Machine learning

This book introduces novel approaches and practical examples of autonomous nuclear power plants that minimize operator intervention. Autonomous nuclear power plants with artificial intelligence presents a framework to enable nuclear power plants to autonomously operate and introduces artificial intelligence (AI) techniques to implement its functions. Although nuclear power plants are already highly automated to reduce human errors and guarantee the reliability of system operations, the term ¿autonomous¿ is still not popular because AI techniques are regarded as less proven technologies. However, the use of AI techniques and the autonomous operation seems unavoidable because of their great advantages, especially, in advanced reactors and small modular reactors.The book includes the following topics:Monitoring, diagnosis, and prediction.Intelligent control.Operator support systems.Operator-autonomous system interaction.Integrationinto the autonomous operation system. This book will provides useful information for researchers and students who are interested in applying AI techniques in the fields of nuclear as well as other industries. This book covers broad practical applications of AI techniques from the classical fault diagnosis to more recent autonomous control. In addition, specific techniques and modelling examples are expected to be very informative to the beginners in the AI studies.

As data is a predominant resource in applications, Riemannian geometry is a natural framework to model and unify complex nonlinear sources of data. However, the development of computational tools from the basic theory of Riemannian geometry is laborious. In this monograph the authors present a self-contained exposition of the basic concepts of Riemannian geometry from a computational viewpoint, providing illustrations and examples at each step. They proceed to demonstrate how these concepts are implemented in the open-source project Geomstats, explaining the choices that were made and the conventions chosen. The reader thus learns in one self-contained volume the theory of Riemann geometry and geometric statistics and their implementation to perform statistics and machine learning on manifolds. Containing many practical Python examples, this monograph is a valuable resource both for mathematicians and applied scientists to learn the theory of Riemann geometry and its use in practice implemented with the Geomstats package where most of the difficulties are hidden under high-level functions.

Multi-Criteria Decision-Making for Renewable Energy: Methods, Applications, and Challengesbrings together the latest fuzzy and soft computing methods, models, and algorithms as applied to the field of renewable energy and supported by specific application examples and case studies. The book begins by approaching renewable energy sources, challenges and factors that affect their development, as well as green renewable energy sites and the utilization of fuzzy multi-criteria decision-making (MCDM) techniques in these broad contexts, as well as utilization in addressing the various environmental, economic, and social barriers to ensuring the sustainability of energy resources.Detailed chapters focus on the application of multi-criteria decision-making methods for planning, modeling and prioritization in specific areas of renewable energy, including solar energy, wind farms, solar-powered hydrogen production plants, biofuel production, energy storage, hydropower, and marine energy. Finally, future opportunities and research directions are explored.

The book includes select proceedings of the International Conference on Computational Intelligence in Machine Learning (ICCIML 2021). The book constitutes peer-reviewed papers on machine learning, computational intelligence, the internet of things, and smart city applications emphasizing multi-disciplinary research in artificial intelligence and cyber-physical systems. This book addresses the comprehensive nature of computational intelligence, artificial intelligence, machine learning, and deep learning to emphasize its character in modeling, identification, optimization, prediction, forecasting, and control of future intelligent systems. The book will be useful for researchers, research scholars, and students to formulate their research ideas and find future directions in these areas. It will help the readers to solve a diverse range of problems in industries and their real-world applications.

This book gives a comprehensive view of graph theory in informational retrieval (IR) and natural language processing(NLP). This book provides number of graph techniques for IR and NLP applications with examples. It also provides understanding of graph theory basics, graph algorithms and networks using graph. The book is divided into three parts and contains nine chapters. The first part gives graph theory basics and graph networks, and the second part provides basics of IR with graph-based information retrieval. The third part covers IR and NLP recent and emerging applications with case studies using graph theory. This book is unique in its way as it provides a strong foundation to a beginner in applying mathematical structure graph for IR and NLP applications. All technical details that include tools and technologies used for graph algorithms and implementation in Information Retrieval and Natural Language Processing with its future scope are explained in a clear and organized format.

