Multidimensional Particle Swarm Optimization for Machine Learning and Pattern Recognition (Adaptation, Learning, and Optimization)
Format: PDF / Kindle (mobi) / ePub
For many engineering problems we require optimization processes with dynamic adaptation as we aim to establish the dimension of the search space where the optimum solution resides and develop robust techniques to avoid the local optima usually associated with multimodal problems. This book explores multidimensional particle swarm optimization, a technique developed by the authors that addresses these requirements in a well-defined algorithmic approach.
After an introduction to the key optimization techniques, the authors introduce their unified framework and demonstrate its advantages in challenging application domains, focusing on the state of the art of multidimensional extensions such as global convergence in particle swarm optimization, dynamic data clustering, evolutionary neural networks, biomedical applications and personalized ECG classification, content-based image classification and retrieval, and evolutionary feature synthesis. The content is characterized by strong practical considerations, and the book is supported with fully documented source code for all applications presented, as well as many sample datasets.
The book will be of benefit to researchers and practitioners working in the areas of machine intelligence, signal processing, pattern recognition, and data mining, or using principles from these areas in their application domains. It may also be used as a reference text for graduate courses on swarm optimization, data clustering and classification, content-based multimedia search, and biomedical signal processing applications.
them before going into the details of the method detailed in this book. This chapter begins with a detailed history of optimization, covering the major achievements in time along with the people behind them. The rest of the chapter then draws the focus on major optimization techniques, while briefly explaining the mathematical theory and foundations over some sample problems. 2.1 History of Optimization In its most basic terms, Optimization is a mathematical discipline that concerns the finding
Classification Results on Synthetic Problems . . . . . 7.2.4 Classification Results on Medical Diagnosis Problems . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7.2.5 Parameter Sensitivity and Computational Complexity Analysis. . . . . . . . . . . . . . . . . . . . . . 7.3 Evolutionary RBF Classifiers for Polarimetric SAR Images. 7.3.1 Polarimetric SAR Data Processing . . . . . . . . . . . . 7.3.2 SAR Classification Framework. . . . . . . . . . . . . . . 7.3.3 Polarimetric SAR
this work showed that the bPSO can outperform K-means, FCM, KHM, and some other state-of-the-art clustering methods in any (evaluation) criteria. This is indeed an expected outcome due to the PSO’s aforementioned ability to cope up with the local optima by maintaining a guided random search operation through the swarm particles. In clustering, similar to other PSO applications, each particle represents a potential solution at a particular time t, i.e., the particle a in the swarm, n ¼ fx1 ; ::;
preliminary discussion and experimental results of the application of the basic PSO over four nonlinear functions were given in Sect. 3.4.1. We now selected seven benchmark functions and biased them with a dimensional term in order to 5.1 Fractional Global Best Formation 105 Table 5.2 Pseudo-code for FGBF in MD PSO FGBF in MD PSO (f ða; jÞ) 1. Create a new aGB particle, fxxdaGB; j ðtÞ; xydaGB; j ðtÞg for 8d 2 ½Dmin ; Dmax ; 8j 2 ½1; d ðf ða; jÞÞ be the index array of particles yielding the
within the second for loop, for (int cur_d=m_xdMin; cur_d