A Dynamically Constrained Multiobjective Genetic Fuzzy System for Regression Problems

Abstract

In this paper, a multiobjective genetic fuzzy system (GFS) to learn the granularities of fuzzy partitions, tuning the membership functions (MFs), and learning the fuzzy rules is presented. It uses dynamic constraints, which enable three-parameter MF tuning to improve the accuracy while guaranteeing the transparency of fuzzy partitions. The fuzzy models (FMs) are initialized by a method that combines the benefits of Wang-Mendel (WM) and decision-tree algorithms. Thus, the initial FMs have less rules, rule conditions, and input variables than if WM initialization were to be used. Moreover, the fuzzy partitions of initial FMs are always transparent. Our approach is tested against recent multiobjective and monoobjective GFSs on six benchmark problems. It is concluded that the accuracy and interpretability of our FMs are always comparable or better than those in the comparative studies. Furthermore, on some benchmark problems, our approach clearly outperforms some comparative approaches. Suitability of our approach for higher dimensional problems is shown by studying three benchmark problems that have up to 21 input variables.

An evolutionary method to generate Mamdani rule-based systems with hedge algebra based semantics for regression problems

“…Tính dễ hiểu của FRBS rất khó hình thức hóa, vì vậy các nhà nghiên cứu thường tập trung vào một số đặc trưng của khái niệm này và đưa ra các ràng buộc để thỏa mãn những đặc trưng đó. Trong [11] các tác giả đưa ra một số đặc trưng: 1) sự rõ ràng của phân hoạch (số tập mờ, khả năng phân biệt giữa các tập mờ, phân hoạch có phủ toàn bộ vũ trụ); 2) độ phức tạp của hệ luật (số luật, chiều dài của luật).…”

A Multi-gene Genetic Programming Fuzzy Inference System for Regression Problems

“…As a GFS integrates a Fuzzy Inference System (FIS) and a Genetic Based Meta-Heuristic (GBMH), it provides fair accuracy and linguistic interpretability (FIS component) through the automatic learning of its parameters/rules (GBMH component). Works on GFSs applied to regression problems are mostly based on improving the Genetic Based Meta-Heuristic counterpart of GFSs by using Multi-Objective Evolutionary Algorithms [3,[7][8][9][10]. In general most of these works do not explore linguistic hedges and negation operators.…”

Fuzzy modeling system based on hybrid evolutionary approach

“…They provide a scheme to represent the knowledge in a way that resembles human communication and reasoning. Fuzzy systems have demonstrated their ability in several application fields, such as control problems [9][10][11], classification [12][13][14][15], regression [16,17], and general data mining problems [18,19] , due to their ability to handle uncertainty and imprecision and to describe the behavior of different complex systems without requiring a precise mathematical model. Design of fuzzy model or fuzzy model identification is the task of finding the parameters of fuzzy models so as to get the desired behavior.…”