This book focuses on Bayesian estimation problems for Information Engineering students, particularly those in Automation Engineering. It covers both off-line and on-line estimation, including real-time filtering and prediction. The text examines stochastic filtering, which estimates signals in dynamic systems with random disturbances. To achieve this, state-space models play a fundamental role in many parts of the book. The book traces the evolution of filtering techniques from Wiener and Kolmogorov’s stationary approach to Kalman’s state-space method. It begins with probability theory and Bayesian estimation fundamentals, and then moves on to Wiener and Kalman theories for discrete-time linear systems. The final chapters deal with nonlinear estimation using modern stochastic simulation techniques such as Markov chain Monte Carlo and particle filters, which have revolutionised the field of statistics in recent years and have found many applications in engineering and science. Throughout, the book balances theoretical concepts with practical examples and numerical illustrations. It concludes with exercises on the Kalman filter, useful for exam preparation. The content is suitable for advanced undergraduate and postgraduate students in the field.
GIANLUIGI PILLONETTO is Full Professor in the subject area of Control and Dynamic Systems at the Department of Information Engineering, University of Padova, Italy. His teaching experience includes numerous courses (Data Analysis, Estimation and Filtering, Signals and Systems, Automatic Control, Functional Analysis, Machine Learning). He currently teaches three courses: Systems and Models, Estimation and Filtering, Applied Functional Analysis and Machine Learning.
MAURO BISIACCO was Associate Professor in the subject area of Control and Dynamic Systems at the Department of Information Engineering, University of Padova, Italy (since October 2021 he is retired). His teaching experience included numerous courses (Systems Theory, Automatic Control, Identification Theory, Fundamentals of Automation, Model Identification and Data Analysis, Advanced Control Techniques, Systems and Models, Digital Control).