Adaptive Modeling and Spectral Estimation of Nonstationary Biomedical Signals Based on Kalman Filtering
Abstract:
Abstract—We describe an algorithm to estimate the instantaneous power spectral density (PSD) of nonstationary signals. The algorithm is based on a dual Kalman filter that adaptively generates an estimate of the autoregressive model parameters at each time instant. The algorithm exhibits superior PSD tracking performance in nonstationary signals than classical nonparametric methodologies, and does not assume local stationarity of the data. Furthermore, it provides better time-frequency resolution, and is robust to model mismatches. We demonstrate its usefulness by a sample application involving PSD estimation of intracranial pressure signals (ICP) from patients with traumatic brain injury (TBI). Index Terms—Intracranial pressure, Kalman filter, linear models, spectral estimation, traumatic brain injury.
Citations
| 797 | A new approach to linear filtering and predictionn problems – Kalman - 1960 |
| 416 | Applied Optimal Estimation – Gelb, editor - 1974 |
| 64 | Maximum Entropy Spectral Analysis – Burg - 1975 |
| 62 | Modern Spectral Estimation – Kay - 1988 |
| 61 | The use of the fast Fourier transform for the estimation of power spectra: A method based on time averaging over short, modified periodograms – Welch - 1967 |
| 26 | The Measurement of Power Spectra – BLACKMAN, TUKEY - 1958 |
| 9 | A two-observation kalman framework for maximum-likelihood modeling of noisy time series – Nelson, Wan - 1998 |
| 7 | Filtering: Theory and Practice Using MATLAB – Grewal, Andrews, et al. - 2001 |
| 7 | Neural dual extended Kalman filtering: applications in speech enhancement and monaural blind signal separation – Wan, Nelson - 1997 |
| 2 | Smoothing periodograms from time series with continuous spectra – Barlett - 1948 |
| 2 | of noise from speech using the dual EKF algorithm – “Removal - 1998 |
