Optimal estimation theory for dynamic systems with set membership uncertainty: an overview
Automatica (Journal of IFAC)
Advanced lectures on machine learning
The role of vector autoregressive modeling in predictor-based subspace identification
Automatica (Journal of IFAC)
Nonparametric identification of population models via Gaussian processes
Automatica (Journal of IFAC)
Bayes and empirical Bayes semi-blind deconvolution using eigenfunctions of a prior covariance
Automatica (Journal of IFAC)
Brief paper: Fast algorithms for nonparametric population modeling of large data sets
Automatica (Journal of IFAC)
A new kernel-based approach for linear system identification
Automatica (Journal of IFAC)
Input estimation in nonlinear dynamical systems using differential algebra techniques
Automatica (Journal of IFAC)
Order estimation for subspace methods
Automatica (Journal of IFAC)
Non-stationary stochastic embedding for transfer function estimation
Automatica (Journal of IFAC)
Regularization networks: fast weight calculation via Kalman filtering
IEEE Transactions on Neural Networks
On the estimation of transfer functions, regularizations and Gaussian processes-Revisited
Automatica (Journal of IFAC)
A Bayesian approach to sparse dynamic network identification
Automatica (Journal of IFAC)
Consistent identification of Wiener systems: A machine learning viewpoint
Automatica (Journal of IFAC)
Estimation of building occupancy levels through environmental signals deconvolution
Proceedings of the 5th ACM Workshop on Embedded Systems For Energy-Efficient Buildings
Hi-index | 22.15 |
A novel Bayesian paradigm for the identification of output error models has recently been proposed in which, in place of postulating finite-dimensional models of the system transfer function, the system impulse response is searched for within an infinite-dimensional space. In this paper, such a nonparametric approach is applied to the design of optimal predictors and discrete-time models based on prediction error minimization by interpreting the predictor impulse responses as realizations of Gaussian processes. The proposed scheme describes the predictor impulse responses as the convolution of an infinite-dimensional response with a low-dimensional parametric response that captures possible high-frequency dynamics. Overparameterization is avoided because the model involves only a few hyperparameters that are tuned via marginal likelihood maximization. Numerical experiments, with data generated by ARMAX and infinite-dimensional models, show the definite advantages of the new approach over standard parametric prediction error techniques and subspace methods both in terms of predictive capability on new data and accuracy in reconstruction of system impulse responses.