This book presents the outcomes of the 16th International Conference on Software Engineering, Artificial Intelligence Research, Management and Applications (SERA 2018), which was held in Kunming, China on June 13-15, 2018. The aim of the conference was to bring together researchers and scientists, businessmen and entrepreneurs, teachers, engineers, computer users, and students to discuss the various fields of computer science, to share their experiences, and to exchange new ideas and information in a meaningful way. The book includes findings on all aspects (theory, applications and tools) of computer and information science, and discusses related practical challenges and the solutions adopted to solve them. The conference organizers selected the best papers from those accepted for presentation. The papers were chosen based on review scores submitted by members of the program committee and underwent a further rigorous round of review. From this second round, 13 of the conference's most promising papers were then published in this Springer (SCI) book and not the conference proceedings. We eagerly await the important contributions that we know these authors will make to the field of computer and information science.

This book addresses the topic of fractional-order modeling of nuclear reactors. Approaching neutron transport in the reactor core as anomalous diffusion, specifically subdiffusion, it starts with the development of fractional-order neutron telegraph equations. Using a systematic approach, the book then examines the development and analysis of various fractional-order models representing nuclear reactor dynamics, ultimately leading to the fractional-order linear and nonlinear control-oriented models. The book utilizes the mathematical tool of fractional calculus, the calculus of derivatives and integrals with arbitrary non-integer orders (real or complex), which has recently been found to provide a more compact and realistic representation to the dynamics of diverse physical systems. Including extensive simulation results and discussing important issues related to the fractional-order modeling of nuclear reactors, the book offers a valuable resource for students and researchers working in the areas of fractional-order modeling and control and nuclear reactor modeling.

Now, for the first time, publication of the landmark work in backpropagation Scientists, engineers, statisticians, operations researchers, and other investigators involved in neural networks have long sought direct access to Paul Werbos's groundbreaking, much-cited 1974 Harvard doctoral thesis, The Roots of Backpropagation, which laid the foundation of backpropagation. Now, with the publication of its full text, these practitioners can go straight to the original material and gain a deeper, practical understanding of this unique mathematical approach to social studies and related fields. In addition, Werbos has provided three more recent research papers, which were inspired by his original work, and a new guide to the field. Originally written for readers who lacked any knowledge of neural nets, The Roots of Backpropagation firmly established both its historical and continuing significance as it:
* Demonstrates the ongoing value and new potential of backpropagation
* Creates a wealth of sound mathematical tools useful across disciplines
* Sets the stage for the emerging area of fast automatic differentiation
* Describes new designs for forecasting and control which exploit backpropagation
* Unifies concepts from Freud, Jung, biologists, and others into a new mathematical picture of the human mind and how it works
* Certifies the viability of Deutsch's model of nationalism as a predictive tool--as well as the utility of extensions of this central paradigm
"What a delight it was to see Paul Werbos rediscover Freud's version of 'back-propagation.' Freud was adamant (in The Project for a Scientific Psychology) that selective learning could only take place if the presynaptic neuron was as influenced as is the postsynaptic neuron during excitation. Such activation of both sides of the contact barrier (Freud's name for the synapse) was accomplished by reducing synaptic resistance by the absorption of 'energy' at the synaptic membranes. Not bad for 1895 But Werbos 1993 is even better." --Karl H. Pribram Professor Emeritus, Stanford University

This book introduces readers to the latest exciting advances in human motion sensing and recognition, from the theoretical development of fuzzy approaches to their applications. The topics covered include human motion recognition in 2D and 3D, hand motion analysis with contact sensors, and vision-based view-invariant motion recognition, especially from the perspective of Fuzzy Qualitative techniques. With the rapid development of technologies in microelectronics, computers, networks, and robotics over the last decade, increasing attention has been focused on human motion sensing and recognition in many emerging and active disciplines where human motions need to be automatically tracked, analyzed or understood, such as smart surveillance, intelligent human-computer interaction, robot motion learning, and interactive gaming. Current challenges mainly stem from the dynamic environment, data multi-modality, uncertain sensory information, and real-time issues. These techniques are shown to effectively address the above challenges by bridging the gap between symbolic cognitive functions and numerical sensing & control tasks in intelligent systems. The book not only serves as a valuable reference source for researchers and professionals in the fields of computer vision and robotics, but will also benefit practitioners and graduates/postgraduates seeking advanced information on fuzzy techniques and their applications in motion analysis.

