Preface

Deep learning is a branch of machine learning similar to artificial intelligence. As it is an exciting new field, many scientists and researchers are studying the applications of deep learning and proposing new architectures.

This book presents the state of the art, architectures, and systems of deep learning applications. The applications of deep learning vary from medical imaging to industrial quality checking, sports, and precision agriculture. The book is divided into two sections. The first section covers deep learning architectures, whereas the second section describes the state of the art of applications based on deep learning.

The editors thank the authors for their high-level contributions and their proactive collaboration in the realization of this book.

**II**

**Chapter 8 145**

**Chapter 9 167**

**Chapter 10 185**

Application of Deep Learning Methods for Detection and Tracking

Application of Artificial Neural Networks to Chemical and Process

Material Classification via Machine Learning Techniques:

Construction Projects Progress Monitoring

*by Wesam Salah Alaloul and Abdul Hannan Qureshi*

*by Fabio Machado Cavalcanti, Camila Emilia Kozonoe, Kelvin André Pacheco* 

*by Marina Ivasic-Kos, Kristina Host and Miran Pobar*

of Players

Engineering

*and Rita Maria de Brito Alves*

**Pier Luigi Mazzeo and Paolo Spagnolo** National Research Council of Italy (CNR), Institute of Applied Sciences and Intelligent Systems (ISASI), Lecce, Italy

Section 1

Architectures

**1**

Section 1 Architectures

**Chapter 1**

**Abstract**

nonlinear system

**1. Introduction**

system [1, 2].

**3**

Tuning Artificial Neural Network

Controller Using Particle Swarm

*Sabrine Slama, Ayachi Errachdi and Mohamed Benrejeb*

**Keywords:** neural networks, particle swarm optimization, indirect control,

We are interested, in this chapter, in adaptive system control of a class of singleinput single-output (SISO) non-linear systems using neural network. In fact, this system control is a very general approach to adaptive control since one can combine in principle any parameter estimation scheme with any control strategy. In addition, its architecture is based on two neural network blocks corresponding to the system controller and the model identification of the dynamic behavior of the

The use of artificial neural network (ANN) for identification, diagnosis, modeling and control has generated a lot of interest for quite some time now, because they have proved to be excellent function approximators, mapping any function to an arbitrary degree of accuracy, coupled with their ability for generalization,

Many architectures of neural networks are used. Among them, the most common and the most popular architecture is the multilayered perceptron,

implemented with the standardized backpropagation algorithm. If the initial set of weights is not selected properly, this algorithm, employing a gradient descent search technique is seriously prone to getting trapped in local optimum solutions.

This chapter proposes an optimization technique of Artificial Neural Network (ANN) controller, of single-input single-output time-varying discrete nonlinear system. A bio-inspired optimization technique, Particle Swarm Optimization (PSO), is proposed to be applied in ANN to avoid any possibilities from local extreme condition. Further, a PSO based neural network controller is also developed to be integrated with the designed system to control a nonlinear systems. The simulation results of an example of nonlinear system demonstrate the effectiveness of the proposed approach using Particle Swarm Optimization approach in terms of reduced oscillations compared to classical neural network optimization method.

Optimization Technique for

Nonlinear System

MATLAB was used as simulation tool.

self-organization and self-learning [3].
