New Medical Diagnosis Models Based on Generalized Type-2 Fuzzy Logic


Book Description

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.




Type-3 Fuzzy Logic in Intelligent Control


Book Description

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




New Perspectives on Hybrid Intelligent System Design based on Fuzzy Logic, Neural Networks and Metaheuristics


Book Description

In this book, recent developments on fuzzy logic, neural networks and optimization algorithms, as well as their hybrid combinations, are presented. In addition, the above-mentioned methods are applied to areas such as, intelligent control and robotics, pattern recognition, medical diagnosis, time series prediction and optimization of complex problems. The book contains a collection of papers focused on hybrid intelligent systems based on soft computing techniques. There are some papers with the main theme of type-1 and type-2 fuzzy logic, which basically consists of papers that propose new concepts and algorithms based on type-1 and type-2 fuzzy logic and their applications. There also some papers that offer theoretical concepts and applications of meta-heuristics in different areas. Another group of papers describe diverse applications of fuzzy logic, neural networks and hybrid intelligent systems in medical problems. There are also some papers that present theory and practice of neural networks in different areas of application. In addition, there are papers that present theory and practice of optimization and evolutionary algorithms in different areas of application. Finally, there are some papers describing applications of fuzzy logic, neural networks and meta-heuristics in pattern recognition and classification problems.










Soft Computing for Data Analytics, Classification Model, and Control


Book Description

This book presents a set of soft computing approaches and their application in data analytics, classification model, and control. The basics of fuzzy logic implementation for advanced hybrid fuzzy driven optimization methods has been covered in the book. The various soft computing techniques, including Fuzzy Logic, Rough Sets, Neutrosophic Sets, Type-2 Fuzzy logic, Neural Networks, Generative Adversarial Networks, and Evolutionary Computation have been discussed and they are used on variety of applications including data analytics, classification model, and control. The book is divided into two thematic parts. The first thematic section covers the various soft computing approaches for text classification and data analysis, while the second section focuses on the fuzzy driven optimization methods for the control systems. The chapters has been written and edited by active researchers, which cover hypotheses and practical considerations; provide insights into the design of hybrid algorithms for applications in data analytics, classification model, and engineering control.




Nature-inspired Optimization of Type-2 Fuzzy Neural Hybrid Models for Classification in Medical Diagnosis


Book Description

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.







Fuzzy Logic-Based Software Systems


Book Description

This book aims to provide information about significant advances of Fuzzy Logic in software systems to researchers, scientists, educators, students, software engineers and developers. In particular, this book explains how Fuzzy Logic, can be used in software systems to automatically predict, model, decide, diagnose, recommend etc.. In more details, Fuzzy Logic is an artificial intelligent technique that is ideal for successfully addressing, , the uncertainty, imprecision and vagueness that exist in many diverse scientific and technological areas. It was introduced by Lotfi A. Zadeh of the University of California at Berkeley, as a methodology for computing with words. This ability of Fuzzy Logic allows the representation of imprecise and vague data in a more realistic way. Therefore, Fuzzy Logic-based systems can simulate the human reasoning and decision-making processes, addressing the human subjectivity. Fuzzy Logic-based software systems are referred to any software that concerns an automated program or process that is used in everyday life, like heating or air-conditioning system, or in the scientific world, like a medical diagnostic system, which uses Fuzzy Logic in order to perform reasoning. A Fuzzy Logic-based system consists of three basic modules: Fuzzifier, Inference Engine and Defuzzifier. The Fuzzifier accepts as input numerical data and assigns them to fuzzy sets with some degree of membership, converting crisp data to fuzzy sets. The Inference Engine applies fuzzy rules over the defined fuzzy sets and produces outputs based on linguistic information. The Defuzzifier, converts fuzzy values into crisp values. The use of Fuzzy Logic in software systems constitutes a compelling and active research area in recent years, especially due to the increased interest in artificial intelligence. In the view of the above, this book presents thoroughly the Fuzzy Logic theory and the structure and operation of a Fuzzy Logic-based system. It also explains the role of Fuzzy Logic in artificial intelligence and smart applications, presenting how it can improve the efficiency and effectiveness of automatic processes and tasks. Furthermore, the book describes techniques of artificial intelligence with which the fuzzy logic is combined and how. Furthermore, this book presents several Fuzzy Logic-based software systems in the discipline of medicine, education, decision making and recommendation, natural language processing, automotive engineering and industry, heating, ventilation and air-conditioning, navigation, scheduling, network traffic and security. Thereby, this book can provide deep insights and valuable information not only to readers of computer science-related disciplines, but also to readers, who come from a variety of disciplines and are interesting in systems that perform tasks related to their discipline, in a more efficient way.




Hybrid Intelligent Systems in Control, Pattern Recognition and Medicine


Book Description

This book describes the latest advances in fuzzy logic, neural networks and optimization algorithms, as well as their hybrid combinations, and their applications in areas such as: intelligent control and robotics, pattern recognition, medical diagnosis, time series prediction, and optimization of complex problems. The book is divided into five main parts. The first part proposes new concepts and algorithms based on type-1 and type-2 fuzzy logic and their applications; the second explores new concepts and algorithms in neural networks and fuzzy logic applied to recognition. The third part examines the theory and practice of meta-heuristics in various areas of application, while the fourth highlights diverse applications of fuzzy logic, neural networks and hybrid intelligent systems in medical contexts. Finally, the fifth part focuses on applications of fuzzy logic, neural networks and meta-heuristics to robotics problems.