@article {PALACIOS201660, title = {An extension of the FURIA classification algorithm to low quality data through fuzzy rankings and its application to the early diagnosis of dyslexia}, journal = {Neurocomputing}, volume = {176}, year = {2016}, note = {Recent Advancements in Hybrid Artificial Intelligence Systems and its Application to Real-World Problems}, pages = {60 - 71}, abstract = {An early detection and reeducation of dyslexic children is critical for their integration in the classroom. Parents and instructors can help the psychologist to detect potential cases of dyslexia before the children׳s writing age. Artificial intelligence tools can also assist in this task. Dyslexia symptoms are detected with tests whose results may be vague or ambiguous, thus machine learning techniques for low quality data are advised. In particular, in this paper it is suggested that a new extension to vague datasets of the classification algorithm FURIA (Fuzzy Unordered Rule Induction Algorithm) has advantages over other approaches in both the computational effort during the learning stage and the linguistic quality of the induced classification rules. The new approach is benchmarked with different test problems and compared to other artificial intelligence tools for dyslexia diagnosis in the literature.}, keywords = {Dyslexia, FURIA, Fuzzy rule based classifiers, Low Quality Data}, issn = {0925-2312}, doi = {https://doi.org/10.1016/j.neucom.2014.11.088}, url = {http://www.sciencedirect.com/science/article/pii/S0925231215005706}, author = {Ana Palacios and Luciano S{\'a}nchez and In{\'e}s Couso and S{\'e}bastien Destercke} } @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} } @conference {6622418, title = {CI-LQD: A software tool for modeling and decision making with Low Quality Data}, booktitle = {2013 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)}, year = {2013}, month = {July}, pages = {1-8}, abstract = {The software tool CI-LQD (Computational Intelligence for Low Quality Data) is introduced in this paper. CI-LQD is an ongoing project that includes a lightweight open source software that has been designed with scientific and teaching purposes in mind. The main usefulness of the software is to automate the calculations involved in the statistical comparisons of different algorithms, with both numerical and graphical techniques, when the available information is interval-valued, fuzzy, incomplete or otherwise vague. A growing catalog of evolutionary algorithms for learning classifiers, models and association rules, along with their corresponding data conditioning and preprocessing techniques, is included. A demonstrative example of the tool is described that illustrates the capabilities of the software.}, keywords = {Algorithm design and analysis, Artificial intelligence, Association rules, CI-LQD, Computational intelligence, data conditioning, data mining, data preprocessing technique, Databases, Decision making, evolutionary algorithm, Evolutionary algorithms, evolutionary computation, graphical technique, learning classifier, lightweight open source software, Low Quality Data, Probability distribution, Software algorithms, software tool, software tools, statistical analysis, statistical comparison}, issn = {1098-7584}, doi = {10.1109/FUZZ-IEEE.2013.6622418}, author = {A. M. Palacios and L. S{\'a}nchez and I. Couso} } @conference {6622420, title = {Engine Health Monitoring for engine fleets using fuzzy radviz}, booktitle = {2013 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)}, year = {2013}, month = {July}, pages = {1-8}, abstract = {A new algorithm for assessment of Engine Health Monitoring (EHM) data in aircraft is proposed. The diagnostic tool quantifies step changes, shifts and trends in EHM data by means of a transformation that aggregates concurrent readings of EHM data into a single fuzzy state. A Genetic Fuzzy System is used to detect the occurance of a specific trend of interest in the sequence of states. The activation of the rules is represented in a 2D map by means of an extension of the Radviz visualization algorithm to fuzzy data.