This book is an invaluable resource for anyone interested in the intersection of statistics, machine learning, and data science. It offers a unique perspective on Bayesian inference, revealing its potential to provide robust solutions in an increasingly data-driven world. The book is your gateway to understanding and leveraging the power of Bayesian methods in the ever-evolving landscape of data analysis.

This book explores how human civilization has contributed to changes in the Anthropocene, an era that marks a fundamental change in the way mankind has interacted with the Earth system. It examines the 21st century in the context of human development of water infrastructures, climate change impacts on freshwater resources, groundwater depletion, rising population, land use change, extreme events (droughts, floods, and wildfires). The implications of climate change impacts on environmental assets and the global water cycle are also highlighted. The book takes a pragmatically trans-disciplinary and holistic approach to the discussion of these issues, and the Earth system in the Anthropocene, drawing from a plethora of case studies. The capabilities of machine learning tools in satellite hydrology applications have been demonstrated as well as the feasibility of remote sensing data and innovative geospatial tools in environmental assessment. The book further showcases the multiple strengths and potential of new multi-disciplinary satellite radar programmes and geodetic missions, to measure and characterize extreme events, and their links to global climate, as well as in remote sensing of the environment.

This thesis presents significant advances in the use of neural networks to study the properties of neutrinos. Machine learning tools like neural networks (NN) can be used to identify the particle types or determine their energies in detectors such as those used in the NOvA neutrino experiment, which studies changes in a beam of neutrinos as it propagates approximately 800 km through the earth. NOvA relies heavily on simulations of the physics processes and the detector response; these simulations work well, but do not match the real experiment perfectly. Thus, neural networks trained on simulated datasets must include systematic uncertainties that account for possible imperfections in the simulation. This thesis presents the first application in HEP of adversarial domain generalization to a regression neural network. Applying domain generalization to problems with large systematic variations will reduce the impact of uncertainties while avoiding the risk of falsely constraining the phase space. Reducing the impact of systematic uncertainties makes NOvA analysis more robust, and improves the significance of experimental results.

This book offers a glimpse of the status of machine- and deep-learning methodological development, seeking to meet the challenge of new hyperspectral imaging applications.

This book covers all the emerging trends in artificial intelligence (AI) and the Internet of Things (IoT). The Internet of Things is a term that has been introduced in recent years to define devices that are able to connect and transfer data to other devices via the Internet. While IoT and sensors have the ability to harness large volumes of data, AI can learn patterns in the data and quickly extract insights in order to automate tasks for a variety of business benefits.

This book explores how human civilization has contributed to changes in the Anthropocene, an era that marks a fundamental change in the way mankind has interacted with the Earth system. It examines the 21st century in the context of human development of water infrastructures, climate change impacts on freshwater resources, groundwater depletion, rising population, land use change, extreme events (droughts, floods, and wildfires). The implications of climate change impacts on environmental assets and the global water cycle are also highlighted. The book takes a pragmatically trans-disciplinary and holistic approach to the discussion of these issues, and the Earth system in the Anthropocene, drawing from a plethora of case studies. The capabilities of machine learning tools in satellite hydrology applications have been demonstrated as well as the feasibility of remote sensing data and innovative geospatial tools in environmental assessment. The book further showcases the multiple strengths and potential of new multi-disciplinary satellite radar programmes and geodetic missions, to measure and characterize extreme events, and their links to global climate, as well as in remote sensing of the environment.

This book presents select papers from 3rd EAI International Conference on Computational Intelligence and Communications (CICom 2022). The papers reveal recent advances in the broader domains of Computational Intelligence including (1) automation, control, and intelligent transportation system, (2) big data, internet of things, and smart cities, (3) wireless communication systems and cyber security and (4) human/brain-computer interfaces, and image and pattern recognition. The book demonstrates complex real-world problems in which mathematical or traditional modellings are not the preferred solution, hence alternative solutions are needed. This collection of applications demonstrates the important advances in computational intelligence. The book chapters’ present various ideas that will benefit researchers, graduate students and engineers in this domain.

