Servizi per la didattica

Latent Variables-based Multivariate Data Analysis for Knowledge Discovery (didattica di eccellenza)


A.A. 2018/19

Course Language


Course degree

Doctorate Research in Chemical Engineering - Torino

Course structure
Teaching Hours
Lezioni 20
Teacher Status SSD h.Les h.Ex h.Lab h.Tut Years teaching
Fissore Davide Professore Associato ING-IND/26 2 0 0 0 1
Teaching assistant

SSD CFU Activities Area context
*** N/A ***    
PERIOD: MARCH Prof. Alberto Ferrer is Head of the Multivariate Statistical Engineering Research Group ( and Professor of Statistics at the Department of Applied Statistics, Operation Research and Quality at Universitat Politècnica de València (Spain). His main interest focuses on statistical techniques for quality and productivity improvement, especially those related to multivariate statistical methods for both continuous and batch processes, and data analytics. He is active in industrial teaching and consultancy activities on Big Data, Internet of Things (IoT), Six Sigma, Process Analytical Technology (PAT), Multivariate Image Anlaysis (MIA), Process Chemometrics and Statistical Methods for Knowledge Discovery. We are witnessing a data avalanche in a lot of areas: banking, marketing, science, engineering, technology and so on, leading to the so-called Big Data environment. The quantity of data streams that has become available and stored in historical databases has grown by orders of magnitude, and the extraction of useable and timely information from these databases has now become a major concern. Big data exhibit high volume and correlation, rank deficiency, low signal-to-noise ratio, complex and changing structure, and missing values. Most of the classic statistical analysis methods commonly taught in textbooks and courses are not suitable for analyzing this type of data.
In this seminar we illustrate the potential of latent variable-based multivariate statistical methods to analyze Big Data streams and visualize extracted information in a way that is easily interpreted and that is useful for process understanding, process monitoring, troubleshooting, process improvement and optimization. A critical comparison with other classic statistical methods and data mining techniques from machine learning will also be provided. Special emphasis will be given to multivariate image analysis. Timetable: 20 hours, from March 26th to March 29th (9:30-12:30, 14:30-16:30), Room Denina @ DISAT.
References: • Abdi, H. and Williams, L.J. (2010) “Principal Component Analysis”. Computational Statistics, 2, 433-459. • Duchesne C, Liu J.J., MacGregor J.F. (2012) “Multivariate image analysis in the process industries: a review”. Chemometrics and Intelligent Laboratory Systems,117:116‐128. • Geladi, P., and Kowalski, B.R. (1986) “Partial Least-Squares Regression: A Tutorial”. Analytica Chimica Acta, 185, 1-17. • MacGregor, J.F., Bruwer M.J., Miletic, I., Cardin, M., Liu, Z. (2015) Latent Variable Models and Big Data in the Process Industries. 9th International Symposium on Advanced Control of Chemical Processes. The International Federation of Automatic Control. June 7-10, 2015, Whistler, British Columbia, Canada, 521-525. • Prats‐Montalban J.M., de Juan A., Ferrer A. (2011) “Multivariate image analysis: a review with applications”. Chemometrics and Intelligent Laboratory Systems, 107, 1-23. • Wold, S., Esbensen, K., and Geladi, P. (1987) “Principal Component Analysis”. Chemometrics and Intelligent Laboratory Systems, 2, 37-52. • Wold, S., Sjöström, M., Eriksson, L. (2001) “PLS-regression: a basic tool of chemometrics”. Chemometrics and Intelligent Laboratory Systems, 58, 109-130.
Modalità di esame:

© Politecnico di Torino
Corso Duca degli Abruzzi, 24 - 10129 Torino, ITALY