This monograph by Florian Rohrbein, Germano Veiga and Ciro Natale is an edited collection of 15 authoritative contributions in the area of robot technology transfer between academia and industry. It comprises three parts on "Future Industrial Robotics," "Robotic Grasping" as well as "Human-Centered Robots." The book chapters cover almost all the topics nowadays considered hot within the robotics community, from reliable object recognition to dexterous grasping, from speech recognition to intuitive robot programming, from mobile robot navigation to aerial robotics, from safe physical human-robot interaction to body extenders. All contributions stem from the results of ECHORD the European Clearing House for Open Robotics Development, a large-scale integrating project funded by the European Commission within the 7th Framework Programme from 2009 to 2013. ECHORD s two main pillars were the so-called experiments, 51 small-sized industry-driven research projects and the structured dialog a powerful interaction instrument between the stakeholders. The results described in this volume are expected to shed new light on innovation and technology transfer from academia to industry in the field of robotics."

This book provides an introduction to Swarm Robotics, which is the application of methods from swarm intelligence to robotics. It goes on to present methods that allow readers to understand how to design large-scale robot systems by going through many example scenarios on topics such as aggregation, coordinated motion (flocking), task allocation, self-assembly, collective construction, and environmental monitoring. The author explains the methodology behind building multiple, simple robots and how the complexity emerges from the multiple interactions between these robots such that they are able to solve difficult tasks. The book can be used as a short textbook for specialized courses or as an introduction to Swarm Robotics for graduate students, researchers, and professionals who want a concise introduction to the field.

Cognitive science is a multidisciplinary science concerned with understanding and utilizing models of cognition. It has spawned a great dealof research on applications such as expert systems and intelligent tutoring systems, and has interacted closely with psychological research. However, it is generally accepted that it is difficult to apply cognitive-scientific models to medical training and practice. This book is based on a NATO Advanced Research Workshop held in Italy in 1991, the purpose of which was to examine the impact ofmodels of cognition on medical training and practice and to outline future research programmes relating cognition and education, and in particular to consider the potential impact of cognitive science on medical training and practice. A major discovery presented in the book is that the research areas related to artificial intelligence, cognitive psychology, and medical decision making are considerably closer, both conceptually and theoretically, than many of the workshop participants originally thought.

This book provides simultaneously a design blueprint, user guide, research agenda, and communication platform for current and future developments in artificial intelligence (AI) approaches to systems biology. It places an emphasis on the molecular dimension of life phenomena and in one chapter on anatomical and functional modeling of the brain.

As design blueprint, the book is intended for scientists and other professionals tasked with developing and using AI technologies in the context of life sciences research. As a user guide, this volume addresses the requirements of researchers to gain a basic understanding of key AI methodologies for life sciences research. Its emphasis is not on an intricate mathematical treatment of the presented AI methodologies. Instead, it aims at providing the users with a clear understanding and practical know-how of the methods. As a research agenda, the book is intended for computer and life science students, teachers, researchers, and managers who want to understand the state of the art of the presented methodologies and the areas in which gaps in our knowledge demand further research and development. Our aim was to maintain the readability and accessibility of a textbook throughout the chapters, rather than compiling a mere reference manual. The book is also intended as a communication platform seeking to bride the cultural and technological gap among key systems biology disciplines. To support this function, contributors have adopted a terminology and approach that appeal to audiences from different backgrounds.

This monograph reports on advances in the measurement and study of autonomic nervous system (ANS) dynamics as a source of reliable and effective markers for mood state recognition and assessment of emotional responses. Its primary impact will be in affective computing and the application of emotion-recognition systems. Applicative studies of biosignals such as: electrocardiograms; electrodermal responses; respiration activity; gaze points; and pupil-size variation are covered in detail, and experimental results explain how to characterize the elicited affective levels and mood states pragmatically and accurately using the information thus extracted from the ANS. Nonlinear signal processing techniques play a crucial role in understanding the ANS physiology underlying superficially noticeable changes and provide important quantifiers of cardiovascular control dynamics. These have prognostic value in both healthy subjects and patients with mood disorders. Moreover, Autonomic Nervous System Dynamics for Mood and Emotional-State Recognition proposes a novel probabilistic approach based on the point-process theory in order to model and characterize the instantaneous ANS nonlinear dynamics providing a foundation from which machine "understanding" of emotional response can be enhanced. Using mathematics and signal processing, this work also contributes to pragmatic issues such as emotional and mood-state modeling, elicitation, and non-invasive ANS monitoring. Throughout the text a critical review on the current state-of-the-art is reported, leading to the description of dedicated experimental protocols, novel and reliable mood models, and novel wearable systems able to perform ANS monitoring in a naturalistic environment. Biomedical engineers will find this book of interest, especially those concerned with nonlinear analysis, as will researchers and industrial technicians developing wearable systems and sensors for ANS monitoring.

