About me

I am an associate professor and researcher at the Department of Computer Science, Applied Mathematics and Statistics of the University of Girona. I am interested in machine learning problems in which data uncertainty/missingness is a determining characteristic, such as weakly supervised learning. I also study probabilistic graphical models for probabilistic inference and machine learning. Many of my works aim to learn probabilistic graphical models, commonly Bayesian networks, from weakly labeled data. I have applied these developments to problems from different domains, such as biomedical, environmental, and educational domains.

Publications

• Jul2024

  Modeling river flow for flood forecasting: A case study on the Ter river

  F. Serrano-López, S. Ger-Roca, M. Salamó, J. Hernández-González

  In Applied Computing and Geosciences in press · Supplementary material

• Apr2024

  Fairness and bias correction in machine learning for depression prediction across four study populations

  V.N. Dang, A. Cascarano, R.H. Mulder, C. Cecil, M.A. Zuluaga, J. Hernández-González, K. Lekadir

  In Scientific Reports 14: 7848

• Dec2023

  On the Supervision of Peer Assessment Tasks: An Efficient Instructor Guidance Technique

  J. Hernández-González, P.J. Herrera

  In IEEE Transactions on Learning Technologies 16(6): 926-939 · Supplementary material

• Dec2023

  Predicting ICU Mortality in Acute Respiratory Distress Syndrome Patients Using Machine Learning: The POSTCARDS Study

  J. Villar, J.M. González-Martín, J. Hernández-González, et al.

  In Critical Care Medicine 51(12): 1638-1649

• Aug2023

  Machine and deep learning for longitudinal biomedical data: a review of methods and applications

  A. Cascarano, J. Mur-Petit, J. Hernández-González, M. Camacho, N.T. Eadie, P. Gkontra, M. Chadeau-Hyam, J. Vitria, K. Lekadir

  In Artificial Intelligence Review 56: 1711-1771

• Jan2023

  On the use of the descriptive variable for enhancing the aggregation of crowdsourced labels

  I. Beñaran-Muñoz, J. Hernández-González, A. Pérez

  In Knowledge and Information Systems 65: 241-260

• Oct2022

  Modeling three sources of uncertainty in assisted reproductive technologies with probabilistic graphical models

  J. Hernández-González, O. Valls, A. Torres-Martín, J. Cerquides

  In Computers in Biology and Medicine 150: 106160 · Supplementary material

• Sep2022

  Machine learning from crowds using candidate set-based labelling

  I. Beñaran-Muñoz, J. Hernández-González, A. Pérez

  In IEEE Intelligent Systems 37(6): 57-68

• Aug2022

  On the relative value of weak information of supervision for learning generative models: An empirical study

  J. Hernández-González, A. Pérez

  In International Journal of Approximate Reasoning 150: 258-272 · Supplementary material

• Oct2021

  Validation on Real Data of an Extended Embryo-Uterine Probabilistic Graphical Model for Embryo Selection

  A. Torres-Martín, J. Hernández-González, J. Cerquides

  In Proceedings of the 23rd International Conference of the Catalan Association for Artificial Intelligence (CCIA)

• May2021

  A Conceptual Probabilistic Framework for Annotation Aggregation of Citizen Science Data

  J. Cerquides, M.O. Mulayim, J. Hernández-González, A.R. Shankar, J.L. Fernández-Márquez

  In Mathematics 9(8): 875

• Dec2020

  A Robust Solution to Variational Importance Sampling of Minimum Variance

  J. Hernández-González, J. Cerquides

  In Entropy 22(12): 1405

• Oct2019

  Variational importance sampling: initial findings

  J. Hernández-González, J. Capdevila, J. Cerquides

  In Proceedings of the 22nd International Conference of the Catalan Association for Artificial Intelligence (CCIA)

• Apr2019

  A framework for evaluation in learning from label proportions

  J. Hernández-González

  In Progress in Artificial Intelligence 8 (3): 359-373 · Supplementary material

• Apr2019

  Beach litter forecasting on the SE coast of the Bay of Biscay: A bayesian networks approach

