This project intends to supply an innovative service that can be accessed via the Web to hospital management, public and private research institutes, cell factories and public and private biobanks that use adult stem cells in the field of regenerative medicine, a service capable of grouping and aggregating information from the Internet in real time.
The Web has an enormous amount of data that could be analysed to extract information useful for the purposes of regenerative medicine. The process of extracting, transforming and loading data in a Business Intelligence system (known as ETL systems) normally uses data that has already been structured, or partially structured, stored in a company’s IT system. However, when information is sourced from the Web, it is not structured and it is definitely not reliable.
In order to extract information from the Web, it is therefore necessary to identify algorithms that will allow us to determine the level of reliability of a website and load unstructured information to a data warehouse. The project aims to define such algorithms, implement them and experiment their use for the analysis of information found on the Internet.
Project co-financed within the Innovation Poles of the Piedmont Region (POR FESR 2007/2013, Axis I, Activities I.1.3 - II Annual program for projects and services for Research and Innovation).