This book provides readers with a comprehensive and recent exposition in deep learning and its multidisciplinary applications, with a concentration on advances of deep learning architectures. The book discusses various artificial intelligence (AI) techniques based on deep learning architecture with applications in natural language processing, semantic knowledge, forecasting and many more. The authors shed light on various applications that can benefit from the use of deep learning in pattern recognition, person re-identification in surveillance videos, action recognition in videos, image and video captioning. The book also highlights how deep learning concepts can be interwoven with more modern concepts to yield applications in multidisciplinary fields. Presents a comprehensive look at deep learning and its multidisciplinary applications, concentrating on advances of deep learning architectures; Includes a survey of deep learning problems and solutions, identifying the main open issues, innovations and latest technologies; Shows industrial deep learning in practice with examples/cases, efforts, challenges, and strategic approaches.

This book provides a step-by-step methodology and derivation of deep learning algorithms as Long Short-Term Memory (LSTM) and Convolution Neural Network (CNN), especially for estimating parameters, with back-propagation as well as examples with real datasets of hydrometeorology (e.g. streamflow and temperature) and environmental science (e.g. water quality). Deep learning is known as part of machine learning methodology based on the artificial neural network. Increasing data availability and computing power enhance applications of deep learning to hydrometeorological and environmental fields. However, books that specifically focus on applications to these fields are limited. Most of deep learning books demonstrate theoretical backgrounds and mathematics. However, examples with real data and step-by-step explanations to understand the algorithms in hydrometeorology and environmental science are very rare. This book focuses on the explanation of deep learning techniques and their applications to hydrometeorological and environmental studies with real hydrological and environmental data. This book covers the major deep learning algorithms as Long Short-Term Memory (LSTM) and Convolution Neural Network (CNN) as well as the conventional artificial neural network model.

This book provides application of multi criteria decision making techniques for managerial discretion. With this book, a concerted platform has been provided for several peers and other management organizations to understand and implement these tools and deal with the practical problems in a better way so as to provide more robust managerial decision making.

Sensitivity analysis is used to ascertain how a given model output depends upon the input parameters. This is an important method for checking the quality of a given model, as well as a powerful tool for checking the robustness and reliability of its analysis. The topic is acknowledged as essential for good modelling practice, and is an implicit part of any modelling field.

• Offers an accessible introduction to sensitivity
• Covers all the latest research
• Illustrates concepts with numerous examples, applications and case studies
• Includes contributions from the leading researchers active in developing strategies for sensitivity analysis

Essential themes in the biochemical cycling of mercury are the relative importance of anthropogenic versus natural sources, transformation and migration processes at the local, regional and global scale, global emission inventories of different mercury sources (both point and diffuse) of both natural and anthropogenic origin. In this regard, Siberia, with its vast territory and variety of natural zones, is of special interest in the global mercury cycle and in terms of the influence of geographical zones on source and sink terms in regional budgets. Siberia contains large areas of mercuriferous belts; natural deposits that emit mercury into the atmosphere and water. Siberian gold has been mined with the use of mercury since the early 1800s. But there, too, huge forest zones and vast areas of tundra and wetland (bogs) can act as efficient sinks for atmospheric mercury. Audience: Environmental scientists, legislators, politicians and the interested citizen wishing to gain a clear picture of the biogeochemical cycling of mercury.

This book concerns issues related to biomathematics, medicine, or cybernetics as practiced by engineers. Considered population dynamics models are still in the interest of researchers, and even this interest is increasing, especially now in the time of SARS-CoV-2 coronavirus pandemic, when models are intensively studied in order to help predict its behaviour within human population. The structures of population dynamics models and practical methods of finding their solutions are discussed. Finally, the hypothesis of the existence of non-trivial ergodic properties of the model of erythropoietic response dynamics formulated by A. Lasota in the form of delay differential equation with unimodal feedback is analysed. The research can be compared with actual medical data, as well as shows that the structures of population models can reflect the dynamic structures of reality.

