Search

Preprocessing is the process of adapting the input of our Computational Intelligence (CI) problem to the CI technique applied. Images are inputs of many problems, and Fractal processing of the images to extract relevant geometry characteristics is a very important tool. This chapter is dedicated to Fractal Preprocessing. In Pedology, fractal models were fitted to match the structure of soils and techniques of multifractal analysis of soil images were developed as is described in a state-of-the-art panorama. A box-counting method and a gliding box method are presented, both obtaining from images sets of dimension parameters, and are evaluated in a discussed case study from images of samples, and the second seems preferable. Finally, a comprehensive list of references is given [ABSTRACT FROM AUTHOR]

Support Vector Machines is the most recent algorithm in the Machine Learning community. After a bit less than a decade of live, it has displayed many advantages with respect to the best old methods: generalization capacity, ease of use, solution uniqueness. It has also shown some disadvantages: maximum data handling and speed in the training phase. However, these disadvantages will be overcome in the near future, as computer power increases, leaving an all-purpose learning method both cheap to use and giving the best performance. This chapter provides an overview about the main SVM configuration, its mathematical applications and the easiest implementation [ABSTRACT FROM AUTHOR]

Among the different types of Neural Networks (NN), the most popular and frequently used architectures are the Multilayer Perceptron (MLP) and Radial Basis Functions (RBF) due to their approximation capabilities. In this chapter we discuss the use of RBF networks to solve problems in different areas related to communications systems. In the first part of the chapter, we revise the structure of the RBF networks and the main procedures to train them. In the second part, the main applications of RBF networks in communication systems are presented and described. In particular, we will focus our attention in antenna array signal processing (direction-of-arrival estimation and beamforming) and channel equalization (intersymbol interferences and co-channel interferences). Other applications such as coding/decoding, system identification, fault detection in access networks and automatic recognition of wireless standards are also mentioned [ABSTRACT FROM AUTHOR]

This chapter is dedicated to the scope of which facts should be considered when deciding whether a Neural Network (NN) solution is suitable to solve a given problem. This is followed by a detailed example of a successful and useful application: a Neural Binary Detector [ABSTRACT FROM AUTHOR]

This chapter starts with a historical summary of the evolution of Neural Networks from the first models which are very limited in application capabilities to the present ones that make possible to think in applying automatic process to tasks that formerly had been reserved to the human intelligence. After the historical review, Neural Networks are dealt from a computational point of view. This perspective helps to compare Neural Systems with classical Computing Systems and leads to a formal and common presentation that will be used throughout the book [ABSTRACT FROM AUTHOR]