Rosario Delgado

Associate professor at UAB
Research area: Probability / Mathematical Modelling

PhD in Mathematics obtained at Universitat de Barcelona (1994)


Degree in Mathematics from Universtitat de Barcelona (1987).

Current research:

  • Machine Learning methods for pre-processing of the data.
  • Supervised Learning for classification and performance measures.
  • Bayesian networks with applications to criminology, health care and other areas.
  • Ensembles of classifiers.
  • Applications of Probability and Statistics to different areas of the field of Sciences and the Social Sciences.

Research lines

Probability Modelling

Machine Learning

Supervised Learning


Bayesian networks

Selected publications

1.      "A semi-hard voting combiner scheme to ensemble multi-class probabilistic classifiers". Appl Intell (2021).

2.      "Survival in the Intensive Care Unit: a prognosis model based on Bayesian Classifiers" amb J.D. Núñez-González, J.C. Yébenes i Ángel Lavado. Artificial Intelligence in Medicine. Volume 115, May 2021, 102054

3.      "Why Cohen’s Kappa should be avoided as performance measure in classification" with X.A. Tibau. PLoS ONE 14(9): e0222916 (2019).

4.      "Enhancing Confusion Entropy (CEN) for binary and multiclass classification" with J.D. Núñez-González. PLoS ONE 14(1): e0210264 (2019).

5.      "Measuring Features Strength in Probabilistic Classification" with X.A. Tibau. In: Medina J. et al. (eds) Information Processing and Management of Uncertainty in Knowledge-Based Systems. Theory and Foundations. IPMU 2018. Communications in Computer and Information Science, vol 853, pp. 357-369. Springer, Cham (2018).

6.      "A Bayesian Network Profiler for Wildfire Arsonists" with J.L. González, A. Sotoca and X.A. Tibau. In Machine Learning, Optimization, and Big Data. Second International Workshop, MOD 2016, Volterra, Italy, August 26-29, 2016, Revised Selected Papers. P.M. Pardalos et al. (Eds.): MOD 2016, Lecture Notes in Computer Science (LNCS) 10122, pp. 379–390, Springer International Publishing AG 2016.
DOI: 10.1007/978-3-319-51469-7 31.