Patricia Melin

In this book, a novel optimization method inspired by a paradigm from nature is introduced. The chemical reactions are used as a paradigm to propose an optimization method that simulates these natural processes. The proposed algorithm is described in detail and then a set of typical complex benchmark functions is used to evaluate the performance of the algorithm. Simulation results show that the proposed optimization algorithm can outperform other methods in a set of benchmark functions.This chemical reaction optimization paradigm is also applied to solve the tracking problem for the dynamic model of a unicycle mobile robot by integrating a kinematic and a torque controller based on fuzzy logic theory. Computer simulations are presented confirming that this optimization paradigm is able to outperform other optimization techniques applied to this particular robot application.

This book is intended to be a reference for scientists and engineers interested in applying type-3 fuzzy logic and fractal theory techniques in medical diagnosis. In this book, a new model based on type-3 fuzzy logic and fractal theory for applications in medical diagnosis is presented. The main idea is that a higher type and order of fuzzy logic can help in solving various diagnosis problems and find better results. In addition, fractal theory is also employed for enhancing medical diagnosis. In this regard, several hybrid intelligent methods are offered. In this book, the authors test the proposed methods using several medical diagnosis problems, like diagnosis of problems in the brain, hearth, lungs, and others. The authors can notice that when type-3 fuzzy systems are implemented to model the behavior of systems, the results in diagnosis are enhanced, because the management of uncertainty is better. For this reason, the authors consider in this book the proposed methods using type-3 fuzzy systems and fractal theory to improve the diagnosis in complex medical problems.

This book provides a new model for clustering, classification, and time series prediction by using artificial neural networks to computationally simulate the behavior of the cognitive functions of the brain is presented. This model focuses on the study of intelligent hybrid neural systems and their use in time series analysis and decision support systems. Therefore, through the development of eight case studies, multiple time series related to the following problems are analyzed: traffic accidents, air quality and multiple global indicators (energy consumption, birth rate, mortality rate, population growth, inflation, unemployment, sustainable development, and quality of life). The main contribution consists of a Generalized Type-2 fuzzy integration of multiple indicators (time series) using both supervised and unsupervised neural networks and a set of Type-1, Interval Type-2, and Generalized Type-2 fuzzy systems. The obtained results show the advantages of the proposed model of Generalized Type-2 fuzzy integration of multiple time series attributes. This book is intended to be a reference for scientists and engineers interested in applying type-2 fuzzy logic techniques for solving problems in classification and prediction. We consider that this book can also be used to get novel ideas for new lines of research, or to continue the lines of research proposed by the authors of the book.

This book focuses on the field of type-3 fuzzy logic for applications in time series prediction. The main idea is that a higher type and order of fuzzy logic can help in solving various prediction problems and find better results. In addition, neural networks and fractal theory are employed in enhancing prediction results. In this regard, several hybrid intelligent methods are offered. In this book we test the proposed methods using several prediction problems, like predicting COVID-19 and the stock market. We can notice that when Type-3 fuzzy systems are implemented to model the behavior of systems, the results in prediction are enhanced, because the management of uncertainty is better. For this reason, we consider in this book the proposed methods using type-3 fuzzy systems, neural networks and fractal theory to improve the prediction behavior of the complex nonlinear systems. This book is intended to be a reference for scientists and engineers interested in applying type-3 fuzzy logic techniques for solving complex prediction problems. This book can also be used as a reference for graduate courses like the following: soft computing, fuzzy logic, neural networks, bio-inspired algorithms, intelligent prediction, and similar ones. We consider that this book can also be used to get novel ideas for new lines of research, or to continue the lines of research proposed by the authors of the book.

This book focuses on the field of type-3 fuzzy logic, also considering metaheuristics for applications in the control area. The main idea is that these areas together can solve various control problems and find better results. In this book, we test the proposed method using several benchmark problems, such as the problem for filling a water tank and the problem for controlling the trajectory in an autonomous mobile robot. We notice that when interval type-3 fuzzy systems are implemented to model the behavior of the systems, the results in control show a better stabilization, because the management of uncertainty is better. For this reason, we consider in this book the proposed method using type-3 fuzzy systems, fuzzy controllers, and metaheuristic algorithms to improve the control behavior of complex nonlinear plants. This book is intended to be a reference for scientists and engineers interested in applying type-3 fuzzy logic techniques for solving problems in intelligent control. We consider that this book can also be used to get novel ideas for new lines of research, or to continue the lines of research proposed by the authors of the book

