Phosphene evaluation in a visual prosthesis with artificial neural networks

Archambeau, Cédric;Lendasse, Amaury;Trullemans, Charles;Veraart, Claude;Verleysen, Michel;et.al.
(2001) EUNITE 2001, European Symposium on Intelligent Techniques, Hybrid Systems and their implementation on Smart Adaptive Systems — Location: Tenerife (Spain) (13.December.2001)

Files

64-Phospheneevaluationinavisualprosthesiswithartificialneuralnetworks.pdf
  • Restricted Access
  • Adobe PDF
  • 678.25 KB
Request a copy

Details

Authors
  • Archambeau, CédricUCLouvain
    Author
  • Lendasse, AmauryUCLouvain
    Author
  • Trullemans, CharlesUCLouvain
    Author
  • Veraart, ClaudeUCLouvain
    Author
  • Delbeke, JeanUCLouvain
    Author
  • Verleysen, MichelUCLouvain
    Author
Show more
Abstract
The electrical stimulation of the optic nerve is investigated, as an approach to the development of a microsystems-based visual prosthesis. Non-linear prediction models, i.e. artificial neural networks, for phosphene localisation are used and show promising results. The prediction error is reduced up to 20% in comparison with linear statistical models and the error standard deviation is restrained such that the prediction accuracy is similar to the measurements accuracy. In addition, it is shown that linear methods do not suit this kind of problems.
Affiliations

Citations

  • APA
  • Chicago
  • FWB

Archambeau, C., Lendasse, A., Trullemans, C., Veraart, C., Delbeke, J., & Verleysen, M. (2001). Phosphene evaluation in a visual prosthesis with artificial neural networks. Proceedings of EUNITE 2001, European Symposium on Intelligent Techniques, Hybrid Systems and their implementation on Smart Adaptive Systems, p. 509-515. https://hdl.handle.net/2078.5/226196