This book delivers the state of the art in deep learning (DL) methods hybridized with evolutionary computation (EC). Over the last decade, DL has dramatically reformed many domains: computer vision, speech recognition, healthcare, and automatic game playing, to mention only a few. All DL models, using different architectures and algorithms, utilize multiple processing layers for extracting a hierarchy of abstractions of data. Their remarkable successes notwithstanding, these powerful models are facing many challenges, and this book presents the collaborative efforts by researchers in EC to solve some of the problems in DL. EC comprises optimization techniques that are useful when problems are complex or poorly understood, or insufficient information about the problem domain is available. This family of algorithms has proven effective in solving problems with challenging characteristics such as non-convexity, non-linearity, noise, and irregularity, which dampen the performance of most classic optimization schemes. Furthermore, EC has been extensively and successfully applied in artificial neural network (ANN) research -from parameter estimation to structure optimization. Consequently, EC researchers are enthusiastic about applying their arsenal for the design and optimization of deep neural networks (DNN). This book brings together the recent progress in DL research where the focus is particularly on three sub-domains that integrate EC with DL: (1) EC for hyper-parameter optimization in DNN; (2) EC for DNN architecture design; and (3) Deep neuroevolution. The book also presents interesting applications of DL with EC in real-world problems, e.g., malware classification and object detection. Additionally, it covers recent applications of EC in DL, e.g. generative adversarial networks (GAN) training and adversarial attacks. The book aims to prompt and facilitate the research in DL with EC both in theory and in practice.

This book presents a theoretical analysis of the modern methods used for modeling various chemical engineering processes. Currently, the two primary problems in the chemical industry are the optimal design of new devices and the optimal control of active processes. Both of these problems are often solved by developing new methods of modeling. These methods for modeling specific processes may be different, but in all cases, they bring the mathematical description closer to the real processes by using appropriate experimental data. In this book, the authors detail a new approach for the modeling of chemical processes in column apparatuses. Further, they describe the types of neural networks that have been shown to be effective in solving important chemical engineering problems. Readers are also presented with mathematical models of integrated bioethanol supply chains (IBSC) that achieve improved economic and environmental sustainability. The integration of energy and mass processes is one of the most powerful tools for creating sustainable and energy efficient production systems. This book defines the main approaches for the thermal integration of periodic processes, direct and indirect, and the recent integration of small-scale solar thermal dryers with phase change materials as energy accumulators. An exciting overview of new approaches for the modeling of chemical engineering processes, this book serves as a guide for the important innovations being made in theoretical chemical engineering.

Modern economic growth is characterized by structural changes based on the introduction of new technologies into economics. The replacement and renova tion of technologies in industrial environments undergoing technical change is clearly one of the key aspects of economic development. The mathematical modeling of evolutionary economics under technical change (TC) has been rigorously considered by many authors during last decades. There is a wide variety of economic approaches and models describing different aspects of technical change. Among these are the models of embodied technical progress [19], [35], [70], [129], endogenous growth models [94], [102], the models of technological innovations [31], [32], [41], and others. The perspective self organization evolutionary approach is developed in [20], [38], [122], [123], [124], [126], which unites the aspects of diffusion of new technologies, technological and behavioral diversity of firms, learning mechanisms, age-dependent effects, and other important features of real-life economics. On the whole, an interest in evolutionary economics has brought considerable progress in the description and conceptualization of the sources, characteristics, direction and effects of technical change [125]. However, the modeling and control of technology lifetime under technical change has received rather little attention in mathematical economics in con trary to other aspects of technical progress. The lifetime of technologies has rarely been formally treated as a part of more general mathematical theory of economic dynamics. A problem which is still to be resolved consists in establishing the rational strategies of technologies' replacement under various assumptions on the behavior of technical change.

This thesis develops a pioneering methodology and a concept for identifying critical loads and load model parameters in large power networks based on their influence on power system stability. The research described in the thesis first develops an automatic load modelling tool (ALMT) that can be used to automatically build load model from actual measured power system data without human intervention and the benefits of the ALMY are explored. Secondly, it develops a pioneering framework based on Morris screening method for ranking power system load model parameters based on their influence on overall power system stability (voltage, frequency, transient and small disturbance stability) considering different load models and loading conditions. Thirdly, a novel probabilistic methodology for determining the accuracy levels of critical load model parameters has been developed. This book will be of interest to students and researchers within the field of electrical engineering, as well as industry professionals.