This book provides insights into the First International Conference on Communication, Devices and Computing (ICCDC 2017), which was held in Haldia, India on November 2-3, 2017. It covers new ideas, applications and the experiences of research engineers, scientists, industrialists, scholars and students from around the globe. The proceedings highlight cutting-edge research on communication, electronic devices and computing, and address diverse areas such as 5G communication, spread spectrum systems, wireless sensor networks, signal processing for secure communication, error control coding, printed antennas, analysis of wireless networks, antenna array systems, analog and digital signal processing for communication systems, frequency selective surfaces, radar communication, and substrate integrated waveguide and microwave passive components, which are key to state-of-the-art innovations in communication technologies.

This book explains the fundamentals of the Internet of Things - from different architectures for managing IoT platforms to the insights on trust, security, and privacy in IoT environments, including consumer electronic devices or home applications. This opens the doors to new innovations that will build novel interactions among things and humans, and enables the realization of smart cities, infrastructures, and services. The book presents a complete overview on the research and the technology of this rapidly emerging topic.

This volume highlights new trends and challenges in research on agents and the new digital and knowledge economy, and includes 23 papers classified into the following categories: business process management, agent-based modeling and simulation, and anthropic-oriented computing. All papers were originally presented at the 11th International KES Conference on Agents and Multi-Agent Systems - Technologies and Applications (KES-AMSTA 2017) held June 21-23, 2017 in Vilamoura, Algarve, Portugal. Today's economy is driven by technologies and knowledge. Digital technologies can free, shift and multiply choices, and often intrude on the territory of other industries by providing new ways of conducting business operations and creating value for customers and companies. The topics covered in this volume include software agents, multi-agent systems, agent modeling, mobile and cloud computing, big data analysis, business intelligence, artificial intelligence, social systems, computer embedded systems and nature inspired manufacturing, etc., all of which contribute to the modern Digital Economy. The results presented here will be of theoretical and practical value to researchers and industrial practitioners working in the fields of artificial intelligence, collective computational intelligence, innovative business models, the new digital and knowledge economy and, in particular, agent and multi-agent systems, technologies, tools and applications.

This book presents state-of-the-art research advances in the field of biologically inspired cooperative control theories and their applications. It describes various biologically inspired cooperative control and optimization approaches and highlights real-world examples in complex industrial processes. Multidisciplinary in nature and closely integrating theory and practice, the book will be of interest to all university researchers, control engineers and graduate students in intelligent systems and control who wish to learn the core principles, methods, algorithms, and applications.

This book describes load modeling approaches for complex work pieces and batch forgings, and demonstrates analytical modeling and data-driven modeling approaches for known and unknown complex forging processes. It overcomes the current shortcomings of modeling, analysis and control approaches, presenting contributions in three major areas: In the first, several novel modeling approaches are proposed: a process/shape-decomposition modeling method to help estimate the deformation force; an online probabilistic learning machine for the modeling of batch forging processes; and several data-driven identification and modeling approaches for unknown forging processes under different work conditions. The second area develops model-based dynamic analysis methods to derive the conditions of stability and creep. Lastly, several novel intelligent control methods are proposed for complex forging processes. One of the most serious problems in forging forming involves the inaccurate forging conditions, velocity and position offered by the hydraulic actuator due to the complexity of both the deformation process of the metal work piece and the motion process of the hydraulic actuator. The book summarizes the current weaknesses of modeling, analysis and control approaches. are summarized as follows: a) With the current modeling approaches it is difficult to model complex forging processes with unknown parameters, as they only model the dynamics in local working areas but do not effectively model unknown nonlinear systems across multiple working areas; further, they do not take the batch forging process into account, let alone its distribution modeling. b) All previous dynamic analysis studies simplify the forging system to having a single-frequency pressure fluctuation and neglect the influences of non-linear load force. Further, they fail to take the flow equation in both valves and cylinders into account. c) Conventional control approaches only consider the linear deformation force and pay no attention to sudden changes and the motion synchronization for the multi-cylinder system, making them less effective for complex, nonlinear time-varying forging processes subject to sudden changes.

This book reviews the state of the art in deep learning approaches to high-performance robust disease detection, robust and accurate organ segmentation in medical image computing (radiological and pathological imaging modalities), and the construction and mining of large-scale radiology databases. It particularly focuses on the application of convolutional neural networks, and on recurrent neural networks like LSTM, using numerous practical examples to complement the theory. The book's chief features are as follows: It highlights how deep neural networks can be used to address new questions and protocols, and to tackle current challenges in medical image computing; presents a comprehensive review of the latest research and literature; and describes a range of different methods that employ deep learning for object or landmark detection tasks in 2D and 3D medical imaging. In addition, the book examines a broad selection of techniques for semantic segmentation using deep learning principles in medical imaging; introduces a novel approach to text and image deep embedding for a large-scale chest x-ray image database; and discusses how deep learning relational graphs can be used to organize a sizable collection of radiology findings from real clinical practice, allowing semantic similarity-based retrieval.The intended reader of this edited book is a professional engineer, scientist or a graduate student who is able to comprehend general concepts of image processing, computer vision and medical image analysis. They can apply computer science and mathematical principles into problem solving practices. It may be necessary to have a certain level of familiarity with a number of more advanced subjects: image formation and enhancement, image understanding, visual recognition in medical applications, statistical learning, deep neural networks, structured prediction and image segmentation.

