◉ Home

The ADMIRABLE  — Advanced Data MIning Research And (Business intelligence | Bioinformatics | Big data) LEarning — research group main aim is the development of new ensemble algorithms and the application of data mining, data visualization and pattern matching techniques to diverse fields as bioinformatics, time series classification and high dimensional data analysis.

Among the main achievements of the researchers of the group is the development of several new ensemble construction algorithms: Rotation Forest, Disturbing Neighbours, Nonlinear Boosting Projections, Random Balance, …, that have aroused the interest of the data mining community.

Its members are in close relationship with research groups of other universities, currently collaborating with groups from the universities of Córdoba and Valladolid. The researchers of the group have international connections too. They have done research works while visiting other universities such as Stockholm University in Sweden, University of Gales and West Scotland University in United Kingdom, and Tsinghua University in China.

Its research interests are among others: Artificial Intelligence, Data Mining, Multi-Dimensional Data Visualization, Ensemble Construction, Bioinformatics, Regressors Ensembles, Instance Selection, Feature Selection, Decision Trees.

The group is recognized by the regional government of Castile and Leon as a Consolidated Research Unit.

◉ Research lines

Ensemble Construction
This research line consists in designing new algorithms for construction strong classifiers from the combination of a set of weak classifiers.
Data Mining
Data mining has its roots in artificial intelligence and statistics, is the process of extracting hidden patterns from data solving forecasting, classification and clustering problems.
Instance and attribute selection
Reduce the number of instances and characteristics of a data set to accelerate processing without affecting the information obtained. Extend the methods used in the area of classification to others like regression and multi-label classification.
Big Data
Parallelization of data mining algorithms for their adaptation to the processing of large volumes of data.
Bioinformatics is the application of data mining and data analysis techniques to manage and analyse biological data. Common problems in bioinformatics include sequence aligning and gene prediction.
Data mining applications in Software Engineering
Reduce software maintenance costs by improving the quality of software processes and products through the application of data mining.
Applied Visualization Techniques
Designing new methods for the graphic representation of Multi-dimensional data in order to obtain a clearer idea of its structure, but also 3D modelling and Virtual Reality for the diffusion of Historical-Artistic and Archaeological Heritage

◉ Selected publications