Arana-Daniel N., Lopez-Franco C., Alanis A. Bio-inspired Algorithms for Engineering

Butterworth-Heinemann, 2018. — 152 p. — ISBN: 9780128137888.This book builds a bridge between the proposed bio-inspired algorithms developed in the past few decades and their applications in real-life problems, not only in an academic context, but also in the real world. The book proposes novel algorithms to solve real-life, complex problems, combining well-known bio-inspired algorithms with new concepts, including both rigorous analyses and unique applications. It covers both theoretical and practical methodologies, allowing readers to learn more about the implementation of bio-inspired algorithms. This book is a useful resource for both academic and industrial engineers working on artificial intelligence, robotics, machine learning, vision, classification, pattern recognition, identification and control.Key FeaturesPresents real-time implementation and simulation results for all the proposed schemes
Offers a comparative analysis and rigorous analysis of the convergence of proposed algorithms
Provides a guide for implementing each application at the end of each chapter
Includes illustrations, tables and figures that facilitate the reader’s comprehension of the proposed schemes and applicationsResearch Engineers working on artificial intelligence, robotics, machine learning, vision, classification, pattern recognition, identification and control, among others. Professors and Graduate students working on artificial intelligence, robotics, machine learning, vision, classification, pattern recognition, identification and controlBio-inspired Algorithms
Data Classification Using Support Vector Machines Trained with Evolutionary Algorithms Employing Kernel Adatron
Reconstruction of 3D Surfaces Using RBF Adjusted with PSO
Soft Computing Applications in Robot Vision
Soft Computing Applications inMobile Robotics
Particle Swarm Optimization to Improve Neural Identifiers for Discrete-time Unknown Nonlinear Systems
Bio-inspired Algorithms to Improve Neural Controllers for Discrete-time Unknown Nonlinear System
Final RemarksTrue PDF