}, keywords = {2D map, aerospace engineering, aerospace engines, aircraft, Bandwidth, condition monitoring, data visualisation, diagnostic tool, EHM data, engine fleets, engine health monitoring, Engines, fault diagnosis, fuzzy data, fuzzy Radviz, fuzzy set theory, genetic algorithms, genetic fuzzy system, Genetic Fuzzy Systems, Low Quality Data, Maintenance engineering, Market research, mechanical engineering computing, Monitoring, Radviz visualization algorithm, rule activation, single fuzzy state, states sequence, Temperature measurement, Turbines}, issn = {1098-7584}, doi = {10.1109/FUZZ-IEEE.2013.6622420}, author = {A. Mart{\'\i}nez and L. S{\'a}nchez and I. Couso} } @article {PALACIOS2011841, title = {Linguistic cost-sensitive learning of genetic fuzzy classifiers for imprecise data}, journal = {International Journal of Approximate Reasoning}, volume = {52}, number = {6}, year = {2011}, pages = {841 - 862}, abstract = {Cost-sensitive classification is based on a set of weights defining the expected cost of misclassifying an object. In this paper, a Genetic Fuzzy Classifier, which is able to extract fuzzy rules from interval or fuzzy valued data, is extended to this type of classification. This extension consists in enclosing the estimation of the expected misclassification risk of a classifier, when assessed on low quality data, in an interval or a fuzzy number. A cooperative-competitive genetic algorithm searches for the knowledge base whose fitness is primal with respect to a precedence relation between the values of this interval or fuzzy valued risk. In addition to this, the numerical estimation of this risk depends on the entrywise product of cost and confusion matrices. These have been, in turn, generalized to vague data. The flexible assignment of values to the cost function is also tackled, owing to the fact that the use of linguistic terms in the definition of the misclassification cost is allowed.}, keywords = {Cost sensitive classification, genetic fuzzy system, Low Quality Data}, issn = {0888-613X}, doi = {https://doi.org/10.1016/j.ijar.2011.02.007}, url = {http://www.sciencedirect.com/science/article/pii/S0888613X11000545}, author = {Ana M. Palacios and Luciano S{\'a}nchez and In{\'e}s Couso} } @conference {6007647, title = {Using the Adaboost algorithm for extracting fuzzy rules from low quality data: Some preliminary results}, booktitle = {2011 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE 2011)}, year = {2011}, month = {June}, pages = {1263-1270}, abstract = {When the Adaboost algorithm is used for extracting fuzzy rules from data, each rule is regarded as a weak learner, and knowledge bases as assimilated to ensembles. In this paper we propose an extension of this framework for obtaining fuzzy rule-based classifiers from imprecise data. In the new approach, the mentioned search of the best rule at each iteration is carried out by a genetic algorithm with a fuzzy fitness function. The instances will be assigned fuzzy weights, however each fuzzy rule will be associated to a crisp number of votes.}, keywords = {Adaboost algorithm, Boosting, data handling, Electronic mail, fuzzy fitness function, fuzzy rule extraction, fuzzy rule-based classifiers, fuzzy set theory, Fuzzy systems, fuzzy weights, genetic algorithm, genetic algorithms, Genetic Fuzzy Systems, knowledge based systems, knowledge bases, learning (artificial intelligence), Low Quality Data, Merging, Optimization, pattern classification, Training}, issn = {1098-7584}, doi = {10.1109/FUZZY.2011.6007647}, author = {A. M. Palacios and L. S{\'a}nchez and I. Couso} } @conference {4295659, title = {Learning Fuzzy Linguistic Models from Low Quality Data by Genetic Algorithms}, booktitle = {2007 IEEE International Fuzzy Systems Conference}, year = {2007}, month = {July}, pages = {1-6}, abstract = {Incremental rule base learning techniques can be used to learn models and classifiers from interval or fuzzy-valued data. These algorithms are efficient when the observation error is small. This paper is about datasets with medium to high discrepancies between the observed and the actual values of the variables, such as those containing missing values and coarsely discretized data. We will show that the quality of the iterative learning degrades in this kind of problems, and that it does not make full use of all the available information. As an alternative, we propose a new implementation of a mutiobjective Michigan-like algorithm, where each individual in the population codifies one rule and the individuals in the Pareto front form the knowledge base.}, keywords = {Degradation, Fuzzy sets, Fuzzy systems, genetic algorithms, Global Positioning System, incremental rule base learning techniques, Iterative algorithms, iterative learning degrades, knowledge based systems, learning (artificial intelligence), learning fuzzy linguistic models, Low Quality Data, Noise measurement, Pareto front form, Pareto optimisation, Position measurement, Stochastic resonance, Uncertainty}, issn = {1098-7584}, doi = {10.1109/FUZZY.2007.4295659}, author = {L. S{\'a}nchez and J. Otero} }