This book is for researchers, engineers, and students who are willing to understand how humanoid robots move and be controlled. The book starts with an overview of the humanoid robotics research history and state of the art. Then it explains the required mathematics and physics such as kinematics of multi-body system, Zero-Moment Point (ZMP) and its relationship with body motion. Biped walking control is discussed in depth, since it is one of the main interests of humanoid robotics. Various topics of the whole body motion generation are also discussed. Finally multi-body dynamics is presented to simulate the complete dynamic behavior of a humanoid robot. Throughout the book, Matlab codes are shown to test the algorithms and to help the readers understanding.

"Foundations of Data Mining and Knowledge Discovery" contains the latest results and new directions in data mining research. Data mining, which integrates various technologies, including computational intelligence, database and knowledge management, machine learning, soft computing, and statistics, is one of the fastest growing fields in computer science. Although many data mining techniques have been developed, further development of the field requires a close examination of its foundations. This volume presents the results of investigations into the foundations of the discipline, and represents the state of the art for much of the current research. This book will prove extremely valuable and fruitful for data mining researchers, no matter whether they would like to uncover the fundamental principles behind data mining, or apply the theories to practical applications.

The problem of structure and motion recovery from image sequences is an important theme in computer vision. Considerable progress has been made in this field during the past two decades, resulting in successful applications in robot navigation, augmented reality, industrial inspection, medical image analysis, and digital entertainment, among other areas. However, many of these methods work only for rigid objects and static scenes. The study of non-rigid structure from motion is not only of academic significance, but also has important practical applications in real-world, nonrigid or dynamic scenarios, such as human facial expressions and moving vehicles.

This practical guide/reference provides a comprehensive overview of Euclidean structure and motion recovery, with a specific focus on factorization-based algorithms. The book discusses the latest research in this field, including the extension of the factorization algorithm to recover the structure of non-rigid objects, and presents some new algorithms developed by the authors. Readers require no significant knowledge of computer vision, although some background on projective geometry and matrix computation would be beneficial.

Topics and features: presents the first systematic study of structure and motion recovery of both rigid and non-rigid objects from images sequences; discusses in depth the theory, techniques, and applications of rigid and non-rigid factorization methods in three dimensional computer vision; examines numerous factorization algorithms, covering affine, perspective and quasi-perspective projection models; provides appendices describing the mathematical principles behind projective geometry, matrix decomposition, least squares, and nonlinear estimation techniques; includes chapter-ending review questions, and a glossary of terms used in the book.

This unique text offers practical guidance in real applications and implementations of 3D modeling systems for practitioners in computer vision and pattern recognition, as well as serving as an invaluable source of new algorithms and methodologies for structure and motion recovery for graduate students and researchers.

This book suggests and describes a number of fast parallel circuits for data/vector processing using FPGA-based hardware accelerators. Three primary areas are covered: searching, sorting, and counting in combinational and iterative networks. These include the application of traditional structures that rely on comparators/swappers as well as alternative networks with a variety of core elements such as adders, logical gates, and look-up tables. The iterative technique discussed in the book enables the sequential reuse of relatively large combinational blocks that execute many parallel operations with small propagation delays. For each type of network discussed, the main focus is on the step-by-step development of the architectures proposed from initial concepts to synthesizable hardware description language specifications. Each type of network is taken through several stages, including modeling the desired functionality in software, the retrieval and automatic conversion of key functions, leading to specifications for optimized hardware modules. The resulting specifications are then synthesized, implemented, and tested in FPGAs using commercial design environments and prototyping boards. The methods proposed can be used in a range of data processing applications, including traditional sorting, the extraction of maximum and minimum subsets from large data sets, communication-time data processing, finding frequently occurring items in a set, and Hamming weight/distance counters/comparators. The book is intended to be a valuable support material for university and industrial engineering courses that involve FPGA-based circuit and system design.