The focus of this book is on providing students with insights into geometry that can help them understand deep learning from a unified perspective. Rather than describing deep learning as an implementation technique, as is usually the case in many existing deep learning books, here, deep learning is explained as an ultimate form of signal processing techniques that can be imagined. To support this claim, an overview of classical kernel machine learning approaches is presented, and their advantages and limitations are explained. Following a detailed explanation of the basic building blocks of deep neural networks from a biological and algorithmic point of view, the latest tools such as attention, normalization, Transformer, BERT, GPT-3, and others are described. Here, too, the focus is on the fact that in these heuristic approaches, there is an important, beautiful geometric structure behind the intuition that enables a systematic understanding. A unified geometric analysis to understand the working mechanism of deep learning from high-dimensional geometry is offered. Then, different forms of generative models like GAN, VAE, normalizing flows, optimal transport, and so on are described from a unified geometric perspective, showing that they actually come from statistical distance-minimization problems. Because this book contains up-to-date information from both a practical and theoretical point of view, it can be used as an advanced deep learning textbook in universities or as a reference source for researchers interested in acquiring the latest deep learning algorithms and their underlying principles. In addition, the book has been prepared for a codeshare course for both engineering and mathematics students, thus much of the content is interdisciplinary and will appeal to students from both disciplines.

In this revolutionary work, the author sets the stage for the science of
the 21st Century, pursuing an unprecedented synthesis of fields previously
considered unrelated. Beginning with simple classical concepts, he ends
with a complex multidisciplinary theory requiring a high level of
abstraction. The work progresses across the sciences in several
multidisciplinary directions: Mathematical logic, fundamental physics,
computer science and the theory of intelligence. Extraordinarily enough,
the author breaks new ground in all these fields.

In the field of
fundamental physics the author reaches the revolutionary conclusion that
physics can be viewed and studied as logic in a fundamental sense, as
compared with Einstein's view of physics as space-time geometry. This opens
new, exciting prospects for the study of fundamental interactions. A
formulation of logic in terms of matrix operators and logic vector spaces
allows the author to tackle for the first time the intractable problem of
cognition in a scientific manner. In the same way as the findings of
Heisenberg and Dirac in the 1930s provided a conceptual and mathematical
foundation for quantum physics, matrix operator logic supports an important
breakthrough in the study of the physics of the mind, which is interpreted
as a fractal of quantum mechanics. Introducing a concept of logic quantum
numbers, the author concludes that the problem of logic and the
intelligence code in general can be effectively formulated as eigenvalue
problems similar to those of theoretical physics. With this important leap
forward in the study of the mechanism of mind, the author concludes that
the latter cannot be fully understood either within classical or quantum
notions. A higher-order covariant theory is required to accommodate the
fundamental effect of high-level intelligence. The landmark results
obtained by the author will have implications and repercussions for the
very foundations of science as a whole. Moreover, Stern's Matrix Logic is
suitable for a broad spectrum of practical applications in contemporary
technologies.

This book presents an authoritative collection of contributions reporting on fuzzy logic and decision theory, together with applications and case studies in economics and management science. Dedicated to Professor Jaume Gil Aluja in recognition of his pioneering work, the book reports on theories, methods and new challenges, thus offering not only a timely reference guide but also a source of new ideas and inspirations for graduate students and researchers alike.

This volume is about ultra high-speed cameras, which enable us to see what we normally do not see. These are objects that are moving very fast, or that we just ignore. Ultra high-speed cameras invite us to a wonderland of microseconds. There Alice (the reader) meets a ultra high-speed rabbit (this volume) and travels together through this wonderland from the year 1887 to 2017. They go to the horse riding ground and see how a horse gallops. The rabbit takes her to a showroom where various cameras and illumination devices are presented. Then, he sends Alice into semiconductor labyrinths, wind tunnels, mechanical processing factories, and dangerous explosive fields. Sometimes Alice is large, and at other times she is very small. She sits even inside a car engine. She falls down together with a droplet. She enters a microbubble, is thrown out with a jet stream, and finds herself in a human body. Waking up from her dream, she sees children playing a game: "I see what you do not see, and this is....". Alice thinks: "The ultra high-speed rabbit showed me many things which I had never seen. Now I will go again to this wonderland, and try to find something new.

