Название: Metaheuristic Optimization Algorithms: Optimizers, Analysis, and Applications
Автор: Laith Abualigah
Издательство: Morgan Kaufmann/Elsevier
Год: 2024
Страниц: 628
Язык: английский
Формат: pdf, epub
Размер: 10.1 MB

Metaheuristic Optimization Algorithms: Optimizers, Analysis, and Applications presents the most recent optimization algorithms and their applications across a wide range of scientific and engineering research fields. Metaheuristic Optimization Algorithms have become indispensable tools, with applications in data analysis, text mining, classification problems, computer vision, image analysis, pattern recognition, medicine, and many others. Most complex systems problems involve a continuous flow of data that makes it impossible to manage and analyze manually. The outcome depends on the processing of high-dimensional data, most of it irregular and unordered, present in various forms such as text, images, videos, audio, and graphics. The authors of Meta-Heuristic Optimization Algorithms provide readers with a comprehensive overview of eighteen optimization algorithms to address this complex data, including Particle Swarm Optimization Algorithm, Arithmetic Optimization Algorithm, Whale Optimization Algorithm, and Marine Predators Algorithm, along with new and emerging methods such as Aquila Optimizer, Quantum Approximate Optimization Algorithm, Manta-Ray Foraging Optimization Algorithm, and Gradient Based Optimizer, among others. Each chapter includes an introduction to the modeling concepts used to create the algorithm, followed by the mathematical and procedural structure of the algorithm, associated pseudocode, and real-world case studies to demonstrate how each algorithm can be applied to a variety of scientific and engineering solutions.

Particle swarm optimization (PSO) is a heuristic global optimization technique and an optimization algorithm that is swarm intelligence-based. It is based on studies into the movement of bird flocks. Individual birds share information about their position, speed, and fitness while searching the food source, and the flock's behavior is affected to enhance the likelihood of migration to high-fitness areas. This paper surveys the published papers in PSO algorithms. Twenty research papers are analyzed and classified according to the implementation area used by the PSO algorithm (neural networks, feature selection, and data clustering). The main procedure of the PSO algorithm is presented. Future researchers can use the collected data in this survey as baseline information on the PSO and PSO's applications.

Cuckoo search (CS) is an efficient swarm intelligence-based algorithm that has come a long way since its start in 2009. Due to its simplicity and effectiveness, CS provides several advantages in tackling highly nonlinear optimization problems in engineering work applications. We offer an overview of the latest enhancements to this method in the past 5 years, explore the theoretical underpinning and potential research areas for future advances, and introduce novel metaheuristics to optimize computations based on explicit boosting tasks. Early studies reveal that the algorithm is viable and can exceed existing methods in performance. The CS algorithm is further validated for solving numerous technological optimization challenges. The proposed search technique is compared with the existing standard optimization algorithms. The current CS computations are merged with Levy flight and it was the first time used to solve nonlinear benchmark challenges.

- World-renowned researchers and practitioners in Metaheuristics present the procedures and pseudocode for creating a wide range of optimization algorithms
- Helps readers formulate and design the best optimization algorithms for their research goals through case studies in a variety of real-world applications
- Helps readers understand the links between Metaheuristic algorithms and their application in Computational Intelligence, Machine Learning, and Deep Learning problems








[related-news] [/related-news]