This book provides an in-depth analysis of the current evolutionary machine learning techniques. Discussing the most highly regarded methods for classification, clustering, regression, and prediction, it includes techniques such as support vector machines, extreme learning machines, evolutionary feature selection, artificial neural networks including feed-forward neural networks, multi-layer perceptron, probabilistic neural networks, self-optimizing neural networks, radial basis function networks, recurrent neural networks, spiking neural networks, neuro-fuzzy networks, modular neural networks, physical neural networks, and deep neural networks. The book provides essential definitions, literature reviews, and the training algorithms for machine learning using classical and modern nature-inspired techniques. It also investigates the pros and cons of classical training algorithms. It features a range of proven and recent nature-inspired algorithms used to train different types of artificial neural networks, including genetic algorithm, ant colony optimization, particle swarm optimization, grey wolf optimizer, whale optimization algorithm, ant lion optimizer, moth flame algorithm, dragonfly algorithm, salp swarm algorithm, multi-verse optimizer, and sine cosine algorithm. The book also covers applications of the improved artificial neural networks to solve classification, clustering, prediction and regression problems in diverse fields.

This book focuses on contemporary technologies and research in computational intelligence that has reached the practical level and is now accessible in preclinical and clinical settings. This book's principal objective is to thoroughly understand significant technological breakthroughs and research results in predictive modeling in healthcare imaging and data analysis. Machine learning and deep learning could be used to fully automate the diagnosis and prognosis of patients in medical fields. The healthcare industry's emphasis has evolved from a clinical-centric to a patient-centric model. However, it is still facing several technical, computational, and ethical challenges. Big data analytics in health care is becoming a revolution in technical as well as societal well-being viewpoints. Moreover, in this age of big data, there is increased access to massive amounts of regularly gathered data from the healthcare industry that has necessitated the development of predictive models and automated solutions for the early identification of critical and chronic illnesses. The book contains high-quality, original work that will assist readers in realizing novel applications and contexts for deep learning architectures and algorithms, making it an indispensable reference guide for academic researchers, professionals, industrial software engineers, and innovative model developers in healthcare industry.

This book provides a broad overview of essential features of subsurface environmental modelling at the science-policy interface, offering insights into the potential challenges in the field of subsurface flow and transport, as well as the corresponding computational modelling and its impact on the area of policy- and decision-making. The book is divided into two parts: Part I presents models, methods and software at the science-policy interface. Building on this, Part II illustrates the specifications using detailed case studies of subsurface environmental modelling. It also includes a systematic research overview and discusses the anthropogenic use of the subsurface, with a particular focus on energy-related technologies, such as carbon sequestration, geothermal technologies, fluid and energy storage, nuclear waste disposal, and unconventional oil and gas recovery.

This book presents a collection of contributions in the field of Artificial Neural Networks (ANNs). The themes addressed are multidisciplinary in nature, and closely connected in their ultimate aim to identify features from dynamic realistic signal exchanges and invariant machine representations that can be exploited to improve the quality of life of their end users. Mathematical tools like ANNs are currently exploited in many scientific domains because of their solid theoretical background and effectiveness in providing solutions to many demanding tasks such as appropriately processing (both for extracting features and recognizing) mono- and bi-dimensional dynamic signals, solving strong nonlinearities in the data and providing general solutions for deep and fully connected architectures. Given the multidisciplinary nature of their use and the interdisciplinary characterization of the problems they are applied to - which range from medicine to psychology, industrial and social robotics, computer vision, and signal processing (among many others) - ANNs may provide a basis for redefining the concept of information processing. These reflections are supported by theoretical models and applications presented in the chapters of this book. This book is of primary importance for: (a) the academic research community, (b) the ICT market, (c) PhD students and early-stage researchers, (d) schools, hospitals, rehabilitation and assisted-living centers, and (e) representatives of multimedia industries and standardization bodies.

This book provides engineers and researchers knowledge to help them in system reliability analysis using machine learning, artificial intelligence, big data, genetic algorithm, information theory, multi-criteria decision making, and other techniques. It will also be useful to students learning reliability engineering. The book brings readers up to date with how system reliability relates to the latest techniques of AI, big data, genetic algorithm, information theory, and multi-criteria decision making and points toward future developments in the subject.