This book focuses on next generation data technologies in support of collective and computational intelligence. The book brings various next generation data technologies together to capture, integrate, analyze, mine, annotate and visualize distributed data - made available from various community users - in a meaningful and collaborative for the organization manner. A unique perspective on collective computational intelligence is offered by embracing both theory and strategies fundamentals such as data clustering, graph partitioning, collaborative decision making, self-adaptive ant colony, swarm and evolutionary agents. It also covers emerging and next generation technologies in support of collective computational intelligence such as Web 2.0 social networks, semantic web for data annotation, knowledge representation and inference, data privacy and security, and enabling distributed and collaborative paradigms such as P2P, Grid and Cloud Computing due to the geographically dispersed and distributed nature of the data. The book aims to cover in a comprehensive manner the combinatorial effort of utilizing and integrating various next generations collaborative and distributed data technologies for computational intelligence in various scenarios. The book also distinguishes itself by assessing whether utilization and integration of next generation data technologies can assist in the identification of new opportunities, which may also be strategically fit for purpose.

Intelligence results from the interaction of the brain, body and environment. The question addressed in this book is, can we measure the contribution of the body and its' interaction with the environment? To answer this, we first present a comprehensive overview of the various ways in which a body reduces the amount of computation that the brain has to perform to solve a task. This chapter will broaden your understanding of how important inconspicuously appearing physical processes and physical properties of the body are with respect to our cognitive abilities. This form of contribution to intelligence is called Morphological Intelligence. The main contribution of this book to the field is a detailed discussion of how Morphological Intelligence can be measured from observations alone. The required mathematical framework is provided so that readers unfamiliar with information theory will be able to understand and apply the measures. Case studies from biomechanics and soft robotics illustrate how the presented quantifications can, for example, be used to measure the contribution of muscle physics to jumping and optimise the shape of a soft robotic hand. To summarise, this monograph presents various examples of how the physical properties of the body and the body's interaction with the environment contribute to intelligence. Furthermore, it treats theoretical and practical aspects of Morphological Intelligence and demonstrates the value in two case studies.

This monograph provides logical foundations and a uniform description for nonmonotonic reasoning and belief change. The approach to both these subjects is based on a powerful notion of an epistemic state that subsumes both existing models for nonmonotonic inference and current models for belief change. Many results and constructions in the book are completely new and have not appeared earlier in the literature.The book is primarily intended for experts in Artificial Intelligence and Knowledge Representation who are interested in tools for describing commonsense reasoning tasks as well as in representation capabilities of such tools. It is also of interest to general logicians.

Neurofuzzy and fuzzyneural techniques as tools of studying and analyzing complex problems are relatively new even though neural networks and fuzzy logic systems have been applied as computational intelligence structural e- ments for the last 40 years. Computational intelligence as an independent sci- tific field has grown over the years because of the development of these str- tural elements. Neural networks have been revived since 1982 after the seminal work of J. J. Hopfield and fuzzy sets have found a variety of applications since the pub- cation of the work of Lotfi Zadeh back in 1965. Artificial neural networks (ANN) have a large number of highly interconnected processing elements that usually operate in parallel and are configured in regular architectures. The c- lective behavior of an ANN, like a human brain, demonstrates the ability to learn, recall, and generalize from training patterns or data. The performance of neural networks depends on the computational function of the neurons in the network, the structure and topology of the network, and the learning rule or the update rule of the connecting weights. This concept of trainable neural n- works further strengthens the idea of utilizing the learning ability of neural networks to learn the fuzzy control rules, the membership functions and other parameters of a fuzzy logic control or decision systems, as we will explain later on, and this becomes the advantage of using a neural based fuzzy logic system in our analysis. On the other hand, fuzzy systems are structured numerical est

In six parts, this book considers the extent to which computational, neural, and ecological constraints have shaped the mechanisms underlying motion vision:- Early Motion Vision - Motion Signals for Local and Global Analysis - Optical Flow Patterns - Motion Vision in Action - Neural Coding of Motion - Motion in Natural EnvironmentsEach topic is introduced by a keynote chapter which is accompanied by several companion articles. Written by an international group of experts in neurobiology, psychophysics, animal behaviour, machine vision, and robotics, the book is designed to explore as comprehensively as possible the present state of knowledge concerning the principal factors that have guided the evolution of motion vision.

