∗ All three major approaches to time–varying identification: local estimation, the basis functions approach and the method based on Kalman filtering/smoothing.
∗ Analysis and comparison of tracking capabilities of different time–varying identification schemes.
∗ Discussion of all aspects of time–varying identification such as assessment of the estimation memory, estimation bandwidth and numerical stability of different identification algorithms and optimization of adaptive filters.
∗ Presentation of selected practical applications of time–varying process identification.
Essential reading for adaptive signal processing engineers, researchers, lecturers and senior electrical engineering and computer science students in telecommunications and signal processing.
Models of Nonstationary Processes.
Weighted Least Squares.
Least Mean Squares.