Carlos Cernuda
Johannes Kepler University of Linz
24 Papers
88 Citations
Carlos Cernuda is an academic researcher from Johannes Kepler University of Linz. The author has contributed to research in topics: Fuzzy control system & Population. The author has an hindex of 9, co-authored 22 publications. Previous affiliations of Carlos Cernuda include Basque Center for Applied Mathematics & University of Mondragón.
Chat about Author
Papers
Interpreting Remaining Useful Life estimations combining Explainable Artificial Intelligence and domain knowledge in industrial machinery
Oscar Serradilla,Ekhi Zugasti,Carlos Cernuda,Andoitz Aranburu,Julian Ramirez de Okariz,Urko Zurutuza +5 more
- 19 Jul 2020
TL;DR: The implementation and explanations of a remaining life estimator model based on machine learning, applied to industrial data, and the need of collaboration between expert knowledge technicians and eXplainable Artificial Intelligence techniques to understand advanced machine learning models are highlighted.
49
NIR-based quantification of process parameters in polyetheracrylat (PEA) production using flexible non-linear fuzzy systems
TL;DR: Results on a concrete data set show that the usage of a specific type of fuzzy systems, so-called Takagi-Sugeno fuzzy Systems, for calibrating the chemometric models can outperform state-of-the-art calibration methods as well as support vector regression as alternative non-linear model.
32
Validation of Random Forest Machine Learning Models to Predict Dementia-Related Neuropsychiatric Symptoms in Real-World Data.
Javier Mar,Ania Gorostiza,Oliver Ibarrondo,Carlos Cernuda,Arantzazu Arrospide,Álvaro Iruin,Igor Larrañaga,Mikel Tainta,Enaitz Ezpeleta,Ane Alberdi +9 more
TL;DR: Predictive models can be used to estimate prevalence of NPS in population databases using clinical databases representing the whole population to inform decision-makers, given their relatively good performance.
Incremental and decremental active learning for optimized self-adaptive calibration in viscose production
Carlos Cernuda,Edwin Lughofer,Georg Mayr,Thomas Röder,Peter Hintenaus,Wolfgang Märzinger,Jürgen Kasberger +6 more
TL;DR: Experiments on real-world data streams from viscose production process show that the new self-calibration methods are able to significantly reduce the number of update cycles while still keeping the predictive quality of the calibration models high (below 5% errors) for H 2 SO 4 and Na 2SO 4.
25
Hybrid adaptive calibration methods and ensemble strategy for prediction of cloud point in melamine resin production
Carlos Cernuda,Edwin Lughofer,Peter Hintenaus,Wolfgang Märzinger,Thomas Reischer,Marcin Pawliczek,Jürgen Kasberger +6 more
TL;DR: Non-linear modeling methodology can outperform state-of-the-art linear and non-linear chemometric modeling methods in terms of validation error, the ensemble strategy is able to improve the performance of models without ensembling significantly and incremental model updates are necessary in order to keep the predictive quality of the models high by preventing drifting residuals.
21