Diego Oliva – författare

The use of metaheuristic algorithms (MA) has been increasing in recent years, and the image processing field is not the exempted of their application. In the last two years a big amount of MA has been introduced as alternatives for solving complex optimization problems. This book collects the most prominent MA of the 2019 and 2020 and verifies its use in image processing tasks. In addition, literature review of both MA and digital image processing is presented as part of the introductory information. Each algorithm is detailed explained with special focus in the tuning parameters and the proper implementation for the image processing tasks. Besides several examples permits to the reader explore and confirm the use of this kind of intelligent methods. Since image processing is widely used in different domains, this book considers different kinds of datasets that includes, magnetic resonance images, thermal images, agriculture images, among others. The reader then can have some ideas of implementation that complement the theory exposed of each optimization mechanism. Regarding the image processing problems this book consider the segmentation by using different metrics based on entropies or variances. In the same way, the identification of different shapes and the detection of objects are also covered in the corresponding chapters. Each chapter is complemented with a wide range of experiments and statistical analysis that permits the reader to judge about the performance of the MA. Finally, there is included a section that includes some discussion and conclusions. This section also provides some open questions and research opportunities for the audience.

The use of metaheuristic algorithms (MA) has been increasing in recent years, and the image processing field is not the exempted of their application. In the last two years a big amount of MA has been introduced as alternatives for solving complex optimization problems. This book collects the most prominent MA of the 2019 and 2020 and verifies its use in image processing tasks. In addition, literature review of both MA and digital image processing is presented as part of the introductory information. Each algorithm is detailed explained with special focus in the tuning parameters and the proper implementation for the image processing tasks. Besides several examples permits to the reader explore and confirm the use of this kind of intelligent methods. Since image processing is widely used in different domains, this book considers different kinds of datasets that includes, magnetic resonance images, thermal images, agriculture images, among others. The reader then can have some ideas of implementation that complement the theory exposed of each optimization mechanism. Regarding the image processing problems this book consider the segmentation by using different metrics based on entropies or variances. In the same way, the identification of different shapes and the detection of objects are also covered in the corresponding chapters. Each chapter is complemented with a wide range of experiments and statistical analysis that permits the reader to judge about the performance of the MA. Finally, there is included a section that includes some discussion and conclusions. This section also provides some open questions and research opportunities for the audience.

Federated machine learning is a novel approach to combining distributed machine learning, cryptography, security, and incentive mechanism design. It allows organizations to keep sensitive and private data on users or customers decentralized and secure, helping them comply with stringent data protection regulations like GDPR and CCPA.

Artificial Intelligence Using Federated Learning: Fundamentals, Challenges, and Applications enables training AI models on a large number of decentralized devices or servers, making it a scalable and efficient solution. It also allows organizations to create more versatile AI models by training them on data from diverse sources or domains. This approach can unlock innovative use cases in fields like healthcare, finance, and IoT, where data privacy is paramount.

The book is designed for researchers working in Intelligent Federated Learning and its related applications, as well as technology development, and is also of interest to academicians, data scientists, industrial professionals, researchers, and students.

Federated machine learning is a novel approach to combining distributed machine learning, cryptography, security, and incentive mechanism design. It allows organizations to keep sensitive and private data on users or customers decentralized and secure, helping them comply with stringent data protection regulations like GDPR and CCPA.

Artificial Intelligence Using Federated Learning: Fundamentals, Challenges, and Applications enables training AI models on a large number of decentralized devices or servers, making it a scalable and efficient solution. It also allows organizations to create more versatile AI models by training them on data from diverse sources or domains. This approach can unlock innovative use cases in fields like healthcare, finance, and IoT, where data privacy is paramount.

The book is designed for researchers working in Intelligent Federated Learning and its related applications, as well as technology development, and is also of interest to academicians, data scientists, industrial professionals, researchers, and students.

Designing new algorithms in swarm intelligence is a complex undertaking. Two critical factors have been seen to have a direct correlation with positive results. First is initialization, which serves as the initial step for all swarm intelligence techniques. Candidate solutions are generated to form the initial population, which are subsequently modified during the iterative process. A well-initialized population increases the algorithm''s chances of avoiding local optima and finding the global optimum in fewer iterations. Although random distributions are commonly used for initialization, there are various ways to initialize the population elements.

