Abstract
This paper describes an initial attempt to reduce the complexity of Volterra series and radial basis function nonlinear predictors. The algorithm used exploits signal subspace concepts to reduce the number of nonlinear terms while attempting to maintain the same MSE performance.
| Original language | English |
|---|---|
| Title of host publication | Signal Processing VI Theories and Applications |
| Subtitle of host publication | Proceedings of EUSIPCO-92, Sixth European Signal Processing Conference, Brussels, Belgium, August 24-27, 1992 |
| Editors | J. Vandewalle, R. Boite, M. Moonen, A. Oosterlinck |
| Place of Publication | Amsterdam |
| Publisher | Elsevier Science Publishers B.V. |
| Pages | 791-794 |
| Number of pages | 4 |
| Volume | II |
| ISBN (Print) | 0444895876 |
| Publication status | Published - 1992 |
| Externally published | Yes |
| Event | 6th European Signal Processing Conference - Brussels, Belgium Duration: 24 Aug 1992 → 27 Aug 1992 |
Conference
| Conference | 6th European Signal Processing Conference |
|---|---|
| Abbreviated title | EUSIPCO 92 |
| Country/Territory | Belgium |
| City | Brussels |
| Period | 24/08/92 → 27/08/92 |