Conference Paper

A Minimum-Risk Genetic Fuzzy Classifier Based on Low Quality Data.

DOI: 10.1007/978-3-642-02319-4_79 Conference: Hybrid Artificial Intelligence Systems, 4th International Conference, HAIS 2009, Salamanca, Spain, June 10-12, 2009. Proceedings
Source: DBLP

ABSTRACT Minimum risk classification problems use a matrix of weights for defining the cost of misclassifying an object. In this paper
we extend a simple genetic fuzzy system (GFS) to this case. In addition, our method is able to learn minimum risk fuzzy rules
from low quality data. We include a comprehensive description of the new algorithm and discuss some issues about its fuzzy-valued
fitness function. A synthetic problem, plus two real-world datasets, are used to evaluate our proposal.

  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: To configure a proficient athletics team, coaches combine their expertise with the analysis of data collected during training sessions and competitions. This data and knowledge are vague, thus fuzzy logic is appropriate for designing a decision model. In this paper we will use a Genetic Fuzzy System for designing a model that can help the trainer to assess the performance of a given athlete in the future, given a combination of historical data and expert knowledge. This decision model has interest as a real-world application of GFSs, but it also involves novel kinds of data, whose study is a current trend in machine learning. Examples of such data include subjective perceptions of mistakes of the athletes, the reconciliation of different measurements taken by different observers, and interval-valued training data. We will use a possibilistic representation of these categories of information, in combination with an extension principle-based reasoning method, and finally show that the quality of a GFS which is based in these last principles improves the results of the original formulation of the same algorithm.
    Intelligent Data Engineering and Automated Learning - IDEAL 2009, 10th International Conference, Burgos, Spain, September 23-26, 2009. Proceedings; 01/2009
  • Source
    [Show abstract] [Hide abstract]
    ABSTRACT: When there is a substantial difference between the number of cases of the majority and minority classes, minimum error-based classification systems tend to overlook these last instances. This can be corrected either by preprocessing the dataset or by altering the objective function of the classifier. In this paper we analyze the first approach, in the context of genetic fuzzy systems (GFS), and in particular of those that can operate with imprecisely observed and low quality data. We will analyze the different preprocessing mechanisms of imbalanced datasets and will show the necessity of extending these for solving those problems where the data is both imprecise and im-balanced. In addition, we include a comprehensive description of a new algorithm, able to preprocess imprecise imbalanced datasets. Several real-world datasets are used to evaluate the proposal.
    FUZZ-IEEE 2010, IEEE International Conference on Fuzzy Systems, Barcelona, Spain, 18-23 July, 2010, Proceedings; 01/2010
  • Source
    Journal of multiple-valued logic and soft computing 01/2011; 17:207-228. · 0.67 Impact Factor

Full-text (2 Sources)

Available from
May 23, 2014