This book is a collection of several contributions which show the state of the art in specific areas of Computational Intelligence. This carefully edited book honors the 65th birthday of Rudolf Kruse. The main focus of these contributions lies on treating vague data as well as uncertain and imprecise information with automated procedures, which use techniques from statistics, control theory, clustering, neural networks etc. to extract useful and employable knowledge.

This book provides a comprehensive account of the glowworm swarm optimization (GSO) algorithm, including details of the underlying ideas, theoretical foundations, algorithm development, various applications, and MATLAB programs for the basic GSO algorithm. It also discusses several research problems at different levels of sophistication that can be attempted by interested researchers. The generality of the GSO algorithm is evident in its application to diverse problems ranging from optimization to robotics. Examples include computation of multiple optima, annual crop planning, cooperative exploration, distributed search, multiple source localization, contaminant boundary mapping, wireless sensor networks, clustering, knapsack, numerical integration, solving fixed point equations, solving systems of nonlinear equations, and engineering design optimization. The book is a valuable resource for researchers as well as graduate and undergraduate students in the area of swarm intelligence and computational intelligence and working on these topics.

These proceedings present the latest information on intelligent- transportation technologies and their applications in real-world cases. The Second International Conference on Intelligent Transportation was held in Chengdu, China on November 25-27, 2015, to present the latest research in the field, including intelligent-transportation management, intelligent vehicles, rail transportation systems, traffic transportation networks, as well as road traffic element simulations and their industrial development. The aim of conference was to bring together academics, researchers, engineers and students from across the world to discuss state-of-the-art technologies related to intelligent transportation.

This unique work introduces the basic principles of artificial intelligence with applications in geographical teaching and research, GIS, and planning. Written in an accessible, non-technical and witty style, this book marks the beginning of the Al revolution in geography with major implications for teaching and research. The authors provide an easy to understand basic introduction to Al relevant to geography. There are no special mathematical and statistical skills needed, indeed these might well be a hindrance. Al is a different way of looking at the world and it requires a willingness to experiment, and readers who are unhindered by the baggage of obsolete technologies and outmoded philosophies of science will probably do best. The text provides an introduction to expert systems, neural nets, genetic algorithms, smart systems and artificial life and shows how they are likely to transform geographical enquiry.

• A major methodological milestone in geography
• The first geographical book on artificial intelligence (Al)
• No need for previous mathematical or statistical skills/knowledge
• Accessible style makes a difficult subject available to a wide audience
• Stan Openshaw is one of the world s leading researchers into geographical computing, spatial analysis and GIS.

This book is a survey and analysis of how deep learning can be used to generate musical content. The authors offer a comprehensive presentation of the foundations of deep learning techniques for music generation. They also develop a conceptual framework used to classify and analyze various types of architecture, encoding models, generation strategies, and ways to control the generation. The five dimensions of this framework are: objective (the kind of musical content to be generated, e.g., melody, accompaniment); representation (the musical elements to be considered and how to encode them, e.g., chord, silence, piano roll, one-hot encoding); architecture (the structure organizing neurons, their connexions, and the flow of their activations, e.g., feedforward, recurrent, variational autoencoder); challenge (the desired properties and issues, e.g., variability, incrementality, adaptability); and strategy (the way to model and control the process of generation, e.g., single-step feedforward, iterative feedforward, decoder feedforward, sampling). To illustrate the possible design decisions and to allow comparison and correlation analysis they analyze and classify more than 40 systems, and they discuss important open challenges such as interactivity, originality, and structure. The authors have extensive knowledge and experience in all related research, technical, performance, and business aspects. The book is suitable for students, practitioners, and researchers in the artificial intelligence, machine learning, and music creation domains. The reader does not require any prior knowledge about artificial neural networks, deep learning, or computer music. The text is fully supported with a comprehensive table of acronyms, bibliography, glossary, and index, and supplementary material is available from the authors' website.