This edited volume surveys a variety of topics in statistics and the social sciences in memory of the late Stephen Fienberg. The book collects submissions from a wide range of contemporary authors to explore the fields in which Fienberg made significant contributions, including contingency tables and log-linear models, privacy and confidentiality, forensics and the law, the decennial census and other surveys, the National Academies, Bayesian theory and methods, causal inference and causes of effects, mixed membership models, and computing and machine learning. Each section begins with an overview of Fienberg's contributions and continues with chapters by Fienberg's students, colleagues, and collaborators exploring recent advances and the current state of research on the topic. In addition, this volume includes a biographical introduction as well as a memorial concluding chapter comprised of entries from Stephen and Joyce Fienberg's close friends, former students, colleagues, and other loved ones, as well as a photographic tribute.

This book emphasizes those topological methods (of dynamical systems) and theories that are useful in the study of different classes of nonautonomous evolutionary equations. The content is developed over six chapters, providing a thorough introduction to the techniques used in the Chapters III-VI described by Chapter I-II. The author gives a systematic treatment of the basic mathematical theory and constructive methods for Nonautonomous Dynamics. They show how these diverse topics are connected to other important parts of mathematics, including Topology, Functional Analysis and Qualitative Theory of Differential/Difference Equations. Throughout the book a nice balance is maintained between rigorous mathematics and applications (ordinary differential/difference equations, functional differential equations and partial difference equations). The primary readership includes graduate and PhD students and researchers in in the field of dynamical systems and their applications (control theory, economic dynamics, mathematical theory of climate, population dynamics, oscillation theory etc).

This volume collects papers, based on invited talks given at the IMA workshop in Modeling, Stochastic Control, Optimization, and Related Applications, held at the Institute for Mathematics and Its Applications, University of Minnesota, during May and June, 2018. There were four week-long workshops during the conference. They are (1) stochastic control, computation methods, and applications, (2) queueing theory and networked systems, (3) ecological and biological applications, and (4) finance and economics applications. For broader impacts, researchers from different fields covering both theoretically oriented and application intensive areas were invited to participate in the conference. It brought together researchers from multi-disciplinary communities in applied mathematics, applied probability, engineering, biology, ecology, and networked science, to review, and substantially update most recent progress. As an archive, this volume presents some of the highlights of the workshops, and collect papers covering a broad range of topics.

This book provides novel concepts and techniques for air traffic management (ATM) and communications, navigation, and surveillance (CNS) systems. The book consists of selected papers from the 6th ENRI International Workshop on ATM/CNS (EIWAC2019) held in Tokyo in October 2019, the theme of which was "Exploring Ideas for World Aviation Challenges". Included are key topics to realize safer and more efficient skies in the future, linked to the integrated conference theme consisting of long-term visions based on presentations from various fields. The book is dedicated not only to researchers, academicians, and university students, but also to engineers in the industry, air navigation service providers (ANSPs), and regulators of aviation.

This book contains a selection of research articles written by prominent researchers participating in The 27th World Congress on Engineering (WCE 2019) which was held in London, UK, July 3-5, 2019. Topics covered include engineering mathematics, electrical engineering, communications systems, computer science, chemical engineering, systems engineering, manufacturing engineering, and industrial applications. With contributions carefully chosen to represent the most cutting-edge research presented during the conference, the book contains some of the state of the art in engineering technologies and the physical sciences and their applications and serves as a useful reference for researchers and graduate students working in these fields.

Despite the wealth of natural historical research conducted on migration over decades, there is still a dearth of hypothesis-driven studies that fully integrate theory and empirical analyses to understand the causes and consequences of migration, and a taxonomic bias towards birds in much migration research. This book takes a comparative, integrated view of animal migration, linking evolution with ecology and management, theory with empirical research, and embracing all the major migratory taxa (including human pastoralists). The scope extends beyond the target organism to consider the ecosystem-level dynamics of migration. The emphasis is on exciting new research avenues that are now opening up, whether due to advances in our understanding of migration as a biological phenomenon or through the availability of a range of new technologies.
Broad themes that emerge include integrating migration into the broad spectrum of movement behavior, the need for a comparative and cross-taxonomic approach that considers migration at a range of temporal and spatial scales, and examination of the key roles of resource uncertainty and spatial heterogeneity in driving migratory behavior. The book identifies the potential for new tools to revolutionize the study of migration, including satellite-tracking technology, genomics, and modeling - all of which are linked to increasing computing power. We are now on the verge of a breakthrough in migration research, which is crucial given the multiple threats that face the conservation of migration as a phenomenon, including climate change.