This book focuses on the fields of neural networks, swarm optimization algorithms, clustering and fuzzy logic. This book describes a hybrid method with three different techniques of intelligence computation: neural networks, optimization algorithms and fuzzy logic. Within the neural network techniques, competitive neural networks (CNNs) are used, for the optimization algorithms technique, we used the fireworks algorithm (FWA), and in the area of fuzzy logic, the Type-1 Fuzzy Inference Systems (T1FIS) and the Interval Type-2 Fuzzy Inference Systems (IT2FIS) were used, with their variants of Mamdani and Sugeno type, respectively. FWA was adapted for data clustering with the goal to help of competitive neural network to find the optimal number of neurons. It is important to mention that two variants were applied to the FWA: dynamically adjust of parameters with Type-1 Fuzzy Logic (FFWA) as the first one and Interval Type-2 (F2FWA) as the second one. Subsequently, based on the outputs of the CNN and with the goal of classification data, we designed Type-1 and Interval Type-2 Fuzzy Inference Systems of Mamdani and Sugeno type. This book is intended to be a reference for scientists and engineers interested in applying a different metaheuristic or an artificial neural network in order to solve optimization and applied fuzzy logic techniques for solving problems in clustering and classification data. This book is also used as a reference for graduate courses like the following: soft computing, swarm optimization algorithms, clustering data, fuzzy classify and similar ones. We consider that this book can also be used to get novel ideas for new lines of research, new techniques of optimization or to continue the lines of the research proposed by the authors of the book.

This book briefly reviews the basic concepts of type-2 fuzzy systems and then describes the proposed definitions for interval type-3 fuzzy sets and relations, also interval type-3 inference and systems. The use of type-2 fuzzy systems has become widespread in the leading economy sectors, especially in industrial and application areas, such as services, health, defense, and so on. However, recently the use of interval type-3 fuzzy systems has been receiving increasing attention and some successful applications have been developed in the last year. These issues were taken into consideration for this book, as we did realize that there was a need to offer the main theoretical concepts of type-3 fuzzy logic, as well as methods to design, develop and implement the type-3 fuzzy systems. A review of basic concepts and their use in the design and implementation of interval type-3 fuzzy systems, which are relatively new models of uncertainty and imprecision, are presented. The main focus of thiswork is based on the basic reasons of the need for interval type-3 fuzzy systems in different areas of application. In addition, we describe methods for designing interval type-3 fuzzy systems and illustrate this with some examples and simulations.

This book briefly reviews the basic concepts of type-2 fuzzy systems and then describes the proposed definitions for interval type-3 fuzzy sets and relations, also interval type-3 inference and systems. The use of type-2 fuzzy systems has become widespread in the leading economy sectors, especially in industrial and application areas, such as services, health, defense, and so on. However, recently the use of interval type-3 fuzzy systems has been receiving increasing attention and some successful applications have been developed in the last year. These issues were taken into consideration for this book, as we did realize that there was a need to offer the main theoretical concepts of type-3 fuzzy logic, as well as methods to design, develop and implement the type-3 fuzzy systems. A review of basic concepts and their use in the design and implementation of interval type-3 fuzzy systems, which are relatively new models of uncertainty and imprecision, are presented. The main focus of thiswork is based on the basic reasons of the need for interval type-3 fuzzy systems in different areas of application. In addition, we describe methods for designing interval type-3 fuzzy systems and illustrate this with some examples and simulations.

This book describes the utilization of different soft computing techniques and their optimization for providing an accurate and efficient medical diagnosis. The proposed method provides a precise and timely diagnosis of the risk that a person has to develop a particular disease, but it can be adaptable to provide the diagnosis of different diseases. This book reflects the experimentation that was carried out, based on the different optimizations using bio-inspired algorithms (such as bird swarm algorithm, flower pollination algorithms, and others). In particular, the optimizations were carried out to design the fuzzy classifiers of the nocturnal blood pressure profile and heart rate level. In addition, to obtain the architecture that provides the best result, the neurons and the number of neurons per layers of the artificial neural networks used in the model are optimized. Furthermore, different tests were carried out with the complete optimized model. Another work that is presented in this book is the dynamic parameter adaptation of the bird swarm algorithm using fuzzy inference systems, with the aim of improving its performance. For this, different experiments are carried out, where mathematical functions and a monolithic neural network are optimized to compare the results obtained with the original algorithm. The book will be of interest for graduate students of engineering and medicine, as well as researchers and professors aiming at proposing and developing new intelligent models for medical diagnosis. In addition, it also will be of interest for people working on metaheuristic algorithms and their applications on medicine.