Maintaining diversity among the population elements throughout the iterative process is also essential. This diversity facilitates a more thorough and efficient exploration of the search space. In swarm intelligence algorithms, there are multiple methods to measure diversity, each with its own advantages and disadvantages.

This book presents the theory behind the initialization process and the different mechanisms. Additionally, it includes a comparative study of various diversity indicators. It explores different methodologies to compute its value and explains how it can be incorporated as a mechanism for deciding when to apply operators during the optimization process. Multiple examples are provided in the book using two classical algorithms: Differential Evolution and Particle Swarm Optimization. It includes MATLAB® code and offers several exercises that readers can use for experimentation and design purposes.

Designing new algorithms in swarm intelligence is a complex undertaking. Two critical factors have been seen to have a direct correlation with positive results. First is initialization, which serves as the initial step for all swarm intelligence techniques. Candidate solutions are generated to form the initial population, which are subsequently modified during the iterative process. A well-initialized population increases the algorithm''s chances of avoiding local optima and finding the global optimum in fewer iterations. Although random distributions are commonly used for initialization, there are various ways to initialize the population elements.

Maintaining diversity among the population elements throughout the iterative process is also essential. This diversity facilitates a more thorough and efficient exploration of the search space. In swarm intelligence algorithms, there are multiple methods to measure diversity, each with its own advantages and disadvantages.

This book presents the theory behind the initialization process and the different mechanisms. Additionally, it includes a comparative study of various diversity indicators. It explores different methodologies to compute its value and explains how it can be incorporated as a mechanism for deciding when to apply operators during the optimization process. Multiple examples are provided in the book using two classical algorithms: Differential Evolution and Particle Swarm Optimization. It includes MATLAB® code and offers several exercises that readers can use for experimentation and design purposes.

This book presents a collection of the most recent hybrid methods for image processing. The algorithms included consider evolutionary, swarm, machine learning and deep learning. The respective chapters explore different areas of image processing, from image segmentation to the recognition of objects using complex approaches and medical applications. The book also discusses the theory of the methodologies used to provide an overview of the applications of these tools in image processing.

The book is primarily intended for undergraduate and postgraduate students of science, engineering and computational mathematics, and can also be used for courses on artificial intelligence, advanced image processing, and computational intelligence. Further, it is a valuable resource for researchers from the evolutionary computation, artificial intelligence and image processing communities.

This book presents the proceedings of the 1st International Conference on Artificial Intelligence and Computer Visions (AICV 2020), which took place in Cairo, Egypt, from April 8 to 10, 2020. This international conference, which highlighted essential research and developments in the fields of artificial intelligence and computer visions, was organized by the Scientific Research Group in Egypt (SRGE). The book is divided into sections, covering the following topics: swarm-based optimization mining and data analysis, deep learning and applications, machine learning and applications, image processing and computer vision, intelligent systems and applications, and intelligent networks.

This book helps the reader to identify how different organizations in the context of diverse societies deploy their resources and leverage their capabilities to achieve better performance of its various labor skills, marketing, social responsibility and management capacity. Intelligent Logistics is a complex phenomenon that has become critical for companies to reach their development locally and internationally. On the one hand, macro-factors and market structure influence in business competitiveness, but also in a regional or sector context. The internal aspects and the use of various business tools contribute to the ability to create value in an organization. It is of utmost importance to understand the relevance of crucial aspects in the technological future that should be known and implemented by the Z generation of its incidence in the use of organizational models linked to artificial intelligence.  

Every innovative aspect in the use of new technologies for the distribution of goods and services will be crucial in a globalized world. An avant-garde society will require improved decision-making regarding Logistics 4.0 and its implementation in our lives respecting the environment and being sustainable together with invaluable principles of generating tacit knowledge for future generations. 

This book includes chapters related to the analysis of cultural differences as a tool to enrich tacit knowledge and make processes more efficient, the factors that influence job satisfaction and the value of social capital as a competitive strategy to achieve productivity and competitiveness of organizations, in addition to research of the utmost importance to discover the facets of the diamond with respect to the symbolic capital of the organizations where Generation Z will work and how it will discover the best time to establish an innovation ecosystem that will influence its work trajectory. Industry 4.0 requires a major paradigm shift, since human capital is a source of competitive advantage.