This book addresses the applications of Fourier transform to smile modeling. Smile effect is used generically by ?nancial engineers and risk managers to refer to the inconsistences of quoted implied volatilities in ?nancial markets, or more mat- matically, to the leptokurtic distributions of ?nancial assets and indices. Therefore, a sound modeling of smile effect is the central challenge in quantitative ?nance. Since more than one decade, Fourier transform has triggered a technical revolution in option pricing theory. Almost all new developed option pricing models, es- cially in connection with stochastic volatility and random jump, have extensively applied Fourier transform and the corresponding inverse transform to express - tion pricing formulas. The large accommodation of the Fourier transform allows for a very convenient modeling with a general class of stochastic processes and d- tributions. This book is then intended to present a comprehensive treatment of the Fourier transform in the option valuation, covering the most stochastic factors such as stochastic volatilities and interest rates, Poisson and Levy jumps, including some asset classes such as equity, FX and interest rates, and providing numerical ex- ples and prototype programming codes. I hope that readers will bene't from this book not only by gaining an overview of the advanced theory and the vast large l- erature on these topics, but also by gaining a ?rst-hand feedback from the practice on the applications and implementations of the theory."

This book presents an exhaustive study of atomicity from a mathematics perspective in the framework of multi-valued non-additive measure theory. Applications to quantum physics and, more generally, to the fractal theory of the motion, are highlighted. The study details the atomicity problem through key concepts, such as the atom/pseudoatom, atomic/nonatomic measures, and different types of non-additive set-valued multifunctions. Additionally, applications of these concepts are brought to light in the study of the dynamics of complex systems. The first chapter prepares the basics for the next chapters. In the last chapter, applications of atomicity in quantum physics are developed and new concepts, such as the fractal atom are introduced. The mathematical perspective is presented first and the discussion moves on to connect measure theory and quantum physics through quantum measure theory. New avenues of research, such as fractal/multifractal measure theory with potential applications in life sciences, are opened.

This proceedings volume contains a selection of papers presented at the Fourth International Conference on High Performance Scientific Computing held at the Hanoi Institute of Mathematics, Vietnamese Academy of Science and Technology (VAST), March 2-6, 2009. The conference was organized by the Hanoi Institute of Mathematics, the Interdisciplinary Center for Scientific Computing (IWR), Heidelberg, and its Heidelberg Graduate School of Mathematical and Computational Methods for the Sciences, and Ho Chi Minh City University of Technology. The contributions cover the broad interdisciplinary spectrum of scientific computing and present recent advances in theory, development of methods, and applications in practice. Subjects covered are mathematical modelling, numerical simulation, methods for optimization and control, parallel computing, software development, applications of scientific computing in physics, mechanics, biology and medicine, engineering, hydrology problems, transport, communication networks, production scheduling, industrial and commercial problems.

This book introduces the engineering application of the discrete element method (DEM), especially the simulation analysis of the typical equipment (scraper conveyor, coal silos, subsoiler) in the coal and agricultural machinery. In this book, the DEM is applied to build rigid and loose coupling model, and the kinematic effect of the bulk materials, the mechanical effect of the interaction between the bulk materials, and the mechanical equipment in the operation process of the relevant equipment are studied. On this basis, the optimization design strategy of the relevant structure is proposed. This book effectively promotes the application of DEM in engineering, analyzes the operation state, failure mechanism, and operation effect of related equipment in operation, and provides theoretical basis for the optimal design of equipment. The book is intended for undergraduate and graduate students who are interested in mechanical engineering, researchers investigating coal and agricultural machinery, and engineers working on designing related equipments.