Ernesto Araujo

Particle swarm optimization (PSO) applied to fuzzy modeling in a thermal-vacuum system

A nonlinear identification approach based on particle swarm optimization (PSO) and Takagi-Sugeno (T-S) fuzzy model for describing dynamical behavior of a thermal-vacuum system is proposed in this paper. Identification of nonlinear systems is an important problem in engineering among what fuzzy models have received particular attention due to their potentialities to approximate nonlinear behavior. Meanwhile PSO is proposed as a method for optimizing the premise part of production rules, least mean squares technique is employed for consequent part of production rules of a T-S fuzzy model. Experimental application using a thermal-vacuum system, used for space environmental emulation and satellite qualification, is analyzed. Numerical results indicate that the PSO succeeded in constructing a T-S fuzzy model for nonlinear identification in this particular application.

Improved Takagi-Sugeno fuzzy approach

In this paper Takagi-Sugeno fuzzy approach in analyzed under the fuzzy mapping perspective. Although similar to classical Takagi-Sugeno fuzzy approach in structure, this rule based system differs when employing a subnormal fuzzy mapping instead of using a normalized one. This approach might be considered to be a generalization of traditional Takagi-Sugeno approach to treat uncertainty in mapping procedure. It carries the ability of yielding a completely different input-output mapping by only introducing a new degree of freedom in parameters of fuzzy system design. Additionally, it might be considered to be a generalization of traditional Takagi-Sugeno approach to treat uncertainty, imprecision, vagueness and partial truth in mapping procedure. The proposed approach may be applied for finding out fuzzy models, designing fuzzy controllers, and decision-making process, as well. A zero-order Takagi-Sugeno model is employed to exemplify this nonzero mapping perspective.

Tridimensional fuzzy pain assessment

A tridimensional fuzzy pain assessment for representing professional, social, and sexual aspects concerned to the fifth vital sign of medical condition is proposed in this paper. According to the 3D fuzzy pain assessment herein, pain is not only caused by activity in nociceptive information in the brain. The proposed approach embodies such sensorial information simultaneously that contextualize it within cultural aspects that permeate the human life. This paper extends both previous unidimensional fuzzy pain intensity scale and the accepted professional-social-sexual pain assessment to fuzzy inference systems. The fuzzy professional-social-sexual pain assessment is able to represent the inherent physiological, psychological characteristics by taking into account the emotional, complex perceptual, subjective, and personal phenomenon involving all domains of an individual meanwhile can deal with cultural mechanisms within individual life experience. According to the proposed approach, not only fuzzy set theory but fuzzy systems can also direct and immediately improve medicine and healthcare in general, and pain assessment, in particular, in a subjective and multi-dimensional model.

Fuzzy breast cancer risk assessment

A breast cancer risk assessment based on fuzzy set theory and fuzzy logic is proposed in this paper. The proposed fuzzy breast cancer system maps two controlled and two non-controlled input variables into the risk of breast cancer occurrence. Such an approach covers the age, menopause, simplified fuzzy body mass index (FBMI), and the existence of hormone replacement as input linguistic variable. The risk of a woman developing breast cancer is the outcome of the proposed fuzzy breast cancer risk analysis. The resulting fuzzy breast cancer diagnostic decision system for helping support to evaluate patients with such a clinical condition is an alternative to support healthcare professionals in such a complex health diagnosis.

Unidimensional fuzzy pain intensity scale

A fuzzy pain scale for representing subjectivity and emotionality related to the fifth vital sign of medical condition is proposed in this paper. The classic intensity rating scales are inherently crisp sets. The medical and healthcare community does not realize that since the concept of fuzzy sets does not range all fields of knowledge yet. This paper extends the accepted international classic pain intensity rating scales to fuzzy set theory obtaining the fuzzy visual analog scale (FVAS), fuzzy numerical rating scale (FNRS), fuzzy qualitative pain scale (FQPS), and fuzzy face pain scale (FFPS). These fuzzy pain intensity scales take into account positive characteristics concerning classic pain intensity scales meanwhile represent the inherent imprecision, uncertainty and vagueness presented in the pain report and assessment. The proposed approach demonstrates how fuzzy set theory may push forwards the boundaries of medicine and healthcare by proposing a novel approach in order to improve the human quality level.

