ID:
502594
Duration (hours):
56
CFU:
6
SSD:
AUTOMATICA
Year:
2025
Overview
Date/time interval
Annualità Singola (29/09/2025 - 12/06/2026)
Syllabus
Course Objectives
Knowledge of basic notions of: estimation theory (maximum likelihood estimation, a-posteriori estimation); neural-based model identification; stochastic processes (mean, autocovariance, spectral density, optimal prediction); identification of ARMAX models. Ability to solve identification and prediction problems ranging from model formulation to the use of computer tools (Matlab) for parameter estimation and model simulation.
Course Prerequisites
Basic notions of set theory, logic, calculus, function maximization.
Teaching Methods
Teaching is based on lectures, tutorials and laboratory activities in the computer room.
For teaching activities, slide presentations are used, which are made available to students in the teaching section on the KIRO platform, where video recordings of lectures and teaching materials for exercises and labs are also available. During laboratory hours, students are introduced to model identification from data. Attendance at laboratory activities is optional.
For teaching activities, slide presentations are used, which are made available to students in the teaching section on the KIRO platform, where video recordings of lectures and teaching materials for exercises and labs are also available. During laboratory hours, students are introduced to model identification from data. Attendance at laboratory activities is optional.
Assessment Methods
Written examination: two questions of a theoretical nature and two of a practical nature. One of the theoretical questions may be a closed true/false answer. Duration is between 1.5 and 2 hours. The assessment, in thirtieths, is the average of the marks for the individual answers weighted according to their difficulty. Texts, textbooks and notes may not be consulted during the test. During the second semester, a data analysis project is proposed, to be carried out in small groups and requiring the submission of a code and a slide presentation by a date set by the lecturer. A mark of 0 to 3 points is awarded on the basis of the students' presentation of the project and is added to the mark for the written test. The performance of the project is optional. Examples of examination questions are presented during the lectures.
Texts
Lecture notes (http://sisdin.unipv.it/labsisdin/teaching/teaching.php).
A. Papoulis. Probability, Random Variables, and Stochastic Processes. McGraw-Hill.
L. Ljung. System Identification: Theory for the User. Prentice-Hall.
A. Papoulis. Probability, Random Variables, and Stochastic Processes. McGraw-Hill.
L. Ljung. System Identification: Theory for the User. Prentice-Hall.
Contents
System Identification deals with methodologies that enable the construction of mathematical models of systems and signals based on experimental data. In presence of complex systems whose behavior can be hardly reduced to known "laws of nature", the use of identification techniques is often the only way to obtain models to be used in the context of forecasting, simulation, and control. The methods presented in the course are widely used in heterogeneous fields such as automation, biomedical engineering, econometry, hydrology, geophysics and telecommunications. The main properties (stability, input-output description in the time and frequenct domains) of linear discrete-time systems are introduced. In the context of parametric estimation, the issues of model validation and model complexity are extensively discussed. Neural based identification is also illustrated and discussed, pointing out pros and cons with respect to standard approaches. The study of dynamic systems addresses three main topics: the optimal prediction of stationary stochastic processes (Wiener filtering), the identification of linear discrete-time systems, and spectral estimation (both nonparametric and maximum-entropy).
Estimation theory:
maximum likelihood estimation: properties and examples;
a-posteriori estimation, Bayes estimator;
cross-validation, model complexity and the bias-variance dilemma;
identification of nonlinear-in-parameter models.
Neural identification:
Radial basis function neural networks;
Multi-layer perceptron networks;
generalization, overfitting, selection of network size.
Stochastic processes and optimal prediction:
mean, autocorrelation, autocovariance, independence, incorrelation;
white noise, random walk, MA, AR, and ARMA processes, Yule-Walker equations;
stationarity, power spectral density, nonparametric spectral estimatiom;
spectral factorization, optimal prediction.
Identification of dynamic systems:
classes of dynamic models: output error, ARX, ARMAX;
prediction-error methods for system identification;
least-squares identification of ARX models: probabilistic analysis and persistent excitation.
Estimation theory:
maximum likelihood estimation: properties and examples;
a-posteriori estimation, Bayes estimator;
cross-validation, model complexity and the bias-variance dilemma;
identification of nonlinear-in-parameter models.
Neural identification:
Radial basis function neural networks;
Multi-layer perceptron networks;
generalization, overfitting, selection of network size.
Stochastic processes and optimal prediction:
mean, autocorrelation, autocovariance, independence, incorrelation;
white noise, random walk, MA, AR, and ARMA processes, Yule-Walker equations;
stationarity, power spectral density, nonparametric spectral estimatiom;
spectral factorization, optimal prediction.
Identification of dynamic systems:
classes of dynamic models: output error, ARX, ARMAX;
prediction-error methods for system identification;
least-squares identification of ARX models: probabilistic analysis and persistent excitation.
Course Language
Italian
Degrees
Degrees (2)
ELECTRONIC AND COMPUTER ENGINEERING
Bachelor’s Degree
3 years
Bioengineering
Master’s Degree
2 years
No Results Found
People
People
No Results Found