Neural models based on unsupervised learning for the visualization of large data sets

  • From Spain
  • Responsive
  • Research Services and Capabilities

Summary of the technology

With the models developed by this group, the structure of high-dimensional data sets can be visualized first and subsequently analyzed. I mean, itallows a study of data for example with a large number of instances (examples) andalso a large number of variables for each of them.


Details of the Technology Offer

New and innovative aspects

There are other data visualization methods, but most of them do not providea simple and intuitive way to identify the structure and analyze the behavior of thedata.
In this way, analysis times are reduced and preliminary results are obtained thatthey can guide later, more in-depth analyzes.

Main advantages of its use

By offering a projection that preserves most of the information in the data, maximizing the possibility of enhancing the structure of the data, a subsequent rapid analysis of the data is allowed. In the first place, the general structure of the data set can be identified, detecting their grouping (different types of customers, product groups, behavior of the analyzed machines, stages or regions of operation of the different processes ...). Once this general structure is known, it is possible to proceed to a detailed analysis of each of these groups, considering their internal structure. With all this, you can easily carry out an analysis of the data, drawing conclusions about them when interpreted by an expert in the field (factors that affect customer behavior, star products or with less success, optimal values adjustment of a certain machine, understanding of certain processes).


Currently there is such a large amount of information that it cannot be easily processed to extract knowledge from it. An exhaustive analysis, on a case-by-case basis, would push the analysis of a large number of data that is captured today to unapproachable limits. These can refer to statistics of purchases of our clients, characteristics of different products, records of a certain machine or system, samples of a certain industrial process, etc. The projectionist models propose a data visualization with these characteristics; a large volume and also a high dimensionality (large amount of information for each of the customers, products, records, samples ...).


These models can be applied to any data set that needs to beanalyzed, regardless of the reality to which these data refer.Some application examples are those mentioned above: economic data, production data, operating or access statistics, etc.

Current development status

Device already developed and validated for industrialization.

Desired business relationship

Commercial Agreement, License Agreement, Technical Cooperation: further development; Technical Cooperation: testing new applications; Technical Cooperation: adaptation to specific needs.

Attached documents

Related Keywords

  • Computer related
  • Other
  • analysis
  • learning
  • neural models
  • data sets
  • variables


The aim of the The Technology Transfer Office (TTO) of the Univesidad de Burgos is to promote Innovation technology through the reseach results transfer and the conexions between the University and the new needs and requirements of the society - we are the link between the University and the Industry. Contact person: José Manuel López (


Never miss an update from UNIVERSIDAD DE BURGOS

Create your free account to connect with UNIVERSIDAD DE BURGOS and thousands of other innovative organizations and professionals worldwide


Send a request for information

About Technology Offers

Technology Offers on Innoget are directly posted
and managed by its members as well as evaluation of requests for information. Innoget is the trusted open innovation and science network aimed at directly connect industry needs with professionals online.


Need help requesting additional information or have questions regarding this Technology Offer?
Contact Innoget support