This book focuses on research aspects of ensemble approaches of machine learning techniques that can be applied to address the big data problems.In this book, various advancements of machine learning algorithms to extract data-driven decisions from big data in diverse domains such as the banking sector, healthcare, social media, and video surveillance are presented in several chapters. Each of them has separate functionalities, which can be leveraged to solve a specific set of big data applications. This book is a potential resource for various advances in the field of machine learning and data science to solve big data problems with many objectives. It has been observed from the literature that several works have been focused on the advancement of machine learning in various fields like biomedical, stock prediction, sentiment analysis, etc. However, limited discussions have been carried out on application of advanced machine learning techniques in solving big data problems.

This book highlights recent advance in the area of Machine Learning and IoT, and their applications to solve societal issues/problems or useful for various users in the society. It is known that many smart devices are interconnected and the data generated is being analyzed and processed with machine learning models for prediction, classification, etc., to solve human needs in various sectors like health, road safety, agriculture, and education. This contributed book puts together chapters concerning the use of intelligent techniques in various aspects related to the IoT domain from protocols to applications, to give the reader an up-to-date picture of the state-of-the-art on the connection between computational intelligence, machine learning, and IoT.

This book presents the state of the art in distributed machine learning algorithms that are based on gradient optimization methods. In the big data era, large-scale datasets pose enormous challenges for the existing machine learning systems. As such, implementing machine learning algorithms in a distributed environment has become a key technology, and recent research has shown gradient-based iterative optimization to be an effective solution. Focusing on methods that can speed up large-scale gradient optimization through both algorithm optimizations and careful system implementations, the book introduces three essential techniques in designing a gradient optimization algorithm to train a distributed machine learning model: parallel strategy, data compression and synchronization protocol.Written in a tutorial style, it covers a range of topics, from fundamental knowledge to a number of carefully designed algorithms and systems of distributed machine learning. It will appeal to a broad audience in the field of machine learning, artificial intelligence, big data and database management.

Intelligently connect data points and gain a deeper understanding of environmental problems through hands-on Geospatial Data Science case studies written in PythonThe book includes colored images of important conceptsKey Features:Learn how to integrate spatial data and spatial thinking into traditional data science workflowsDevelop a spatial perspective and learn to avoid common pitfalls along the wayGain expertise through practical case studies applicable in a variety of industries with code samples that can be reproduced and expandedBook Description:Data scientists, when presented with a myriad of data, can often lose sight of how to present geospatial analyses in a meaningful way so that it makes sense to everyone. Using Python to visualize data helps stakeholders in less technical roles to understand the problem and seek solutions. The goal of this book is to help data scientists and GIS professionals learn and implement geospatial data science workflows using Python.Throughout this book, you'll uncover numerous geospatial Python libraries with which you can develop end-to-end spatial data science workflows. You'll learn how to read, process, and manipulate spatial data effectively. With data in hand, you'll move on to crafting spatial data visualizations to better understand and tell the story of your data through static and dynamic mapping applications. As you progress through the book, you'll find yourself developing geospatial AI and ML models focused on clustering, regression, and optimization. The use cases can be leveraged as building blocks for more advanced work in a variety of industries.By the end of the book, you'll be able to tackle random data, find meaningful correlations, and make geospatial data models.What You Will Learn:Understand the fundamentals needed to work with geospatial dataTransition from tabular to geo-enabled data in your workflowsDevelop an introductory portfolio of spatial data science work using PythonGain hands-on skills with case studies relevant to different industriesDiscover best practices focusing on geospatial data to bring a positive change in your environmentExplore solving use cases, such as traveling salesperson and vehicle routing problemsWho this book is for:This book is for you if you are a data scientist seeking to incorporate geospatial thinking into your workflows or a GIS professional seeking to incorporate data science methods into yours. You'll need to have a foundational knowledge of Python for data analysis and/or data science.

