IRCCS Ospedale di Riabilitazione S. Lucia, Italy, and Fabio Topani of Fase Sistemi, Rome, Italy.
The objective of the ABI project is to use EEG signals as an alternative means of interaction with computers. As such, the goal is to develop a brain-actuated mouse. We seek to recognise five EEG patterns by means of artificial neural networks and to associate them with simple commands. Thus, to select an item from a computer screen it suffices to have 5 patterns; four of the patterns will move the pointer "up", "down", "left", and "right", while the fifth pattern will "click" and select the item underneath the pointer.
We seek to build individual brain interfaces rather than universal ones valid for everybody. Our approach is based on a mutual learning process whereby the individual user and the ABI are coupled and adapt to each other: a neural network learns user-specific EEG patterns describing the mental tasks while subjects learn to think in such a way that they are better understood by their personal interface. In other words, every single user chooses his/her most natural mental tasks to concentrate on (e.g., relaxation, visualisation, music composition, arithmetic, preparation of movements) and also the preferred strategies to undertake those tasks.
Another concern of this project is the robust recognition of EEG patterns outside laboratory settings. This presumes the existence of an appropriate EEG equipment that should be compact, easy-to-use, and suitable for deployment in natural environments. No such a commercial EEG system exists, and we will manufacture an appropriate helmet with integrated and amplified electrodes.
The funding for the project is provided by EU for the years 1998-2001.
|Figure 8: A player interfacing the Pacman like game with the ABI prototype.||Figure 9: Partial snapshot of the ABI controlled Pacman like game.|