Dusko Kalenatic

Multi-period Mixed Production Planning with uncertain demands: Fuzzy and interval fuzzy sets approach

This paper shows a general model of a Mixed Production Planning problem with fuzzy demands. The main focus is the development of a model for Production Planning using fuzzy sets in order to use classical mathematical programming techniques to reach an optimal solution over a multiple criteria context. The classical Fuzzy Linear Programming model namely the Soft Constraints Model is used to involve flexibility in the problem. Moreover, an Interval Fuzzy Set approach is used to involve uncertainty in the problem.

Missing data imputation in multivariate data by evolutionary algorithms

This paper presents a proposal based on an evolutionary algorithm to impute missing observations in multivariate data. A genetic algorithm based on the minimization of an error function derived from their covariance matrix and vector of means is presented. All methodological aspects of the genetic structure are presented. An extended explanation of the design of the fitness function is provided. An application example is solved by the proposed method.

An evolutionary approach for imputing missing data in time series

This paper presents a proposal based on an evolutionary algorithm for imputing missing observations in time series. A genetic algorithm based on the minimization of an error function derived from their autocorrelation function, mean, and variance is presented. All methodological aspects of the genetic structure are presented. An extended description of the design of the fitness function is provided. Four application examples are provided and solved by using the proposed method.

Scalarization of type-1 fuzzy Markov chains

This paper presents a method to transform Fuzzy Markov chains into CrispMarkov chains by means of an equivalence matrix derived from the concept of Scalar cardinality of a fuzzy set. This proposal is a linear transformation of the fuzzy space into a probability space. In this paper, a finite-state Fuzzy Markov Chain is transformed into a crisp Markov chain by a linear operator. It is a projection of the fuzzy space into a probability space which allows to compare them one another.

A neuro-evolutive interval type-2 TSK fuzzy system for volatile weather forecasting

This paper presents an hybrid Neuro-Evolutive algorithm for a Firstorder Interval Type-2 TSK Fuzzy Logic System applied to a volatile weather forecasting case. All results are tested by statistical tests asGoldfeld-Quant, Ljung-Box, ARCH, Runs, Turning Points, Bayesian, Akaike and Hannan-Quin criteria. Some methodological aspects about a hybrid implementation among ANFIS, an Evolutive Optimizer and a First order Interval Type-2 TSK FLS are presented. The selected type-reduction algorithm is the IASCO algorithm proposed by Melgarejo in [1] since it presents better computing properties than other algorithms.

Modeling the synergy level in a vertical collaborative supply chain through the IMP interaction model and DEA framework

This work develops a mathematical programming model that characterizes the main variables present in the interaction dynamics of each agent in a collaborative vertical logistical system, such as a supply chain, and measures the synergy level of such system. The model is based on the interaction model developed by the IMP (Industrial Marketing and Purchasing) group and also on the DEA (Data Envelopment Analysis) framework. The basics of these two approaches allow modeling of the characteristics of an agent as well as the collaborative relationships with other agents within the chain. The model was validated using information of supply chain of leather and its products, classified by DANE (Departamento Nacional de Estadistica—Colombia) as the sector CIIU323.

A Simulation Study on Fuzzy Markov Chains

This paper presents a simulation study on Fuzzy Markov chains to identify some characteristics about their behavior, based on matrix analysis. Through experimental evidence it is observed that most of fuzzy Markov chains does not have an ergodic behavior. So, several sizes of Markov chains are simulated and some statistics are collected.

Missing Data Imputation in Time Series by Evolutionary Algorithms

This paper presents a proposal based in an Evolutionary algorithm for imputing missing observations in Time Series. A genetic algorithm based on the minimization of an error function derived from their autocorrelation function, mean and variance, is presented. All methodological aspects of the genetic structure are presented. An extended explanation of the design of the Fitness Function is provided. Four application examples are provided and solved by the proposed method.

Interval type-2 fuzzy markov chains: type reduction

This paper shows an application of Type-reduction algorithms for computing the steady state of an Interval Type-2 Fuzzy Markov Chain (IT2FM). The IT2FM approach is an extension of the scope of a Type-1 fuzzy markov chain (T1FM) that allows to embed several Type-1 fuzzy sets (T1FS) inside its Footprint of Uncertainty. In this way, a finite state Fuzzy Markov Chain process is defined on an Interval Type-2 Fuzzy environment, finding their limiting properties and its Type-reduced behavior. To do so, two examples are provided.

An iterative algorithm for fuzzy mixed production planning based on the cumulative membership function

This paper shows an application of a novel algorithm for Fuzzy Linear Programming (FLP) problems with both fuzzy technological coefficients and constraints, which deals with any kind of fuzzy membership functions for technological parameters and fuzzy linear constraints.The presented approach uses an iterative algorithm which finds stable solutions to problems with fuzzy parameter sinboth sides of an FLP problem. The algorithm is based on the soft constraints method proposed by Zimmermann combined with an iterative procedure which gets a single optimal solution.This paper shows an application of a novel algorithm for Fuzzy Linear Programming (FLP) problems with both fuzzy technological coefficients and constraints, which deals with any kind of fuzzy membership functions for technological parameters and fuzzy linear constraints. The presented approach uses an iterative algorithm which finds stable solutions to problems with fuzzy parameter sinboth sides of an FLP problem. The algorithm is based on the soft constraints method proposed by Zimmermann combined with an iterative procedure which gets a single optimal solution.