The WEB-BI project, co-founded by the Piedmont Region in the context of POR FESR 2007/2013, has the objective to deliver an innovative framework to extract affordable information from web sites. The ICT techniques employed in this framework have been applied in the specific context of Regenerative Medicine, exploring information on therapeutic employment of stem cells and medical products for advanced therapies. The project objectives emerge from the observation that the web contains a huge amount of data, and that converting this data into useful information is a difficult and time consuming task. This is especially true for young research sectors such as Regenerative Medicine. Researchers and professionals working in this field spend a lot of time exploring the web to find new useful information, and relating it to their own knowledge base. Automatic exploration and summarization of web data comes with many problems and obstacles, which include the necessity to deal with multi-linguistic, unstructured and potentially unreliable sources of information. The WEB-BI project applies advanced ICT techniques to solve these problems, and applies Business Intelligence techniques to data extracted from the web, in order to extract statistical information in real-time, and to make available the relevant sources from where this information has been extracted. Instead of exploring the web to gather information of recent trials performed on a specific disease, with WEB-BI one can immediately see how many trials have been performed, where, when, and then read more detailed information of the referred sources. The WEB-BI project has delivered a prototype of the basic tools and techniques that will be later employed to create a publicly available web site, that will provide the following features: - real-time statistical information about trials, published papers, therapies and medical products - automatic digests of clusters of related sources, such as papers published on a specific field of research - direct access to sources of information used to create statistics and digests - exploration of the web to find new relevant sources of information about Regenerative Medicine - automatic evaluation of the affordability of the new sources - natural language processing techniques to extract information from both structured and unstructured documents The WEB-BI research project has been successfully ended in September, 2013, and the involved partners are currently approaching the necessary activities to convert the research result into a product that can be made available to the public.
WEB-BI: Business Intelligence and Regenerative Medicine / Apiletti, Daniele; Ardissone, V.; Baralis, ELENA MARIA; Breganni, S.; Cagliero, Luca; Ciaramella, A.; Ciaramella, M.; De Bonis, S.; Ferrandi, C.; Perego, G.; Vandoni, L.. - STAMPA. - (2013). (Intervento presentato al convegno International Satellite Symposium AICC-GISM tenutosi a Brescia nel 20-22 Novembre 2013).
WEB-BI: Business Intelligence and Regenerative Medicine
APILETTI, DANIELE;BARALIS, ELENA MARIA;CAGLIERO, LUCA;
2013
Abstract
The WEB-BI project, co-founded by the Piedmont Region in the context of POR FESR 2007/2013, has the objective to deliver an innovative framework to extract affordable information from web sites. The ICT techniques employed in this framework have been applied in the specific context of Regenerative Medicine, exploring information on therapeutic employment of stem cells and medical products for advanced therapies. The project objectives emerge from the observation that the web contains a huge amount of data, and that converting this data into useful information is a difficult and time consuming task. This is especially true for young research sectors such as Regenerative Medicine. Researchers and professionals working in this field spend a lot of time exploring the web to find new useful information, and relating it to their own knowledge base. Automatic exploration and summarization of web data comes with many problems and obstacles, which include the necessity to deal with multi-linguistic, unstructured and potentially unreliable sources of information. The WEB-BI project applies advanced ICT techniques to solve these problems, and applies Business Intelligence techniques to data extracted from the web, in order to extract statistical information in real-time, and to make available the relevant sources from where this information has been extracted. Instead of exploring the web to gather information of recent trials performed on a specific disease, with WEB-BI one can immediately see how many trials have been performed, where, when, and then read more detailed information of the referred sources. The WEB-BI project has delivered a prototype of the basic tools and techniques that will be later employed to create a publicly available web site, that will provide the following features: - real-time statistical information about trials, published papers, therapies and medical products - automatic digests of clusters of related sources, such as papers published on a specific field of research - direct access to sources of information used to create statistics and digests - exploration of the web to find new relevant sources of information about Regenerative Medicine - automatic evaluation of the affordability of the new sources - natural language processing techniques to extract information from both structured and unstructured documents The WEB-BI research project has been successfully ended in September, 2013, and the involved partners are currently approaching the necessary activities to convert the research result into a product that can be made available to the public.Pubblicazioni consigliate
I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.
https://hdl.handle.net/11583/2523499
Attenzione
Attenzione! I dati visualizzati non sono stati sottoposti a validazione da parte dell'ateneo