Название: New Perspectives on Hybrid Intelligent System Design based on Fuzzy Logic, Neural Networks and Metaheuristics
Автор: Oscar Castillo, Patricia Melin
Издательство: Springer
Серия: Studies in Computational Intelligence
Год: 2022
Страниц: 471
Язык: английский
Формат: pdf (true), epub
Размер: 56.9 MB

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.

Time series is an ordered sequence of data or observations measured over time. One of the most important utilities of time series is its analysis for the prediction of the measured variable. In organizations it is very useful to consider short- and medium-term predictions, for example to find what would happen with the demand for a certain product, future sales, decisions on inventory, supplies, etc. Recurrent Neural Networks (RNNs) are capable of performing a wide variety of computational tasks including processing sequences, continuation of a trajectory, non-linear prediction, and modeling of dynamical systems. These networks are also known as space–time or dynamic networks, they are a attempt to establish a correspondence between input and output sequences that they are just temporary patterns.

An RNN can be classified as partially and/or totally recurrent. The totally, recurrent are those that each neuron can be connected to any other and their Recurring connections are variable. Partially recurring networks are those that your recurring connections are fixed. The latter are the usual way to recognize or play sequences. They generally have the most forward connections but include a set of feedback connections. RNN are a field within Machine Learning in constant development, which in recent times has gained enormous popularity thanks to the promising results obtained in the most diverse fields of application.

There are contributions on theoretical aspects as well as applications, which make the book very appealing to a wide audience, ranging from researchers to professors and graduate students.