Fuzzy goal-driven intelligent control for satellite environmental qualification

This paper reports on the application of Fuzzy Reference Gain-Scheduling Control (FRGS) to control a thermal-vacuum unit that emulates space environmental conditions for satellite and space device qualification. FRGS is a variation of fuzzy control that changes the controller gain surface in accordance to distinct operational conditions established by the reference (goal). This system allows to incorporate the experience of human operators by emulating human decision-making and reasoning, with the advantage of adaptation when parameters are adjusted on-line. The controller gain surface is adapted by modifying the shapes of the membership functions according to piecewise constant reference values. While the goal-driven adjustment is accomplished in a feedforward manner, feedback control technique is used to guarantee dynamical response. The experimental response obtained in the application to the real system has shown the effectiveness and flexibility of this control approach for such a nonlinear system.

Particle swarm optimization with turbulence (PSOT) applied to thermal-vacuum modelling

Particle Swarm Optimization with Turbulence (PSOT) is, in this paper, applied to find out fuzzy models to represent dynamic behavior of space systems that lie underneath the space qualification process. In optimization area, each minimal improvement in results may represents a maximal, precious meaning and PSOT improve the performance of the established Particle Swarm Optimization (PSO) by introducing a slight variation, which simulates the action of an atmosphere turbulence to escape from local minima. This paper trades off the results of original PSO presented in a previous paper and PSOT both intertwined with Takagi-Sugeno (TS) fuzzy modeling dealing with experimental results of a thermal-vacuum system. Particle Swarm Optimization with turbulence has demonstrated to be a good alternative by taking into account the velocity of convergence to better solution and the total optimization time in generating dynamical models to the proposed system.

Metaheuristic search procedure based on fuzzy graph for p-facility problems

A metaheuristic search procedure modified by fuzzy logic and fuzzy set theory for solving p-facility location problems is proposed in this paper. Known as p-median problem, as well, the objective is to find p centers (locations) in a network in order to minimize (maximize) the average distance between demand nodes and their medians. The proposed approach employs Greedy Randomized Adaptive Search Procedure (GRASP) modified by grading the distances from locations weighted by membership functions or fuzzy rules. In so doing, a novel approach named Fuzzy Greedy Randomized Adaptive Search Procedure (FUGRASP) is presented. In order to verify the feasibility of the proposed method, p centers are computed to minimize the average distances among cities according to their respective air-traffic importance.

Fuzzy eye model

A fuzzy eye model to represent how pupils modifies their characteristic accordingly to the environment or to the context changes is proposed in this paper. In order to carry this adaptation out the Fuzzy Reference Gain-Scheduling (FRGS) approach is employed. The shape and size of pupils are related to support and core of membership functions. Since shape and size of pupils adapt to external signals this fuzzy eye model modify the membership function accordingly to an exogenous signal, as well. This proposed artificial eye model is able to be used in applications such as robotics, industrial systems, surveillance, only to mention few examples. Easy to be implemented both in software and in hardware this model can represent a distinct paradigm in diverse fields of knowledge.

Fuzzy chest pain assessment for unstable angina based on Braunwald symptomatic and obesity clinical conditions

A fuzzy medical diagnostic decision system for helping support to evaluate patients with anginal chest pain and obesity clinical condition is proposed in this paper. Such an approach is based on the Braunwald symptomatic classification, the fuzzy set theory and fuzzy logic, and a risk obesity factor determined by a simplified Fuzzy Body Mass Index (FBMI). The fuzzy Braunwald symptomatic classification intertwined with the fuzzy obesity risk factor overwhelm the current rapid access chest pain clinic approaches that do not discriminate the obesity comorbidity or takes into account the subjectiveness, uncertainty, imprecision, and vagueness concerning such a clinical health condition. The resulting fuzzy obesity-based Braunwald symptomatic chest pain assessment is an alternative to support healthcare professionals in primary health care for patients with anginal chest pain worsened by the obesity clinical condition.