Linear and nonlinear methods for brain-computer interfaces
- 28 July 2003
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Neural Systems and Rehabilitation Engineering
- Vol. 11 (2), 165-169
- https://doi.org/10.1109/tnsre.2003.814484
Abstract
At the recent Second International Meeting on Brain-Computer Interfaces (BCIs) held in June 2002 in Rensselaerville, NY, a formal debate was held on the pros and cons of linear and nonlinear methods in BCI research. Specific examples applying EEG data sets to linear and nonlinear methods are given and an overview of the various pros and cons of each approach is summarized. Overall, it was agreed that simplicity is generally best and, therefore, the use of linear methods is recommended wherever possible. It was also agreed that nonlinear methods in some applications can provide better results, particularly with complex and/or other very large data sets.Keywords
This publication has 20 references indexed in Scilit:
- A general framework for brain-computer interface designIEEE Transactions on Neural Systems and Rehabilitation Engineering, 2003
- An introduction to kernel-based learning algorithmsIEEE Transactions on Neural Networks, 2001
- A brain-controlled switch for asynchronous control applicationsIEEE Transactions on Biomedical Engineering, 2000
- Fisher discriminant analysis with kernelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,1999
- Neural Networks: Tricks of the TradeLecture Notes in Computer Science, 1998
- Autoassociative neural networksComputers & Chemical Engineering, 1992
- Nonlinear principal component analysis using autoassociative neural networksAIChE Journal, 1991
- Asymptotic Analysis of Penalized Likelihood and Related EstimatorsThe Annals of Statistics, 1990
- Robust StatisticsWiley Series in Probability and Statistics, 1981
- Some results on Tchebycheffian spline functionsJournal of Mathematical Analysis and Applications, 1971