Probabilistic Conditional Independence Structures provides the mathematical description of probabilistic conditional independence structures; the author uses non-graphical methods of their description, and takes an algebraic approach.

The monograph presents the methods of structural imsets and supermodular functions, and deals with independence implication and equivalence of structural imsets. Motivation, mathematical foundations and areas of application are included, and a rough overview of graphical methods is also given. In particular, the author has been careful to use suitable terminology, and presents the work so that it will be understood by both statisticians, and by researchers in artificial intelligence. The necessary elementary mathematical notions are recalled in an appendix.

Artificial intelligence provides an environmentally rich paradigm within which design research based on computational constructions can be carried out. This has been one of the foundations for the developing field called "design computing."

Recently, there has been a growing interest in what designers do when they design and how they use computational tools. This forms the basis of a newly emergent field called "design cognition" that draws partly on cognitive science.

This new conference series aims to provide a bridge between the two fields of "design computing" and "design cognition." The papers in this volume are from the "First International Conference on Design Computing and Cognition" (DCC'04) held at the Massachusetts Institute of Technology, USA. They represent state-of-the art research and development in design computing and cognition. They are of particular interest to researchers, developers and users of advanced computation in design and those who need to gain a better understanding of designing.

This volume is an initiative undertaken by the IEEE Computational Intelligence Society's Task Force on Security, Surveillance and Defense to consolidate and disseminate the role of CI techniques in the design, development and deployment of security and defense solutions. Applications range from the detection of buried explosive hazards in a battlefield to the control of unmanned underwater vehicles, the delivery of superior video analytics for protecting critical infrastructures or the development of stronger intrusion detection systems and the design of military surveillance networks. Defense scientists, industry experts, academicians and practitioners alike will all benefit from the wide spectrum of successful applications compiled in this volume. Senior undergraduate or graduate students may also discover uncharted territory for their own research endeavors.

This volume is based on lectures given at the NATO Advanced Study Institute on "Stochastic Games and Applications," which took place at Stony Brook, NY, USA, July 1999. It gives the editors great pleasure to present it on the occasion of L.S. Shapley's eightieth birthday, and on the fiftieth "birthday" of his seminal paper "Stochastic Games," with which this volume opens. We wish to thank NATO for the grant that made the Institute and this volume possible, and the Center for Game Theory in Economics of the State University of New York at Stony Brook for hosting this event. We also wish to thank the Hebrew University of Jerusalem, Israel, for providing continuing financial support, without which this project would never have been completed. In particular, we are grateful to our editorial assistant Mike Borns, whose work has been indispensable. We also would like to acknowledge the support of the Ecole Poly tech nique, Paris, and the Israel Science Foundation. March 2003 Abraham Neyman and Sylvain Sorin ix STOCHASTIC GAMES L.S. SHAPLEY University of California at Los Angeles Los Angeles, USA 1. Introduction In a stochastic game the play proceeds by steps from position to position, according to transition probabilities controlled jointly by the two players."

This bookisan outgrowthoften yearsof researchatthe Universityof Florida Computational NeuroEngineering Laboratory (CNEL) in the general area of statistical signal processing and machine learning. One of the goals of writing the book is exactly to bridge the two ?elds that share so many common problems and techniques but are not yet e?ectively collaborating. Unlikeotherbooks thatcoverthe state ofthe artinagiven?eld, this book cuts across engineering (signal processing) and statistics (machine learning) withacommontheme: learningseenfromthepointofviewofinformationt- orywithanemphasisonRenyi'sde?nitionofinformation.Thebasicapproach is to utilize the information theory descriptors of entropy and divergence as nonparametric cost functions for the design of adaptive systems in unsup- vised or supervised training modes. Hence the title: Information-Theoretic Learning (ITL). In the course of these studies, we discovered that the main idea enabling a synergistic view as well as algorithmic implementations, does not involve the conventional central moments of the data (mean and covariance). Rather, the core concept is the ?-norm of the PDF, in part- ular its expected value (? = 2), which we call the information potential. This operator and related nonparametric estimators link information theory, optimization of adaptive systems, and reproducing kernel Hilbert spaces in a simple and unconventional way.

Artificial intelligence (AI) is revolutionizing every aspect of human life including human healthcare and wellbeing management. Various types of intelligent healthcare engineering applications have been created that help to address patient healthcare and outcomes such as identifying diseases and gathering patient information. Advancements in AI applications in healthcare continue to be sought to aid rapid disease detection, health monitoring, and prescription drug tracking. Advancement of Artificial Intelligence in Healthcare Engineering is an essential scholarly publication that provides comprehensive research on the possible applications of machine learning, deep learning, soft computing, and evolutionary computing techniques in the design, implementation, and optimization of healthcare engineering solutions. Featuring a wide range of topics such as genetic algorithms, mobile robotics, and neuroinformatics, this book is ideal for engineers, technology developers, IT consultants, hospital administrators, academicians, healthcare professionals, practitioners, researchers, and students.