The two-volume set CCIS 1869 and 1870 constitutes the refereed proceedings of the 4th International Conference on Neural Computing for Advanced Applications, NCAA 2023, held in Hefei, China, in July 2023.The 83 full papers and 1 short paper presented in these proceedings were carefully reviewed and selected from 211 submissions. The papers have been organized in the following topical sections: Neural network (NN) theory, NN-based control systems, neuro-system integration and engineering applications; Machine learning and deep learning for data mining and data-driven applications; Computational intelligence, nature-inspired optimizers, and their engineering applications; Deep learning-driven pattern recognition, computer vision and its industrial applications; Natural language processing, knowledge graphs, recommender systems, and their applications; Neural computing-based fault diagnosis and forecasting, prognostic management, and cyber-physical system security; Sequence learning for spreading dynamics, forecasting, and intelligent techniques against epidemic spreading (2); Applications of Data Mining, Machine Learning and Neural Computing in Language Studies; Computational intelligent Fault Diagnosis and Fault-Tolerant Control, and Their Engineering Applications; and Other Neural computing-related topics.

This volume discusses the theoretical and practical aspects required to formulate conventional drug dosage forms and advanced technology-based therapeutics. The book is a collection of scholarly literature relevant to pharmaceutical technology and existing pharmaceutical technologies. It is a useful reference for industrial personnel working on developing novel pharmaceutical dosage forms.

This volume delivers up-to-date information on the identification of newer uses, molecular mechanisms, and novel targets of existing drug candidates through the application of various experimental, biophysical, and computational approaches and techniques. The book discusses recent advances in drug repurposing strategies that are currently being used in the discovery and development of drugs against difficult-to-treat, rare, and life-threatening diseases, including microbial infections, COVID-19, parasitic diseases, cardiovascular diseases, neurological disorders, and cancer. The book also discusses the modern experimental assays (HTS) and computational techniques including informatics and databases, molecular docking and dynamics, artificial intelligence and machine learning, virtual screening and pharmacophore modeling, proteomics and metabolomics, and network pharmacology and systems biology approaches.

While GPS is the de-facto solution for outdoor positioning with a clear sky view, there is no prevailing technology for GPS-deprived areas, including dense city centers, urban canyons, buildings and other covered structures, and subterranean facilities such as underground mines, where GPS signals are severely attenuated or totally blocked. As an alternative to GPS for the outdoors, indoor localization using machine learning is an emerging embedded and Internet of Things (IoT) application domain that is poised to reinvent the way we navigate in various indoor environments. This book discusses advances in the applications of machine learning that enable the localization and navigation of humans, robots, and vehicles in GPS-deficient environments.

This book explores the challenges involved in handling medical big data in the diagnosis of neurological disorders. It discusses how to optimally reduce the number of neuropsychological tests during the classification of these disorders by using feature selection methods based on the diagnostic information of enrolled subjects. The book includes key definitions/models and covers their applications in different types of signal/image processing for neurological disorder data. An extensive discussion on the possibility of enhancing the abilities of AI systems using the different data analysis is included. The book recollects several applicable basic preliminaries of the different AI networks and models, while also highlighting basic processes in image processing for various neurological disorders. It also reports on several applications to image processing and explores numerous topics concerning the role of big data analysis in addressing signal and image processing in various real-world scenarios involving neurological disorders.

Machine learning (ML) models, especially large pretrained deep learning (DL) models, are of high economic value and must be properly protected with regard to intellectual property rights (IPR). Model watermarking methods are proposed to embed watermarks into the target model, so that, in the event it is stolen, the model’s owner can extract the pre-defined watermarks to assert ownership. Model watermarking methods adopt frequently used techniques like backdoor training, multi-task learning, decision boundary analysis etc. to generate secret conditions that constitute model watermarks or fingerprints only known to model owners. These methods have little or no effect on model performance, which makes them applicable to a wide variety of contexts. In terms of robustness, embedded watermarks must be robustly detectable against varying adversarial attacks that attempt to remove the watermarks. The efficacy of model watermarking methods is showcased in diverse applications including image classification, image generation, image captions, natural language processing and reinforcement learning.

The increase in fake news, the growing influence on elections, increasing false reports and targeted disinformation campaigns are not least a consequence of advancing digitalisation. Information technology is needed to put a stop to these undesirable developments. With intelligent algorithms and refined data analysis, fakes must be detected more quickly in the future and their spread prevented. However, in order to meaningfully recognize and filter fakes by means of artificial intelligence, it must be possible to distinguish fakes from facts, facts from fictions, and fictions from fakes. This book therefore also asks questions about the distinctions of fake, factual and fictional. The underlying theories of truth are discussed, and practical-technical ways of differentiating truth from falsity are outlined. By considering the fictional as well as the assumption that information-technical further development can profit from humanities knowledge, the authors hope that content-related, technical and methodological challenges of the present and future can be overcome.