  I. Granado, O.C. Basurko, A. Rubio, L. Ferrer, J. Hernández-González, I. Epelde, J.A. Fernandes

  In Continental Shelf Research 180: 14-23

• Jan2019

  Aggregated outputs by linear models: An application on marine litter beaching prediction

  J. Hernández-González, I. Inza, I. Granado, O.C. Basurko, J.A. Fernandes, J.A. Lozano

  In Information Sciences 481: 381-393 · Supplementary material

• Oct2018

  Evaluation in learning from label proportions: an approximation to the precision-recall curve

  J. Hernández-González

  In Proceedings of the 18th Conference of the Spanish Association for Artificial Intelligence (CAEPIA) · Supplementary material

• Oct2018

  Crowd learning with candidate labeling: an EM-based solution

  I. Beñaran-Muñoz, J. Hernández-González, A. Párez

  In Proceedings of the 18th Conference of the Spanish Association for Artificial Intelligence (CAEPIA)

• Jun2018

  A note on the behavior of majority voting in multi-class domains with biased annotators

  J. Hernández-González, I. Inza, J.A. Lozano

  In IEEE Transactions on Knowledge and Data Engineering 31(1): 195-200 · Supplementary material

• Jan2018

  Two datasets of defect reports labeled by a crowd of annotators of unknown reliability

  J. Hernández-González, D. Rodriguez, I. Inza, R. Harrison, J.A. Lozano

  In Data in Brief 18: 840-845

• Jan2018

  Learning to classify software defects from crowds: A novel approach

  J. Hernández-González, D. Rodriguez, I. Inza, R. Harrison, J.A. Lozano

  In Applied Soft Computing Journal 62: 579-591 · Supplementary material

• Aug2017

  Merging knowledge bases in different languages

  J. Hernández-González, Estevam R. Hruschka Jr., Tom M. Mitchell

  In Proceedings of the 11th TextGraphs Workshop at ACL'17

• Feb2017

  Learning from proportions of positive and unlabeled examples

  J. Hernández-González, I. Inza, J.A. Lozano

  International Journal of Intelligent Systems 32: 109--133

• Sep2016

  Whatever you know, just tell me something: Crowd learning with free supervision

  J. Hernández-González, I. Inza, J.A. Lozano

  In Proceedings of the VIII Symposium of Data Mining Theory and Applications (TAMIDA)

• May2016

  Fitting the data from embryo implantation prediction: learning from label proportions

  J. Hernández-González, I. Inza, L. Crisol-Ortiz, M.A. Guembe, M.J. Iñarra, J.A. Lozano

  Statistical Methods in Medical Research 27(4): 1056-1066, 2018 · Supplementary material

• Jan2016

  Weak supervision and other non-standard classification problems: a taxonomy

  J. Hernández-González, I. Inza, J.A. Lozano

  Pattern Recognition Letters 69: 49-55

• Nov2015

  A novel weakly supervised problem: Learning from positive-unlabeled proportions

  J. Hernández-González, I. Inza, J.A. Lozano

  In Proceedings of the 16th Conference of the Spanish Association for Artificial Intelligence (CAEPIA)

• Jan2015

  Multidimensional learning from crowds: usefulness and application of expertise detection

  J. Hernández-González, I. Inza, J.A. Lozano

  International Journal of Intelligent Systems 30(3): 326-354

• Dec2013

  Learning Bayesian network classifiers from label proportions

  J. Hernández-González, I. Inza, J.A. Lozano

  Pattern Recognition 46(12): 3425-3440 · Supplementary material

• Sep2013

  Learning from crowds in multi-dimensional classification domains

  J. Hernández-González, I. Inza, J.A. Lozano

  In Proceedings of the 15th Conference of the Spanish Association for Artificial Intelligence (CAEPIA)

• Nov2011

  Learning naive Bayes models for Multiple-Instance Learning with label proportions

  J. Hernández-González, I. Inza

  In Proceedings of the 14th Conference of the Spanish Association for Artificial Intelligence (CAEPIA)

Special mentions

• 2018

  Best PhD thesis award

  University of the Basque Country

• 2016

  Best idea award

  Open Data Euskadi

• 2015

  Best student paper award

  16th Conference of the Spanish Association for Artificial Intelligence (CAEPIA)