This book presents different experimental results as evidence of the good results obtained compared with respect to conventional approaches and literature references based on fuzzy logic. Nowadays, the evolution of intelligence systems for decision making has been reached considerable levels of success, as these systems are getting more intelligent and can be of great help to experts in decision making. One of the more important realms in decision making is the area of medical diagnosis, and many kinds of intelligence systems provide the expert good assistance to perform diagnosis; some of these methods are, for example, artificial neural networks (can be very powerful to find tendencies), support vector machines, that avoid overfitting problems, and statistical approaches (e.g., Bayesian). However, the present research is focused on one of the most relevant kinds of intelligent systems, which are the fuzzy systems. The main objective of the present work is the generation of fuzzy diagnosis systems that offer competitive classifiers to be applied in diagnosis systems. To generate these systems, we have proposed a methodology for the automatic design of classifiers and is focused in the Generalized Type-2 Fuzzy Logic, because the uncertainty handling can provide us with the robustness necessary to be competitive with other kinds of methods. In addition, different alternatives to the uncertainty modeling, rules-selection, and optimization have been explored. Besides, different experimental results are presented as evidence of the good results obtained when compared with respect to conventional approaches and literature references based on Fuzzy Logic.

This book is focused on the use of intelligent techniques, such as fuzzy logic, neural networks and bio-inspired algorithms, and their application in medical diagnosis. The main idea is that the proposed method may be able to adapt to medical diagnosis problems in different possible areas of the medicine and help to have an improvement in diagnosis accuracy considering a clinical monitoring of 24 hours or more of the patient.In this book, tests were made with different architectures proposed in the different modules of the proposed model. First, it was possible to obtain the architecture of the fuzzy classifiers for the level of blood pressure and for the pressure load, and these were optimized with the different bio-inspired algorithms (Genetic Algorithm and Chicken Swarm Optimization). Secondly, we tested with a local database of 300 patients and good results were obtained. It is worth mentioning that this book is an important part of the proposed generalmodel; for this reason, we consider that these modules have a good performance in a particular way, but it is advisable to perform more tests once the general model is completed.

These authors use soft computing techniques and fractal theory in this new approach to mathematical modeling, simulation and control of complexion-linear dynamical systems. First, a new fuzzy-fractal approach to automated mathematical modeling of non-linear dynamical systems is presented. It is illustrated with examples on the PROLOG programming language. Second, a new fuzzy-genetic approach to automated simulation of dynamical systems is presented. It is illustrated with examples in the MATLAB programming language. Third, a new method for model-based adaptive control using a neuro-fussy fractal approach is combined with the methods mentioned above. This method is illustrated with MATLAB. Finally, applications of these new methods are presented, in the areas such as biochemical processes, robotic systems, manufacturing, food industry and chemical processes.

This book presents an extension of the aggregation operator of the generalized interval type-2 Sugeno integral using generalized type-2 fuzzy logic. This extension enables it to handle higher levels of uncertainty when adding any number of sources and types of information in a wide variety of decision-making applications. The authors also demonstrate that the extended aggregation operator offers better performance than other traditional or extended operators. The book is a valuables reference resource for students and researchers working on theory and applications of fuzzy logic in various areas of application where decision making is performed under high levels of uncertainty, such as pattern recognition, time series prediction, intelligent control and manufacturing.

In this book, a methodology for parameter adaptation in meta-heuristic op-timization methods is proposed. This methodology is based on using met-rics about the population of the meta-heuristic methods, to decide through a fuzzy inference system the best parameter values that were carefully se-lected to be adjusted. With this modification of parameters we want to find a better model of the behavior of the optimization method, because with the modification of parameters, these will affect directly the way in which the global or local search are performed.Three different optimization methods were used to verify the improve-ment of the proposed methodology. In this case the optimization methods are: PSO (Particle Swarm Optimization), ACO (Ant Colony Optimization) and GSA (Gravitational Search Algorithm), where some parameters are se-lected to be dynamically adjusted, and these parameters have the most im-pact in the behavior of each optimization method.Simulation results show that the proposed methodology helps to each optimization method in obtaining better results than the results obtained by the original method without parameter adjustment.

In this book a new model for data classification was developed. This new model is based on the competitive neural network Learning Vector Quantization (LVQ) and type-2 fuzzy logic. This computational model consists of the hybridization of the aforementioned techniques, using a fuzzy logic system within the competitive layer of the LVQ network to determine the shortest distance between a centroid and an input vector. This new model is based on a modular LVQ architecture to further improve its performance on complex classification problems. It also implements a data-similarity process for preprocessing the datasets, in order to build dynamic architectures, having the classes with the highest degree of similarity in different modules. Some architectures were developed in order to work mainly with two datasets, an arrhythmia dataset (using ECG signals) for classifying 15 different types of arrhythmias, and a satellite images segments dataset used for classifying six different types ofsoil. Both datasets show interesting features that makes them interesting for testing new classification methods.

