Externally indexed torrent

If you are the original uploader, contact staff to have it moved to your account

Textbook in PDF format

Bio-Inspired Optimization in Fog and Edge Computing Environments covers novel and innovative solutions for Fog and Edge with Machine Learning (ML) and informatics-based technological solutions for various applications. Recently, nature- or bio-inspired techniques have emerged as a successful tool to understand and analyze collective behavior. Algorithms and mechanisms for the self- organization of complex natural systems have been used to solve optimization problems, particularly in complex systems that are adaptive, ever-evolving, and distributed in nature. What fits more perfectly into this scenario than the rapidly developing era of Fog and Edge computing?
A new era of complexity science is emerging, in which nature- and bio-inspired principles are being applied to provide solutions. At the same time, the complexity of systems is increasing due to such models like the Internet of Things (IoT) and fog computing. Will complexity science, applying the principles of nature, be able to tackle the challenges posed by highly complex networked systems?
Bio-Inspired Optimization in Fog and Edge Computing: Principles, Algorithms, and Systems is an attempt to answer this question. It presents innovative, bio-inspired solutions for fog and edge computing and highlights the role of machine learning and informatics. Nature- or biological-inspired techniques are successful tools to understand and analyze a collective behavior. As this book demonstrates, algorithms, and mechanisms of self-organization of complex natural systems have been used to solve optimization problems, particularly in complex systems that are adaptive, ever-evolving, and distributed in nature.
The optimization module implements one or more optimization techniques to improve accuracy and any other performance parameter as required. Numerous nature- inspired optimization algorithms are available. PSO, GA, and PIO (predictive index optimization) are the most used optimizations. Optimization is mainly applied in the context of ML at the feature selection or reduction levels. The objective is to obtain the best near- optimal solution, for example, an accurate system within a certain time limit. In cloud deployment, optimization generally refers to task-resource scheduling. For a specific application, optimization at the cloud platform level could be ignored and the focus could be on optimization with ML tasks. There is also the option of one optimization technique from the many that are available. This flexibility is advantageous in this deployment, for instance, cloud deployment, otherwise has proved to be costly.
The chapters look at ways of enhancingto enhance the performance of fog networks in real-world applications using nature-based optimization techniques. They discuss challenges and provide solutions to the concerns of security, privacy, and power consumption in cloud data center nodes and fog computing networks. The book also examines how:
The existing fog and edge architecture is used to provide solutions to future challenges.
A geographical information system (GIS) can be used with fog computing to help users in an urban region access prime healthcare.
An optimization framework helps in cloud resource management.
Fog computing can improve the quality, quantity, long-term viability, and cost-effectiveness in agricultural production.
Virtualization can support fog computing, increase resources to be allocated, and be applied to different network layers.
The combination of fog computing and IoT or cloud computing can help healthcare workers predict and analyze diseases in patients