Jo Bac's groundbreaking legal study asks why and how the United States legal system should grant legal personhood to artificial intelligence (AI). This new legal status of AI is visualized as a dependent person, and the AI dependent legal person would be determined by an inextricable connection between AI and a new type of corporate body, introduced here as "AI-Human Amalgamation" (AI-HA). Artificial Intelligence has been defined as one or more computer programs with an ability to create work that is unforeseen by humans. This includes AI capacity to generate unforeseen innovations, patentable inventions, and/or infringe the rights of other patent holders. At present, AI is an entity unrecognized by law. The fact that AI is neither a natural nor a legal person indicates that it cannot be considered the owner of rights or bearer of liabilities. This in turn creates tension both in society and legal systems because questions such as who should hold the rights of AI or be liable for autonomous acts of AI remain unanswered. This book dynamically argues that the AI dependent legal person and AI-HA are necessary to address these new challenges. The creativity and actions of AI and AI-HA would be distinct from those performed by human beings involved in the creation of this amalgamation, such as AI's operators or programmers. As such, this structure would constitute an amalgamation based on human beings and AI cooperation (AI-HA). As a dependent legal person, AI would hold the patent rights to its own inventions, thus ensuring favorable conditions for the incentives of the U.S. patent system. In addition, the proposed legal framework with the use of legislative instruments could address any liability concerns arising from foreseen and unforeseen actions, omissions, and AI's failure to act.

This book is a collection of writings by active researchers in the field of Artificial General Intelligence, on topics of central importance in the field. Each chapter focuses on one theoretical problem, proposes a novel solution, and is written in sufficiently non-technical language to be understandable by advanced undergraduates or scientists in allied fields. This book is the very first collection in the field of Artificial General Intelligence (AGI) focusing on theoretical, conceptual, and philosophical issues in the creation of thinking machines. All the authors are researchers actively developing AGI projects, thus distinguishing the book from much of the theoretical cognitive science and AI literature, which is generally quite divorced from practical AGI system building issues. And the discussions are presented in a way that makes the problems and proposed solutions understandable to a wide readership of non-specialists, providing a distinction from the journal and conference-proceedings literature. The book will benefit AGI researchers and students by giving them a solid orientation in the conceptual foundations of the field (which is not currently available anywhere); and it would benefit researchers in allied fields by giving them a high-level view of the current state of thinking in the AGI field. Furthermore, by addressing key topics in the field in a coherent way, the collection as a whole may play an important role in guiding future research in both theoretical and practical AGI, and in linking AGI research with work in allied disciplines

Security and Dependability for Ambient Intelligence is the primary publication of the SERENITY approach, which provides security and dependability (S&D) solutions for dynamic, highly distributed, heterogeneous systems. The objective of SERENITY is to enhance the security and dependability of ambient intelligence systems by providing a framework supporting the automated integration, configuration, monitoring and adaptation of security and dependability mechanisms.

An edited volume contributed by world leaders in the field, this book covers the problems that the highly dynamic and heterogeneous nature of ambient intelligence systems poses to security and dependability and presents solutions to these problems.

Security and Dependability for Ambient Intelligence is designed for researchers and practitioners focusing on the dynamic integration, deployment and verification of security and dependability solutions in highly distributed systems incorporating ambient intelligence features. It is also suitable as a reference or secondary text for advanced-level students in computer science and computer or electrical engineering.

Evolutionary algorithms are sophisticated search methods that have been found to be very efficient and effective in solving complex real-world multi-objective problems where conventional optimization tools fail to work well. Despite the tremendous amount of work done in the development of these algorithms in the past decade, many researchers assume that the optimization problems are deterministic and uncertainties are rarely examined.

The primary motivation of this book is to provide a comprehensive introduction on the design and application of evolutionary algorithms for multi-objective optimization in the presence of uncertainties. In this book, we hope to expose the readers to a range of optimization issues and concepts, and to encourage a greater degree of appreciation of evolutionary computation techniques and the exploration of new ideas that can better handle uncertainties. "Evolutionary Multi-Objective Optimization in Uncertain Environments: Issues and Algorithms" is intended for a wide readership and will be a valuable reference for engineers, researchers, senior undergraduates and graduate students who are interested in the areas of evolutionary multi-objective optimization and uncertainties.

Biologically inspired approaches for artificial sensing have been extensively applied to different sensory modalities over the last decades and chemical senses have been no exception. The olfactory system, and the gustatory system to a minor extent, has been regarded as a model for the development of new artificial chemical sensing s- tems. One of the main contributions to this field was done by Persaud and Dodd in 1982 when they proposed a system based on an array of broad-selective chemical sensors coupled with a pattern recognition engine. The array aimed at mimicking the sensing strategy followed by the olfactory system where a population of bro- selective olfactory receptor neurons encodes for chemical information as patterns of activity across the neuron population. The pattern recognition engine proposed was not based on bio-inspired but on statistical methods. This influential work gave rise to a new line of research where this paradigm has been used to build chemical sensing instruments applied to a wide range of odor detection problems. More recently, some researchers have proposed to extend the biological inspiration of this system also to the processing of the sensor array signals. This has been mo- vated in part by the increasing body of knowledge available on biological olfaction, which has become in the last decade a focus of attention of the experimental neu- science community.