With the growing use of information technology and the recent advances in web systems, the amount of data available to users has increased exponentially. Thus, there is a critical need to understand the content of the data. As a result, data-mining has become a popular research topic in recent years for the treatment of the "data rich and information poor" syndrome. In this carefully edited volume a theoretical foundation as well as important new directions for data-mining research are presented. It brings together a set of well respected data mining theoreticians and researchers with practical data mining experiences. The presented theories will give data mining practitioners a scientific perspective in data mining and thus provide more insight into their problems, and the provided new data mining topics can be expected to stimulate further research in these important directions.

Theoretical Advances in Neural Computation and Learning brings together in one volume some of the recent advances in the development of a theoretical framework for studying neural networks. A variety of novel techniques from disciplines such as computer science, electrical engineering, statistics, and mathematics have been integrated and applied to develop ground-breaking analytical tools for such studies. This volume emphasizes the computational issues in artificial neural networks and compiles a set of pioneering research works, which together establish a general framework for studying the complexity of neural networks and their learning capabilities. This book represents one of the first efforts to highlight these fundamental results, and provides a unified platform for a theoretical exploration of neural computation. Each chapter is authored by a leading researcher and/or scholar who has made significant contributions in this area. Part 1 provides a complexity theoretic study of different models of neural computation. Complexity measures for neural models are introduced, and techniques for the efficient design of networks for performing basic computations, as well as analytical tools for understanding the capabilities and limitations of neural computation are discussed. The results describe how the computational cost of a neural network increases with the problem size. Equally important, these results go beyond the study of single neural elements, and establish to computational power of multilayer networks. Part 2 discusses concepts and results concerning learning using models of neural computation. Basic concepts such as VC-dimension and PAC-learning are introduced, and recentresults relating neural networks to learning theory are derived. In addition, a number of the chapters address fundamental issues concerning learning algorithms, such as accuracy and rate of convergence, selection of training data, and efficient algorithms for learning useful classes of mappings.

This book provides a complete background on metaheuristics to solve complex bi-level optimization problems (continuous/discrete, mono-objective/multi-objective) in a diverse range of application domains. Readers learn to solve large scale bi-level optimization problems by efficiently combining metaheuristics with complementary metaheuristics and mathematical programming approaches. Numerous real-world examples of problems demonstrate how metaheuristics are applied in such fields as networks, logistics and transportation, engineering design, finance and security.

Computational intelligence techniques are gaining momentum in the medical prognosis and diagnosis. This volume presents advanced applications of machine intelligence in medicine and bio-medical engineering. Applied methods include knowledge bases, expert systems, neural networks, neuro-fuzzy systems, evolvable systems, wavelet transforms, and specific internet applications. The volume is written in view of explaining to the practitioner the fundamental issues related to computational intelligence paradigms and to offer a fast and friendly-managed introduction to the most recent methods based on computer intelligence in medicine.

Artificial Neural Networks have captured the interest of many researchers in the last five years. As with many young fields, neural network research has been largely empirical in nature, relyingstrongly on simulationstudies ofvarious network models. Empiricism is, of course, essential to any science for it provides a body of observations allowing initial characterization of the field. Eventually, however, any maturing field must begin the process of validating empirically derived conjectures with rigorous mathematical models. It is in this way that science has always pro ceeded. It is in this way that science provides conclusions that can be used across a variety of applications. This monograph by Michael Lemmon provides just such a theoretical exploration of the role ofcompetition in Artificial Neural Networks. There is "good news" and "bad news" associated with theoretical research in neural networks. The bad news isthat such work usually requires the understanding of and bringing together of results from many seemingly disparate disciplines such as neurobiology, cognitive psychology, theory of differential equations, largc scale systems theory, computer science, and electrical engineering. The good news is that for those capable of making this synthesis, the rewards are rich as exemplified in this monograph."

In today's global culture where the internet has established itself as a main tool of communication, the global system of economy and regulations, as well as data and decisions based on data analysis, have become essential for public actors and institutions. Governments need to be updated and use the latest technologies to understand what society's demands are, and user behavioral data, which can be pulled by intelligent applications, can offer tremendous insights into this. Application of Artificial Intelligence in Government Practices and Processes identifies definitional perspectives of behavioral data science and what its use by governments means for automation, predictability, and risks to privacy and free decision making in society. Many governments can train their algorithms to work with machine learning, leading to the capacity to interfere in the behavior of society and potentially achieve a change in societal behavior without society itself even being aware of it. As such, the use of artificial intelligence by governments has raised concerns about privacy and personal security issues. Covering topics such as digital democracy, data extraction techniques, and political communications, this book is an essential resource for data analysts, politicians, journalists, public figures, executives, researchers, data specialists, communication specialists, digital marketers, and academicians.

