TY - GEN
T1 - Identification of NARX Hammerstein models based on support vector machines
AU - Al-Dhaifallah, Mujahed
AU - Westwick, David
PY - 2008
Y1 - 2008
N2 - This paper presents a new algorithm for identification of NARX Hammerstein systems using support vector machines (SVMs) to model the static nonlinear elements. The SVM is fitted by minimizing an e-insensitive, L-1 cost function which is robust in the presence of outliers. Another advantage of this algorithm is that the value of the uncertainty level epsilon can be specified by the user which gives more control on the sparseness of the solution. The effect of this choice is demonstrated using simulations.
AB - This paper presents a new algorithm for identification of NARX Hammerstein systems using support vector machines (SVMs) to model the static nonlinear elements. The SVM is fitted by minimizing an e-insensitive, L-1 cost function which is robust in the presence of outliers. Another advantage of this algorithm is that the value of the uncertainty level epsilon can be specified by the user which gives more control on the sparseness of the solution. The effect of this choice is demonstrated using simulations.
KW - Nonlinear system identification
KW - Nonparametric methods
UR - https://www.scopus.com/pages/publications/79961020376
U2 - 10.3182/20080706-5-KR-1001.3523
DO - 10.3182/20080706-5-KR-1001.3523
M3 - Conference contribution
AN - SCOPUS:79961020376
SN - 9783902661005
T3 - IFAC Proceedings Volumes (IFAC-PapersOnline)
BT - Proceedings of the 17th World Congress, International Federation of Automatic Control, IFAC
ER -