This book focuses on the fields of hybrid intelligent systems based on fuzzy systems, neural networks, bio-inspired algorithms and time series. This book describes the construction of ensembles of Interval Type-2 Fuzzy Neural Networks models and the optimization of their fuzzy integrators with bio-inspired algorithms for time series prediction. Interval type-2 and type-1 fuzzy systems are used to integrate the outputs of the Ensemble of Interval Type-2 Fuzzy Neural Network models. Genetic Algorithms and Particle Swarm Optimization are the Bio-Inspired algorithms used for the optimization of the fuzzy response integrators. The Mackey-Glass, Mexican Stock Exchange, Dow Jones and NASDAQ time series are used to test of performance of the proposed method. Prediction errors are evaluated by the following metrics: Mean Absolute Error, Mean Square Error, Root Mean Square Error, Mean Percentage Error and Mean Absolute Percentage Error. The proposed prediction model outperforms state of the art methods in predicting the particular time series considered in this work.

In this book, a new approach for diagnosis and risk evaluation of ar-terial hypertension is introduced. The new approach was implement-ed as a hybrid intelligent system combining modular neural net-works and fuzzy systems. The different responses of the hybrid system are combined using fuzzy logic. Finally, two genetic algo-rithms are used to perform the optimization of the modular neural networks parameters and fuzzy inference system parameters. The experimental results obtained using the proposed method on real pa-tient data show that when the optimization is used, the results can be better than without optimization. This book is intended to be a refer-ence for scientists and physicians interested in applying soft compu-ting techniques, such as neural networks, fuzzy logic and genetic algorithms, in medical diagnosis, but also in general to classification and pattern recognition and similar problems.

In this book four new methods are proposed. In the first method the generalized type-2 fuzzy logic is combined with the morphological gra-dient technique. The second method combines the general type-2 fuzzy systems (GT2 FSs) and the Sobel operator; in the third approach the me-thodology based on Sobel operator and GT2 FSs is improved to be applied on color images. In the fourth approach, we proposed a novel edge detec-tion method where, a digital image is converted a generalized type-2 fuzzy image. In this book it is also included a comparative study of type-1, inter-val type-2 and generalized type-2 fuzzy systems as tools to enhance edge detection in digital images when used in conjunction with the morphologi-cal gradient and the Sobel operator. The proposed generalized type-2 fuzzy edge detection methods were tested with benchmark images and synthetic images, in a grayscale and color format.Another contribution in this book is that the generalized type-2 fuzzy edge detector method is applied in the preprocessing phase of a face rec-ognition system; where the recognition system is based on a monolithic neural network. The aim of this part of the book is to show the advantage of using a generalized type-2 fuzzy edge detector in pattern recognition applications.The main goal of using generalized type-2 fuzzy logic in edge detec-tion applications is to provide them with the ability to handle uncertainty in processing real world images; otherwise, to demonstrate that a GT2 FS has a better performance than the edge detection methods based on type-1 and type-2 fuzzy logic systems.

In this book a neural network learning method with type-2 fuzzy weight adjustment is proposed. The mathematical analysis of the proposed learning method architecture and the adaptation of type-2 fuzzy weights are presented. The proposed method is based on research of recent methods that handle weight adaptation and especially fuzzy weights.The internal operation of the neuron is changed to work with two internal calculations for the activation function to obtain two results as outputs of the proposed method. Simulation results and a comparative study among monolithic neural networks, neural network with type-1 fuzzy weights and neural network with type-2 fuzzy weights are presented to illustrate the advantages of the proposed method.The proposed approach is based on recent methods that handle adaptation of weights using fuzzy logic of type-1 and type-2. The proposed approach is applied to a cases of prediction for the Mackey-Glass (for ô=17) and Dow-Jones time series, and recognition of person with iris biometric measure. In some experiments, noise was applied in different levels to the test data of the Mackey-Glass time series for showing that the type-2 fuzzy backpropagation approach obtains better behavior and tolerance to noise than the other methods.The optimization algorithms that were used are the genetic algorithm and the particle swarm optimization algorithm and the purpose of applying these methods was to find the optimal type-2 fuzzy inference systems for the neural network with type-2 fuzzy weights that permit to obtain the lowest prediction error.

In this book, a new method for hybrid intelligent systems is proposed. The proposed method is based on a granular computing approach applied in two levels. The techniques used and combined in the proposed method are modular neural networks (MNNs) with a Granular Computing (GrC) approach, thus resulting in a new concept of MNNs; modular granular neural networks (MGNNs). In addition fuzzy logic (FL) and hierarchical genetic algorithms (HGAs) are techniques used in this research work to improve results. These techniques are chosen because in other works have demonstrated to be a good option, and in the case of MNNs and HGAs, these techniques allow to improve the results obtained than with their conventional versions; respectively artificial neural networks and genetic algorithms.