This book constitutes the proceedings of the 37th International Conference, IVCNZ 2022, which took place in Auckland, New Zealand, in November 2022.The 37 papers (14 accepted for long oral presentation, 23 for short oral presentation) included in this volume were carefully reviewed and selected from 79 submissions. The conference presents papers on all aspects of computer vision, image processing, computer graphics, virtual and augmented reality, visualization, and HCI applications related to these fields.

This book, now in an extensively revised and updated second edition, provides a comprehensive overview of both machine learning and deep learning and their role in oncology, medical physics, and radiology. Readers will find thorough coverage of basic theory, methods, and demonstrative applications in these fields. An introductory section explains machine and deep learning, reviews learning methods, discusses performance evaluation, and examines software tools and data protection. Detailed individual sections are then devoted to the use of machine and deep learning for medical image analysis, treatment planning and delivery, and outcomes modeling and decision support. Resources for varying applications are provided in each chapter, and software code is embedded as appropriate for illustrative purposes. The book will be invaluable for students and residents in medical physics, radiology, and oncology and will also appeal to more experienced practitioners and researchers and members of applied machine learning communities. 

This book constitutes the revised selected proceedings of Second International Symposium on Biomedical and Computational Biology, BECB 2022, held as a virtual event in August 2022.The 58 full papers included in this book were carefully reviewed and selected from 135 submissions. The papers are organized in topical sections as follows: The Charge Transfer Network Model for Arbitrary Proteins Complexes; A Self-Supervised 3D/2D Registration Method for Incomplete DSA Vessels; The Potential Role of RNA "Writer" TRMT61B in the Immune Regulation of Breast Cancer; Extraction, Composition Analysis and Blood Lipid Lowering Activity of Rana chensinensis Ovum Oil.

Machine learning has become key in supporting decision-making processes across a wide array of applications, ranging from autonomous vehicles to malware detection. However, while highly accurate, these algorithms have been shown to exhibit vulnerabilities, in which they could be deceived to return preferred predictions. Therefore, carefully crafted adversarial objects may impact the trust of machine learning systems compromising the reliability of their predictions, irrespective of the field in which they are deployed. The goal of this book is to improve the understanding of adversarial attacks, particularly in the malware context, and leverage the knowledge to explore defenses against adaptive adversaries. Furthermore, to study systemic weaknesses that can improve the resilience of machine learning models.

This book constitutes the refereed proceedings of the 17th International Conference on Green, Pervasive, and Cloud Computing, GPC 2022, held in Chengdu, China, in December 2022.The 19 full papers presented in this book were carefully reviewed and selected from 104 submissions. GPC 2022 shares novel ideas and experiences in the areas of Green, Pervasive, and Cloud Computing.

"The Shape of Data shows how to use geometry- and topology-based algorithms for machine learning. The book focuses on practical applications rather than dense mathematical concepts, with coding examples using social network data, text data, medical data, and education data"--

This book introduces a Responsible AI framework and guides you through processes to apply at each stage of the machine learning (ML) life cycle, from problem definition to deployment, to reduce and mitigate the risks and harms found in artificial intelligence (AI) technologies. AI offers the ability to solve many problems today if implemented correctly and responsibly. This book helps you avoid negative impacts ¿ that in some cases have caused loss of life ¿ and develop models that are fair, transparent, safe, secure, and robust.The approach in this book raises your awareness of the missteps that can lead to negative outcomes in AI technologies and provides a Responsible AI framework to deliver responsible and ethical results in ML. It begins with an examination of the foundational elements of responsibility, principles, and data. Next comes guidance on implementation addressing issues such as fairness, transparency, safety, privacy, and robustness. The book helps you think responsibly while building AI and ML models and guides you through practical steps aimed at delivering responsible ML models, datasets, and products for your end users and customers. What You Will LearnBuild AI/ML models using Responsible AI frameworks and processesDocument information on your datasets and improve data qualityMeasure fairness metrics in ML modelsIdentify harms and risks per task and run safety evaluations on ML modelsCreate transparent AI/ML modelsDevelop Responsible AI principles and organizational guidelinesWho This Book Is ForAI and ML practitioners looking for guidance on building models that are fair, transparent, and ethical; those seeking awareness of the missteps that can lead to unintentional bias and harm from their AI algorithms; policy makers planning to craft laws, policies, and regulations that promote fairness and equity in automated algorithms

