@article {OTERO201642, title = {Finding informative code metrics under uncertainty for predicting the pass rate of online courses}, journal = {Information Sciences}, volume = {373}, year = {2016}, pages = {42 - 56}, abstract = {A method is proposed for predicting the pass rate of a Computer Science course. Input data comprises different software metrics that are evaluated on a set of programs, comprising students{\textquoteright} answers to a list of computing challenges proposed by the course instructor. Different kinds of uncertainty are accepted, including missing answers and multiple responses to the same challenge. The most informative metrics are selected according to an extension to vague data of the observed Fisher information. The proposed method was tested on experimental data collected during two years at Oviedo University. Yearly changes in the pass rate of two groups were accurately predicted on the basis of 7 software metrics. 73 volunteer students and 1500 source files were involved in the experimentation.}, keywords = {Automatic grading, feature selection, Genetic Fuzzy Systems, Low Quality Data, vague data}, issn = {0020-0255}, doi = {https://doi.org/10.1016/j.ins.2016.08.090}, url = {http://www.sciencedirect.com/science/article/pii/S0020025516306715}, author = {Jos{\'e} Otero and Luis Junco and Rosario Su{\'a}rez and Ana Palacios and In{\'e}s Couso and Luciano S{\'a}nchez} } @article {PALACIOS201210212, title = {Eliciting a human understandable model of ice adhesion strength for rotor blade leading edge materials from uncertain experimental data}, journal = {Expert Systems with Applications}, volume = {39}, number = {11}, year = {2012}, pages = {10212 - 10225}, abstract = {The published ice adhesion performance data of novel {\textquotedblleft}ice-phobic{\textquotedblright} coatings varies significantly, and there are not reliable models of the properties of the different coatings that help the designer to choose the most appropriate material. In this paper it is proposed not to use analytical models but to learn instead a rule-based system from experimental data. The presented methodology increases the level of post-processing interpretation accuracy of experimental data obtained during the evaluation of ice-phobic materials for rotorcraft applications. Key to the success of this model is a possibilistic representation of the uncertainty in the data, combined with a fuzzy fitness-based genetic algorithm that is capable to elicit a suitable set of rules on the basis of incomplete and imprecise information.}, keywords = {fuzzy rule-based classifiers, Genetic Fuzzy Systems, Ice-phobic materials, Isotropic materials, Shear adhesion strength, vague data}, issn = {0957-4174}, doi = {https://doi.org/10.1016/j.eswa.2012.02.155}, url = {http://www.sciencedirect.com/science/article/pii/S0957417412004186}, author = {Ana M. Palacios and Jos{\'e} L. Palacios and Luciano S{\'a}nchez} } @article {VILLAR2009250, title = {Taximeter verification using imprecise data from GPS}, journal = {Engineering Applications of Artificial Intelligence}, volume = {22}, number = {2}, year = {2009}, pages = {250 - 260}, abstract = {Until recently, local governments in Spain were using machines with rolling cylinders for testing and verification of taximeters. However, the tyres condition can lead to errors in the process and the mechanical construction of the test equipment is not compatible with certain vehicles. Thus, a new measurement device should be designed. In our opinion, the verification of a taximeter will not be reliable unless measurements taken on an actual taxi run are used. Global positioning system (GPS) sensors are intuitively well suited for this process, because they provide the position and the speed with independence from those car devices that are under test. Nevertheless, since GPS measurements are inherently imprecise, GPS-based sensors are difficult to homologate. In this paper we will show how these legal problems can be solved. We propose a method for computing an upper bound of the length of the trajectory, taking into account the vagueness of the GPS data. The uncertainty in the GPS data will be modelled by fuzzy techniques. The upper bound will be computed using a multiobjective evolutionary algorithm. The accuracy of the measurements will be improved further by combining it with restrictions based on the dynamic behavior of the vehicles.}, keywords = {fuzzy fitness function, Genetic Fuzzy Systems, GPS, Metrology, vague data}, issn = {0952-1976}, doi = {https://doi.org/10.1016/j.engappai.2008.07.002}, url = {http://www.sciencedirect.com/science/article/pii/S0952197608001267}, author = {Jos{\'e} Villar and Adolfo Otero and Jos{\'e} Otero and Luciano S{\'a}nchez} } @article {SANCHEZ2008607, title = {Mutual information-based feature selection and partition design in fuzzy rule-based classifiers from vague data}, journal = {International Journal of Approximate Reasoning}, volume = {49}, number = {3}, year = {2008}, pages = {607 - 622}, abstract = {Algorithms for preprocessing databases with incomplete and imprecise data are seldom studied. For the most part, we lack numerical tools to quantify the mutual information between fuzzy random variables. Therefore, these algorithms (discretization, instance selection, feature selection, etc.) have to use crisp estimations of the interdependency between continuous variables, whose application to vague datasets is arguable. In particular, when we select features for being used in fuzzy rule-based classifiers, we often use a mutual information-based ranking of the relevance of inputs. But, either with crisp or fuzzy data, fuzzy rule-based systems route the input through a fuzzification interface. The fuzzification process may alter this ranking, as the partition of the input data does not need to be optimal. In our opinion, to discover the most important variables for a fuzzy rule-based system, we want to compute the mutual information between the fuzzified variables, and we should not assume that the ranking between the crisp variables is the best one. In this paper we address these problems, and propose an extended definition of the mutual information between two fuzzified continuous variables. We also introduce a numerical algorithm for estimating the mutual information from a sample of vague data. We will show that this estimation can be included in a feature selection algorithm, and also that, in combination with a genetic optimization, the same definition can be used to obtain the most informative fuzzy partition for the data. Both applications will be exemplified with the help of some benchmark problems.}, keywords = {feature selection, Fuzzy fitness, Genetic Fuzzy Systems, vague data}, issn = {0888-613X}, doi = {https://doi.org/10.1016/j.ijar.2008.06.005}, url = {http://www.sciencedirect.com/science/article/pii/S0888613X08001102}, author = {Luciano S{\'a}nchez and M. Rosario Su{\'a}rez and J.R. Villar and In{\'e}s Couso} }