This book presents revised and extended versions of the best papers presented at the 9th International Joint Conference on Computational Intelligence (IJCCI 2017), held in Funchal, Madeira, from 1 to 3 November 2017. It focuses on four of the main fields of computational intelligence: evolutionary computation, fuzzy computation, neural computation, and cognitive and hybrid systems. As well as presenting the recent advances of these areas, it provides new and innovative solutions for established researchers and a source of information and/or inspiration those new to the field. Discussing innovative techniques in various application areas, it is a useful resource for individual researchers and a valuable addition to academic libraries (of universities and engineering schools).

Based on the idea of a universal rule for problem solving, the book suggests that the "System-Fuzzy Approach (SFA)" Model can be applied to various complex real-world problems. It is the first book for problem solving in complicated problems with a universal project management tool. Systematic searching is an essential step in identifying the right direction in problem solving; and the fuzzy steps in concrete problem solving reflect the flexibility and compromises involved in the process. Nevertheless, the fuzzy steps also demonstrate human beings' impressively flexible problem-solving skills. Simulating human decision-making processes based on fuzzy information processing is essential in our digital era, in which many problems need to be solved by means of artificial intelligence; hence the Fuzzy-AI Model emerged. As a universal rule and tool, it can be applied to a broad range of real-world problems. Offering a valuable guide to fuzzy decision-making, this book is intended for researchers, scientists and graduate students in the fields of Engineering, Economics, Sociology, Managerial Science, Project Management etc.

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.

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.

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 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 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.

Medical imaging is an indispensable tool for modern healthcare. Machine leaning plays an essential role in the medical imaging field, with applications including medical image analysis, computer-aided diagnosis, organ/lesion segmentation, image fusion, image-guided therapy, and image annotation and image retrieval. Machine Learning in Computer-Aided Diagnosis: Medical Imaging Intelligence and Analysis provides a comprehensive overview of machine learning research and technology in medical decision-making based on medical images. This book covers major technical advancements and research findings in the field of Computer-Aided Diagnosis (CAD). As it demonstrates the practical applications of CAD, this book is a useful reference for professors in engineering and medical schools, students in engineering and applied-science, medical students, medical engineers, researchers in industry, academia, and health science, radiologists, cardiologists, surgeons, and healthcare professionals.

This book focuses on innovative strategies to manage and build software systems for generating new knowledge from large archaeological data sets The book also reports on two case studies carried out in real-world scenarios within the Cultural Heritage setting. The book presents an original conceptual framework for developing software solutions to assist the knowledge generation process in connection with large archaeological data sets and related cultural heritage information- a context in which the inputs are mainly textual sources written in freestyle, i.e. without a predetermined, standard structure. Following an in-depth exploration of recent works on the knowledge generation process in the above-mentioned context and IT-based options for facilitating it, the book proposes specific new techniques capable of capturing the structure and semantics implicit in such textual sources, and argues for using this information in the knowledge generation process. The main result is the development of a conceptual framework that can accommodate textual sources and integrate the information included in them into a software engineering framework. The said framework is meant to assist cultural heritage professionals in general, and archaeologists in particular, in both knowledge extraction and the subsequent decision-making process.

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 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 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.

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 book gathers 12 of the most promising papers presented at the 15th International Conference on Software Engineering, Artificial Intelligence Research, Management and Applications (SERA 2017) held on June 7-9, 2017 at the University of Greenwich, London, UK. The aim of this conference was to bring together researchers and scientists, businessmen and entrepreneurs, teachers, engineers, computer users, and students to discuss the numerous fields of computer science, to share their experiences and to exchange new ideas and information in a meaningful way. The book also presents research findings regarding all aspects (theory, applications and tools) of computer and information science, and discusses the practical challenges encountered along the way and the solutions adopted to solve them.

