| Description |
1 online resource (viii, 73 pages) : illustrations (some color) |
| Series |
SpringerBriefs in applied sciences and technology, Computational intelligence, 2191-530X |
|
SpringerBriefs in applied sciences and technology. Computational intelligence, 2191-530X
|
| Contents |
Intro; Preface; Contents; 1 Introduction; References; 2 Theory and Background; 2.1 Artificial Neural Networks; 2.2 History of Artificial Neural Networks; 2.3 Neural Networks Architecture; 2.3.1 Input Function; 2.3.2 Activation Function; 2.3.3 Output Function; 2.3.4 Learning; 2.4 Supervised Learning Neural Networks; 2.4.1 Perceptron; 2.4.2 Multilayer Perceptron; 2.4.3 MLPs Backpropagation Algorithm; 2.5 Unsupervised Learning Neural Networks; 2.5.1 Competitive Learning; 2.5.2 Learning Vector Quantization; 2.6 Modular Neural Networks; 2.6.1 Characteristics of Modular Neural Networks |
|
2.7 Fuzzy Inference Systems2.7.1 Fuzzy Sets; 2.7.2 Membership Functions; 2.7.3 Fuzzy If-Then Rules; 2.7.4 Components of a Fuzzy Inference System; 2.8 Interval Type-2 Fuzzy Inference Systems; References; 3 Problem Statement; 3.1 Datasets; 3.1.1 Arrhythmia Dataset; 3.1.2 Satellite Images Dataset; References; 4 Proposed Classification Method; 4.1 Fuzz LVQ; 4.2 Model Architectures; 4.2.1 Data Similarity Process; 4.2.2 Model Architectures for the Arrhythmia Dataset; 4.2.3 Model Architectures for the Satellite Images Dataset; References; 5 Simulation Results |
|
5.1 Arrhythmia Dataset Methods Description5.1.1 Arrhythmia Dataset Simulation Results; 5.1.2 Arrhythmia Dataset Statistical Analysis; 5.2 Satellite Images Dataset Methods Description; 5.2.1 Satellite Images Dataset Simulation Results; 5.2.2 Satellite Images Dataset Statistical Analysis; Reference; 6 Conclusions; 6.1 Future Work; Reference; Appendix; A.1 Main LVQ Neural Network Architecture for Arrhythmia Classification (5 Modules); A.2 Main LVQ Neural Network Architecture for Satellite Images Classification; A.3 Integration Unit; A.4 Main Type-1 Fuzzy System; A.5. Main Type-2 Fuzzy System |
| Summary |
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 of soil. Both datasets show interesting features that makes them interesting for testing new classification methods |
| Bibliography |
Includes bibliographical references and index |
| Notes |
Online resource; title from PDF title page (SpringerLink, viewed February 14, 2018) |
| Subject |
Neural networks (Computer science)
|
|
Fuzzy logic.
|
|
Artificial intelligence.
|
|
COMPUTERS -- General.
|
|
Fuzzy logic
|
|
Neural networks (Computer science)
|
| Form |
Electronic book
|
| Author |
Melin, Patricia, 1962- author.
|
|
Castillo, Oscar, 1959- author.
|
| ISBN |
9783319737737 |
|
3319737732 |
|
