Decision making with imprecise parameters

ArticleinInternational Journal of Approximate Reasoning 51(8):869-882 · October 2010with34 Reads
DOI: 10.1016/j.ijar.2010.06.002 · Source: DBLP
We analyze the impact of imprecise parameters on performance of an uncertainty-modeling tool presented in this paper. In particular, we present a reliable and efficient uncertainty-modeling tool, which enables dynamic capturing of interval-valued clusters representations sets and functions using well-known pattern recognition and machine learning algorithms. We mainly deal with imprecise learning parameters in identifying uncertainty intervals of membership value distributions and imprecise functions. In the experiments, we use the proposed system as a decision support tool for a production line process. Simulation results indicate that in comparison to benchmark methods such as well-known type-1 and type-2 system modeling tools, and statistical machine-learning algorithms, proposed interval-valued imprecise system modeling tool is more robust with less error.
    • "In fact, one of the most recent construction methods of IVFSs is based on ignorance functions in order to model this uncertainty [11]. IVFSs have been applied successfully in classification tasks [48], approximate reasoning [9], decision making [14] and image processing [10], among others. Following on from the above, we propose a methodology in which we use IVFSs to model the linguistic labels of the system. "
    [Show abstract] [Hide abstract] ABSTRACT: Fuzzy Rule-Based Systems are appropriate tools to deal with classification problems due to their good properties. However, they can suffer a lack of system accuracy as a result of the uncertainty inherent in the definition of the membership functions and the limitation of the homogeneous distribution of the linguistic labels.The aim of the paper is to improve the performance of Fuzzy Rule-Based Classification Systems by means of the Theory of Interval-Valued Fuzzy Sets and a post-processing genetic tuning step. In order to build the Interval-Valued Fuzzy Sets we define a new function called weak ignorance for modeling the uncertainty associated with the definition of the membership functions. Next, we adapt the fuzzy partitions to the problem in an optimal way through a cooperative evolutionary tuning in which we handle both the degree of ignorance and the lateral position (based on the 2-tuples fuzzy linguistic representation) of the linguistic labels.The experimental study is carried out over a large collection of data-sets and it is supported by a statistical analysis. Our results show empirically that the use of our methodology outperforms the initial Fuzzy Rule-Based Classification System. The application of our cooperative tuning enhances the results provided by the use of the isolated tuning approaches and also improves the behavior of the genetic tuning based on the 3-tuples fuzzy linguistic representation.
    Full-text · Article · Sep 2011
  • [Show abstract] [Hide abstract] ABSTRACT: In this study, a new centroid type reduction method is proposed for piecewise linear interval type-2 fuzzy sets based on geometrical approach. The main idea behind the proposed method relies on the assumption that the part of footprint of uncertainty (FOU) of an interval type-2 fuzzy set (IT2FS) has a constant width where the centroid is searched. This constant width assumption provides a way to calculate the centroid of an IT2FS in closed form by using derivative based optimization without any need of iterations. When the related part of FOU is originally constant width, the proposed method finds the accurate centroid of an IT2FS; otherwise, an enhancement can be performed in the algorithm in order to minimize the error between the accurate and the calculated centroids. Moreover, only analytical formulas are used in the proposed method utilizing geometry. This eliminates the need of using discretization of an IT2FS for the type reduction process which in return naturally improves the accuracy and the computation time. The proposed method is compared with Enhanced Karnik–Mendel Iterative Procedure (EKMIP) in terms of the accuracy and the computation time on seven test fuzzy sets. The results show that the proposed method provides more accurate results with shorter computation time than EKMIP.
    Article · Nov 2013
  • [Show abstract] [Hide abstract] ABSTRACT: In this study, an exact analytical inversion procedure is presented for interval type-2 Takagi–Sugeno–Kang fuzzy logic systems (IT2 TSK FLSs) with closed form inference methods. In this inversion procedure, the inversion variable is needed to be defined by piecewise linear interval type-2 fuzzy sets (PWL IT2 FSs). This provides a way to define an IT2 TSK FLS in a form that is composed of several fuzzy subsystems with respect to the inversion variable. In the proposed procedure, the output definitions of fuzzy subsystems are derived in a unique parametric form in terms of the inversion variable by using parameters of linear definition of membership functions. By rearranging this definition with respect to the inversion variable; either a linear, quadratic or cubic equation is obtained depending on the types of the inference method and rule consequents of the IT2 TSK FLS. Since explicit analytical solutions are available for these types of equations, the exact inverse solution(s) of each fuzzy subsystem can easily be calculated. The inverse solution set of overall IT2 TSK FLS is obtained by composing the inverse solutions of all fuzzy subsystems. The exactness and feasibility of the proposed inversion procedure has been illustrated through simulation examples.
    Article · Dec 2015

Recommended publications

Discover more