Abstract : The design of adaptive nonlinear filters has sparked a great interest in the machine learning community. The present paper aims to present some recent developments in nonlinear adaptive filtering. We present an in-depth analysis of the performance and complexity of a class of kernel filters based on the recursive least-squares algorithm. A key feature that underlies kernel algorithms is that they map the data in a high-dimensional feature space where linear filtering is performed. The arithmetic operations are carried out in the initial space via evaluation of inner products between pairs of input patterns called kernels. We evaluated the SNR improvement and the convergence speed of kernel-based recursive least-squares filters on two types of applications: time series prediction and cardiac artifacts extraction from magnetoencephalographic data.
https://hal-utt.archives-ouvertes.fr/hal-02358677
Contributor : Jean-Baptiste Vu Van <>
Submitted on : Tuesday, November 12, 2019 - 9:41:36 AM Last modification on : Wednesday, November 13, 2019 - 1:42:12 AM
Ibtissam Constantin, Régis Lengellé. Performance analysis of kernel adaptive filters based on RLS algorithm. 2013 25th International Conference on Microelectronics (ICM), Dec 2013, Beirut, Lebanon. pp.1-4, ⟨10.1109/ICM.2013.6734965⟩. ⟨hal-02358677⟩