This unique book succinctly summarizes the need to measure how ontologies (one of the building blocks of the Semantic Web) are currently being utilized, providing insights for various stakeholders. Where possible it improves and reuses terms in existing vocabularies/ontologies, as recommended by the Linked Data community. Recent advances in the Semantic Web have led to a proliferation of Resource Description Framework (RDF) data, which employ ontologies to semantically describe the information on the Web making it equally understandable for both humans and machines. However, to create a network effect, it is important that selective ontologies are used by more data publishers to improve the value of that ontology. For this to happen, it is vital to discover what is being used from an ontology to semantically annotate the information on the Web specific to a given domain. Answers to such basic but crucial questions can only be achieved by ascertaining how ontologies in the current semantic web are being utilized and adopted. The proposed frameworks to obtain such insights are explained with real-world examples to provide a clear and detailed description of ontology usage analysis. Both theoretical and practical, the book is of value to academics and professionals working in industry. Specifically, it is of primary interest to researchers, graduate students and practitioners in the area of the Semantic Web and its various real-world applications.

This book provides a general and comprehensible overview of imbalanced learning. It contains a formal description of a problem, and focuses on its main features, and the most relevant proposed solutions. Additionally, it considers the different scenarios in Data Science for which the imbalanced classification can create a real challenge. This book stresses the gap with standard classification tasks by reviewing the case studies and ad-hoc performance metrics that are applied in this area. It also covers the different approaches that have been traditionally applied to address the binary skewed class distribution. Specifically, it reviews cost-sensitive learning, data-level preprocessing methods and algorithm-level solutions, taking also into account those ensemble-learning solutions that embed any of the former alternatives. Furthermore, it focuses on the extension of the problem for multi-class problems, where the former classical methods are no longer to be applied in a straightforward way. This book also focuses on the data intrinsic characteristics that are the main causes which, added to the uneven class distribution, truly hinders the performance of classification algorithms in this scenario. Then, some notes on data reduction are provided in order to understand the advantages related to the use of this type of approaches. Finally this book introduces some novel areas of study that are gathering a deeper attention on the imbalanced data issue. Specifically, it considers the classification of data streams, non-classical classification problems, and the scalability related to Big Data. Examples of software libraries and modules to address imbalanced classification are provided. This book is highly suitable for technical professionals, senior undergraduate and graduate students in the areas of data science, computer science and engineering. It will also be useful for scientists and researchers to gain insight on the current developments in this area of study, as well as future research directions.

This volume presents the first part of the proceedings of the Mediterranean Conference on Information & Communication Technologies (MedICT 2015), which was held at Saidia, Morocco during 7-9 May, 2015. MedICT provides an excellent international forum to the researchers and practitioners from both academia as well as industry to meet and share cutting-edge development. The conference has also a special focus on enabling technologies for societal challenges, and seeks to address multidisciplinary challenges in Information & Communication Technologies such as health, demographic change, wellbeing, security and sustainability issues. The proceedings publish high quality papers which are closely related to the various theories, as well as emerging and practical applications of particular interest to the ICT community. This first volume provides a compact yet broad view of recent developments in devices, technologies and processing, and covers recent research areas in the field including Microwave Devices and Printed Antennas, Advances in Optical and RF Devices and Applications, Signal Processing and Information Theory, Wireless and Optical Technologies and Techniques, Computer Vision, Optimization and Modeling in Wireless Communication Systems, Modeling, Identification and Biomedical Signal Processing, Photovoltaic Cell & Systems, RF Devices and Antennas for Wireless Applications, RFID, Ad Hoc and Networks Issues.

The topic of this monograph falls within the, so-called, biologically motivated computing paradigm, in which biology provides the source of models and inspiration towards the development of computational intelligence and machine learning systems. Specifically, artificial immune systems are presented as a valid metaphor towards the creation of abstract and high level representations of biological components or functions that lay the foundations for an alternative machine learning paradigm. Therefore, focus is given on addressing the primary problems of Pattern Recognition by developing Artificial Immune System-based machine learning algorithms for the problems of Clustering, Classification and One-Class Classification. Pattern Classification, in particular, is studied within the context of the Class Imbalance Problem. The main source of inspiration stems from the fact that the Adaptive Immune System constitutes one of the most sophisticated biological systems that is exceptionally evolved in order to continuously address an extremely unbalanced pattern classification problem, namely, the self / non-self discrimination process. The experimental results presented in this monograph involve a wide range of degenerate binary classification problems where the minority class of interest is to be recognized against the vast volume of the majority class of negative patterns. In this context, Artificial Immune Systems are utilized for the development of personalized software as the core mechanism behind the implementation of Recommender Systems. The book will be useful to researchers, practitioners and graduate students dealing with Pattern Recognition and Machine Learning and their applications in Personalized Software and Recommender Systems. It is intended for both the expert/researcher in these fields, as well as for the general reader in the field of Computational Intelligence and, more generally, Computer Science who wishes to learn more about the field of Intelligent Computing Systems and its applications. An extensive list of bibliographic references at the end of each chapter guides the reader to probe further into application area of interest to him/her.