Recent advances in interval type-2 fuzzy systems. (Q2428182)

This book describes, in a synthetic and comprehensive manner, new methods for building intelligent systems making use of a higher-order fuzzy logic called type-2 fuzzy logic. Combining type-2 fuzzy logic with traditional soft-computing (SC) techniques, this book can be also used as a reference directory for applying type-2 fuzzy logic for solving problems in pattern recognition, intelligent control, intelligent manufacturing, robotics, and automation. Chapter 1 offers a brief introduction to the potential use of type-2 fuzzy logic in different real-world publications. Chapter 2 (Type-2 fuzzy logic systems) describes the basic concepts, notations, type-1 fuzzy logic and its generalization to type-2 fuzzy logic. More precisely, type-2 fuzzy logic enables the management of uncertainty for the membership functions, too, unlike the type-1 membership functions which are considered to be fixed and not uncertain. A formal definition of a type-2 fuzzy set \(\tilde{A}\) is characterized by the following membership function: \[ \tilde{a} = \{((x, u), \mu_{\tilde{A}}(x, u)) \mid \forall x\in X,\forall u\in J_x \subseteq [0, 1]\}, \] in which \(0 \leq \mu_{\tilde{A}}(x, u) \leq 1\), \(J_x\subseteq [0, 1]\) represents the primary membership of \(x\), and \(\mu_{\tilde{A}}(x, u)\) is a type-1 fuzzy set known as the secondary set. Hence, a type-2 membership grade can be any subset in \([0, 1]\) i.e., the primary membership, and to each primary membership there is associated a secondary membership (which is also in \([0, 1]\)) that defines the possibilities of appurtenance for the primary membership function. Type-2 fuzzy logic systems are useful in circumstances where it is difficult to determine an exact membership function, and there exist measurement uncertainties. Chapter 3 (Bio-inspired optimization methods) briefly overviews the basic concepts of bio-inspired optimization methods, particularly swarm optimization, genetic algorithms, and ant colony optimization. Chapter 4 (Overview of genetic algorithms applied in the optimization of type-2 fuzzy systems) shows the diversity of applications using genetic algorithms for automating the design process of type-2 fuzzy system optimization. Chapter 5 (Particle swarm optimization in the design of type-2 fuzzy systems) provides a representative review of works on the optimization of type-2 fuzzy systems using different kinds of particle swarm optimization algorithms, in order to illustrate the advantages of this kind of approach. Chapter 6 (Ant colony optimization algorithms for the design of type-2 fuzzy systems) gives similar information as Chapters 4 and 5, but the type-2 fuzzy systems are optimized with ant colony algorithms. Chapter 7 (Other methods for optimization of type-2 fuzzy systems) describes other methods for the optimization of type-2 fuzzy systems using different kinds of algorithms which are distinct from those presented in Chapters 4, 5, and 6, i.e., different from genetic algorithms, swarm optimization algorithms, and ant colony algorithms. These new methods illustrate the advantages of using specialized and adequate optimization techniques for automating the design process or parameters of type-2 fuzzy systems. Chapter 8 (Simulation results illustrating the optimization) describes the optimization of the membership function parameters for a type-2 fuzzy logic controller in order to find the optimal controller design of an autonomous wheeled mobile robot. The optimization method that was used is based on the chemical reaction paradigm, whose simulation results are shown to outperform other optimization methods utilized for the same control problem. Chapter 9 (Optimization of interval type-2 fuzzy systems for hardware implementation on FPGAs) presents a method for the design of a type-2 fuzzy logic controller (FLC-T2) and a type-1 fuzzy logic controller (FLC-T1) using genetic algorithms. The two controllers have been tested on different levels of uncertainty to regulate the speed in a direct current motor, the comparison being made in VHDL (very high description language) code and also with proportional integral differential (PID) controller. To evaluate the in performance of the three types of controllers, the t-student statistical test was used with the type-2 controller proved to be the best one for this problem. Chapter 10 provides a general synopsis on the field of type-2 fuzzy system optimization, enclosing also the possible future trends. The use of genetic algorithms, ant colony optimization, and particle swarm optimization of the type-2 fuzzy systems is pointed out, and a summary of the total number of papers published in the domain of type-2 fuzzy system optimization is also enclosed.