CYTUVA

Research Group - Data analytics: Big Data

Download PDF

Contact Information

Javier Manuel Aguiar Pérez
Campus Miguel Delibes, Paseo Belén, 15
Valladolid, Valladolid (47011) - 2D096
Send email
983425594
983423667

Basic Information

UniversityUniversidad de Valladolid
Center
DepartmentSignal Theory and Communications and Telematics Engineering
Investigation GroupData Engineering Unit

Description

Big data refers to the set of procedures related to the management of great amounts of information, including macro-data collection, storage, search, sharing, analysis and visualization, which cannot be processed by traditional computer applications.

Artificial intelligence, natural language processing and automatic learning are at the forefront among these techniques. The latter two learn from data, so the more information is storaged, the more machines learn.

There are many tools to manage big data, such as Hadoop, NoSQL, Cassandra, Business intelligence, Automatic learning and MapReduce, among others. These tools deal with any of the three existing types of big data (structured, unstructured and semi-structured data).

As data is collected and storaged using different storage technologies, different data analysis techniques are necessary: association, data mining, clustering or text analytics.

These management techniques and the analysis of great amounts of generated data are effective to develop innovations in business management, provision of public services, design and implementation of development measures, eCommerce or marketing intelligence.

Other information

Number of researchers:

Development status:

In research and development phase

Intellectual Property Rights:

Susceptible Propiedad Intelectual

Differentiation in the market:

Novelty

Applicability of technology:

Yes

Companies and markets:

The set of technologies related to big data can be used in a variety of fields and areas concerned with data analysis and management. The tendency to manipulate great amounts of data lies in the need, in many cases, to include such information in statistical reports and predictive models used in different subjects, such as business and advertising analytics, data on infectious diseases, population espionage and monitoring, or the fight against organized crime.

Advantages:

The Big Data reseach line is quite cross-cutting, so it is intended to develop ad hoc applications to process huge volumes of data in a quick and accurate way, and to convert them in a powerful tool for business development.

The data sources that can be managed are many and of different natures:

Generated by people: emails, WhatsApp messages, Facebook states, Twitter, usage traces in an ERP system, including entries in a database or adding information in a spreadsheet.
Transaction data: invoicing, calls or transactions between accounts create information that, once processed, can become relevant data.
Electronic and web marketing: Web 2.0 has broken the paradigm webmaster-content-reader and the users themselves have become content creators through their interaction with the site.
Machine to machine (M2M): several meters and sensors that transform physical or chemical magnitudes into data.
Biometrics: data generated by biometric readers from security, defense and intelligence services.

Additional Information:

Extensive experience in Spanish and European projects.

UNESCO Code:

3304 - Computer technology

Photos

Videos

Other resources

Related projects

Smart Easy Path (SEP)

The so-called Travelling Salesman Problem (TSP) is based on the idea that every salesman aims at visiting a group of clients travelling the shortest possible distance. The solution proposed by Smart Easy Path (SEP) seeks to answer this problem consid... Read more >

DigiCIELAB: Colorimetric artificial vision application

Colorimeters are commonly used for color measurements. These instruments are expensive and can be time-consuming to operate. A more economical and versatile alternative can be developed with the help of Artificial Vision and Artificial Neural Network... Read more >

Combustion processes in thermal engines. Thermochemical processes of forest biomass gasification - producer gas.

The objective of this research line is to carry out thermochemical processes of forest biomass gasification consisting in the transformation of solids (mostly pine and eucalyptus wood) into low calorific gaseous fuels, also known as producer gas.... Read more >

ComunicaGIF: SAAC design using GIFs

Each person is different and, thus, each communicates in a different way. In some cases, there are disorders o diseases that cause consequences on the subjects like the inability to carry out the traditional communication by spoken language, so they ... Read more >

Generating PDF document