Cheminformatics, QSAR and Machine Learning Applications for Novel Drug Development aims at showcasing different structure-based, ligand-based, and machine learning tools currently used in drug design. It also highlights special topics of computational drug design together with the available tools and databases. The integrated presentation of chemometrics, cheminformatics, and machine learning methods under is one of the strengths of the book. The first part of the content is devoted to establishing the foundations of the area. Here recent trends in computational modeling of drugs are presented. Other topics present in this part include QSAR in medicinal chemistry, structure-based methods, chemoinformatics and chemometric approaches, and machine learning methods in drug design. The second part focuses on methods and case studies including molecular descriptors, molecular similarity, structure-based based screening, homology modeling in protein structure predictions, molecular docking, stability of drug receptor interactions, deep learning and support vector machine in drug design. The third part of the book is dedicated to special topics, including dedicated chapters on topics ranging from de design of green pharmaceuticals to computational toxicology. The final part is dedicated to present the available tools and databases, including QSAR databases, free tools and databases in ligand and structure-based drug design, and machine learning resources for drug design. The final chapters discuss different web servers used for identification of various drug candidates.

This book constitutes the proceedings of the 10th International Conference on Big Data Analytics, BDA 2022, which took place in Hyderabad, India, in December 2022.The 7 full papers and 7 short papers presented in this volume were carefully reviewed and selected from 36 submissions. The book also contains 4 keynote talks in full-paper length. The papers are organized in the following topical sections: Big Data Analytics: Vision and Perspectives; Data Science: Architectures; Data Science: Applications; Graph Analytics; Pattern Mining; Predictive Analytics in Agriculture.

This book constitutes the refereed proceedings of the 21st International Workshop, IWDW 2022, held in Guilin, China, during November 18-19, 2022. The 14 full papers included in this book were carefully reviewed and selected from 30 submissions. They were organized in topical sections as follows: Steganology, Forensics and Security Analysis, Watermarking.

Deep learning has become the dominant approach in addressing various tasks in Natural Language Processing (NLP). Although text inputs are typically represented as a sequence of tokens, there is a rich variety of NLP problems that can be best expressed with a graph structure. As a result, there is a surge of interest in developing new deep learning techniques on graphs for a large number of NLP tasks. In this monograph, the authors present a comprehensive overview on Graph Neural Networks (GNNs) for Natural Language Processing. They propose a new taxonomy of GNNs for NLP, which systematically organizes existing research of GNNs for NLP along three axes: graph construction, graph representation learning, and graph based encoder-decoder models. They further introduce a large number of NLP applications that exploits the power of GNNs and summarize the corresponding benchmark datasets, evaluation metrics, and open-source codes. Finally, they discuss various outstanding challenges for making the full use of GNNs for NLP as well as future research directions. This is the first comprehensive overview of Graph Neural Networks for Natural Language Processing. It provides students and researchers with a concise and accessible resource to quickly get up to speed with an important area of machine learning research.

This book constitutes the proceedings of the 13th International Workshop on Statistical Atlases and Computational Models of the Heart, STACOM 2022, held in conjunction with the 25th MICCAI conference.The 34 regular workshop papers included in this volume were carefully reviewed and selected after being revised and deal with topics such as: common cardiac segmentation and modelling problems to more advanced generative modelling for ageing hearts, learning cardiac motion using biomechanical networks, physics-informed neural networks for left atrial appendage occlusion, biventricular mechanics for Tetralogy of Fallot, ventricular arrhythmia prediction by using graph convolutional network, and deeper analysis of racial and sex biases from machine learning-based cardiac segmentation.In addition, 14 papers from the CMRxMotion challenge are included in the proceedings which aim to assess the effects of respiratory motion on cardiac MRI (CMR) imaging quality and examine the robustness of segmentation models in face of respiratory motion artefacts. A total of 48 submissions to the workshop was received.