Claudio Sartori is Professor of Machine Learning and Informatics. BBS Consultant for activities in the Data Science area. Laurea Degree in Electronic Engineering (Italian title obtained in 1981). Visiting professor at Technical University Federigo Santa Maria, Valparaiso, Chile. Responsible for the Observatory on Technological Innovation for the EULA-GTEC Erasmus + Project, whose goal is the design and launching of an Observatory or Antenna that allow perceiving training problems among managers (to improve training offers) and identifying SMEs demands, which are not clearly revealed (to improve demand identification). The Observatory will also contribute to the employability of graduates creating links with the SMEs labour market. Joint Research cooperation with: Department of Informatics, Technical University Federico Santa Maria (UTFSM), Valparaiso, Chile. Universitè de Nice – Sopia Antipolis, Nice, France.
Modern manufacturing processes exploit massively the digital technology, as is witnessed by the increasing interest towards the new operating paradigms known as “Industry 4.0”. The purpose of this module is to exploit the skills acquired in other modules, mainly “Data analysis”, “Data Mining” and “Operation Analytics”, to deal with the “Manufacturing data” and to extract information useful for increasing the effectiveness of manufacturing.
Models and methods for knowledge extraction from databases. Study of different types of data and methods of pre-treatment. The functions of Data Mining. Supervised and unsupervised learning. Algorithms and methods for constructing classification models. Clustering algorithms. Algorithms for discovering association rules. Methods for evaluating the quality of data mining results. Data mining laboratory in order to apply the studied methods.
Data Science and Business Analytics
Introduction to the base principles and methods of Data Mining and Machine Learning, with particular reference to Classification, Clustering, Association Rules. Analysis of the major problems related to data quality and data transformation. Use of open source software to solve data mining and machine learning problems, with specific reference to datasets related to environment and sustainabilitySustainability Transition Management
The course provides an overview on the Machine learning field, with a particular emphasis on
symbolic learning techniques (sub symbolic techniques will be covered by the course on Neural Networks).
The main learning problems and paradigms will be introduced along with examples explaining how to
use the learned models into decision support systems.
Application areas that will be covered have industrial impact in fields as automotive, energy management,
predictive maintenance and policy making.
The course will cover both lectures and hands-on sessions.