Rules represent a simplified means of programming, congruent with our understanding of human brain constructs. With the advent of business rules management systems, it has been possible to introduce rule-based programming to nonprogrammers, allowing them to map expert intent into code in applications such as fraud detection, financial transactions, healthcare, retail, and marketing. However, a remaining concern is the quality, safety, and reliability of the resulting programs. This book is on business rules programs, that is, rule programs as handled in business rules management systems. Its conceptual contribution is to present the foundation for treating business rules as a topic of scientific investigation in semantics and program verification, while its technical contribution is to present an approach to the formal verification of business rules programs. The author proposes a method for proving correctness properties for a business rules program in a compositional way, meaning that the proof of a correctness property for a program is built up from correctness properties for the individual rules-thus bridging a gap between the intuitive understanding of rules and the formal semantics of rule programs. With this approach the author enables rule authors and tool developers to understand, express formally, and prove properties of the execution behavior of business rules programs. This work will be of interest to practitioners and researchers in the areas of program verification, enterprise computing, database management, and artificial intelligence.

At present, there is a general consensus on the nature of learning programming, but there are different opinions on what forms an effective environment for it. It is generally recognized that the development of a mental model is a formidable task for the student and that learning programming is a complex activity that depends heavily on metacognitive skills. This book, based on a NATO workshop, presents both pure cognitive models and experimental learning environments, and discusses what characteristics can make a learning model effective, especially in relation to the learning environment (natural or computerized). The papers cover cognitive models related to different aspects of programming, classes of learners, and types of environment, and are organized in three groups: theoretical and empirical studies on understanding programming, environments for learning programming, and learning programming in school environments. Comprehension, design, construction, testing, debugging, and verification are recognized as interdependent skills, which require complicated analysis and may develop independently, and indifferent orders, in novices. This book shows that there is unlikely to be asingle path from novice to expert and that the structure of the final product (the program) may not constrain the process by which it comes into being as much as some would advocate.

The field of data mining has made significant and far-reaching advances over the past three decades.Because of its potential power for solving complex problems, data mining has been successfully applied to diverse areas such as business, engineering, social media, and biological science. Many of these applications search for patterns in complex structural information. In biomedicine for example, modeling complex biological systems requires linking knowledge across many levels of science, from genes to disease. Further, the data characteristics of the problems have also grown from static to dynamic and spatiotemporal, complete to incomplete, and centralized to distributed, and grow in their scope and size (this is known as "big data"). The effective integration of big data for decision-making also requires privacy preservation.

The contributions to this monograph summarize the advances of data mining in the respective fields. This volume consists of nine chapters that address subjects ranging from mining data from opinion, spatiotemporal databases, discriminative subgraph patterns, path knowledge discovery, social media, and privacy issues to the subject of computation reduction via binary matrix factorization."

This book starts with the basic concepts of fuzzy sets and progresses througha normative view on possibility distributions and OWA operators in multiple criteria decisions.

Five applications (that all build on experience from solving complex real world problems)of possibility distributions to strategic decisions about closing/not closinga production plant using fuzzy real options, portfolio selection with imprecise future data, predictive probabilities and possibilities for risk assessment in grid computing, fuzzy ontologies for process industry, and design (and implementation) of mobile value servicesare presented and carefully discussed. It can be useful for researchers and students workingin soft computing, real options, fuzzy decision making, grid computing, knowledge mobilization andmobile value services."

The focus of this volume is comprised of the fundamentals, models, and information technologies (IT) methods and tools for disaster prediction and mitigation. A more detailed list of topics includes mathematical and computational modeling of processes leading to or producing disasters, modeling of disaster effects, IT means for disaster mitigation, including data mining tools, knowledge-based and expert systems for use in disaster circumstances, GIS-based systems for disaster prevention and mitigation and equipment for disaster-prone areas. A specific type or class of disasters (natural or human-made), however will not be part of the main focus of this work. Instead, this book was conceived to offer a comprehensive, integrative view on disasters, seeking to determine what various disasters have in common. Because disaster resilience and mitigation involve humans, societies and cultures, not only technologies and economic models, special attention was paid in this volume to gain a comprehensive view on these issues, as a foundation of the IT tool design.