This book puts in one place and in accessible form Richard Berk's most recent work on forecasts of re-offending by individuals already in criminal justice custody. Using machine learning statistical procedures trained on very large datasets, an explicit introduction of the relative costs of forecasting errors as the forecasts are constructed, and an emphasis on maximizing forecasting accuracy, the author shows how his decades of research on the topic improves forecasts of risk. Criminal justice risk forecasts anticipate the future behavior of specified individuals, rather than "predictive policing" for locations in time and space, which is a very different enterprise that uses different data different data analysis tools. The audience for this book includes graduate students and researchers in the social sciences, and data analysts in criminal justice agencies. Formal mathematics is used only as necessary or in concert with more intuitive explanations.

Our society continues to depend upon systems that are built in a way that they end up being inflexible and intolerant to change. Therefore there is an urgent need to investigate innovations and approaches to the management of adaptive and dependable systems. These studies are usually implemented through design, development, and the evaluation of techniques and models to structure computer systems as adaptive systems. Innovations and Approaches for Resilient and Adaptive Systems is a comprehensive collection of knowledge on increasing the notions and models in adaptive and dependable systems. This book aims to enhance the awareness of the role of adaptability and resilience in system environments for researchers, practitioners, educators, and professionals alike.

Brain Storm Optimization (BSO) algorithms are a new kind of swarm intelligence method, which is based on the collective behavior of human beings, i.e., on the brainstorming process. Since the introduction of BSO algorithms in 2011, many studies on them have been conducted. They not only offer an optimization method, but could also be viewed as a framework of optimization techniques. The process employed in the algorithms could be simplified as a framework with two basic operations: the converging operation and the diverging operation. A "good enough" optimum could be obtained through recursive solution divergence and convergence. The resulting optimization algorithm would naturally have the capability of both convergence and divergence. This book is primarily intended for researchers, engineers, and graduate students with an interest in BSO algorithms and their applications. The chapters cover various aspects of BSO algorithms, and collectively provide broad insights into what these algorithms have to offer. The book is ideally suited as a graduate-level textbook, whereby students may be tasked with the study of the rich variants of BSO algorithms that involves a hands-on implementation to demonstrate the utility and applicability of BSO algorithms in solving optimization problems.

Applications of Computer Vision in Fashion and Textiles provides a systematic and comprehensive discussion of three key areas that are taking advantage of developments in computer vision technology, namely textile defect detection and quality control, fashion recognition and 3D modeling, and 2D and 3D human body modeling for improving clothing fit. It introduces the fundamentals of computer vision techniques for fashion and textile applications, also reviewing computer vision techniques for textile quality control, including chapters on wavelet transforms, Gibor filters, Fourier transforms, and neural network techniques. Final sections cover recognition, modeling, retrieval technologies and advanced human shape modeling techniques. The book is essential reading for scientists and researchers working in the field of fashion production, quality assurance, product development, textiles, fashion supply chain managers, R&D professionals and managers in the textile industry.

Ecologists and natural resource managers are charged with making complex management decisions in the face of a rapidly changing environment resulting from climate change, energy development, urban sprawl, invasive species and globalization. Advances in Geographic Information System (GIS) technology, digitization, online data availability, historic legacy datasets, remote sensors and the ability to collect data on animal movements via satellite and GPS have given rise to large, highly complex datasets. These datasets could be utilized for making critical management decisions, but are often "messy" and difficult to interpret. Basic artificial intelligence algorithms (i.e., machine learning) are powerful tools that are shaping the world and must be taken advantage of in the life sciences. In ecology, machine learning algorithms are critical to helping resource managers synthesize information to better understand complex ecological systems. Machine Learning has a wide variety of powerful applications, with three general uses that are of particular interest to ecologists: (1) data exploration to gain system knowledge and generate new hypotheses, (2) predicting ecological patterns in space and time, and (3) pattern recognition for ecological sampling. Machine learning can be used to make predictive assessments even when relationships between variables are poorly understood. When traditional techniques fail to capture the relationship between variables, effective use of machine learning can unearth and capture previously unattainable insights into an ecosystem's complexity. Currently, many ecologists do not utilize machine learning as a part of the scientific process. This volume highlights how machine learning techniques can complement the traditional methodologies currently applied in this field.