Power system modelling and scripting is a quite general and ambitious title. Of course, to embrace all existing aspects of power system modelling would lead to an encyclopedia and would be likely an impossible task. Thus, the book focuses on a subset of power system models based on the following assumptions: (i) devices are modelled as a set of nonlinear differential algebraic equations, (ii) all alternate-current devices are operating in three-phase balanced fundamental frequency, and (iii) the time frame of the dynamics of interest ranges from tenths to tens of seconds. These assumptions basically restrict the analysis to transient stability phenomena and generator controls. The modelling step is not self-sufficient. Mathematical models have to be translated into computer programming code in order to be analyzed, understood and experienced . It is an object of the book to provide a general framework for a power system analysis software tool and hints for filling up this framework with versatile programming code. This book is for all students and researchers that are looking for a quick reference on power system models or need some guidelines for starting the challenging adventure of writing their own code."

Over the last two decades, the field of artificial intelligence has experienced

a separation into two schools that hold opposite opinions on how uncertainty should be treated. This separation is the result of a debate that began at the end of the 1960 s when AI first faced the problem of building machines required to make decisions and act in the real world. This debate witnessed the contraposition between the mainstream school, which relied on probability for handling uncertainty, and an alternative school, which criticized the adequacy of probability in AI applications and developed alternative formalisms.

The debate has focused on the technical aspects of the criticisms raised against probability while neglecting an important element of contrast. This element is of an epistemological nature, and is therefore exquisitely philosophical. In this book, the historical context in which the debate on probability developed is presented and the key components of the technical criticisms therein are illustrated. By referring to the original texts, the epistemological element that has been neglected in the debate is analyzed in detail. Through a philosophical analysis of the epistemological element it is argued that this element is metaphysical in Popper s sense. It is shown that this element cannot be tested nor possibly disproved on the

basis of experience and is therefore extra-scientific. Ii is established that a philosophical analysis is now compelling in order to both solve the problematic division that characterizes the uncertainty field and to secure the foundations of the field itself.

This book highlights practical quantum key distribution systems and research on the implementations of next-generation quantum communication, as well as photonic quantum device technologies. It discusses how the advances in quantum computing and quantum physics have allowed the building, launching and deploying of space exploration systems that are capable of more and more as they become smaller and lighter. It also presents theoretical and experimental research on the potential and limitations of secure communication and computation with quantum devices, and explores how security can be preserved in the presence of a quantum computer, and how to achieve long-distance quantum communication. The development of a real quantum computer is still in the early stages, but a number of research groups have investigated the theoretical possibilities of such computers.

In this book, 22 authors discuss development of Ambient Assisted Living. It presents new technological developments which support the autonomy and independence of individuals with special needs. As the technological innovation raises also social issues, the book addresses micro and macro economical aspects of assistive systems and puts an additional emphasis on the ethical and legal discussion. The presentation is supported by real world examples and applications.

Intelligent systems are now being used more commonly than in the past. These involve cognitive, evolving and artificial-life, robotic, and decision making systems, to name a few. Due to the tremendous speed of development, on both fundamental and technological levels, it is virtually impossible to offer an up-to-date, yet comprehensive overview of this field. Nevertheless, the need for a volume presenting recent developments and trends in this domain is huge, and the demand for such a volume is continually increasing in industrial and academic engineering 1 communities. Although there are a few volumes devoted to similar issues, none offer a comprehensive coverage of the field; moreover they risk rapidly becoming obsolete. The editors of this volume cannot pretend to fill such a large gap. However, it is the editors' intention to fill a significant part of this gap. A comprehensive coverage of the field should include topics such as neural networks, fuzzy systems, neuro-fuzzy systems, genetic algorithms, evolvable hardware, cellular automata-based systems, and various types of artificial life-system implementations, including autonomous robots. In this volume, we have focused on the first five topics listed above. The volume is composed of four parts, each part being divided into chapters, with the exception of part 4. In Part 1, the topics of "Evolvable Hardware and GAs" are addressed. In Chapter 1, "Automated Design Synthesis and Partitioning for Adaptive Reconfigurable Hardware," Ranga Vemuri and co-authors present state-of-the-art adaptive architectures, their classification, and their applications."

Rapid developments in electronics over the past two decades have induced a move from purely mechanical vehicles to mechatronics design. Recent advances in computing, sensors, and information technology are pushing mobile equipment design to incorporate higher levels of automation under the novel concept of intelligent vehicles. Mechatronics and Intelligent Systems for Off-road Vehicles introduces this concept, and provides an overview of recent applications and future approaches within this field. Several case studies present real examples of vehicles designed to navigate in off-road environments typically encountered by agriculture, forestry, and construction machines. The examples analyzed describe and illustrate key features for agricultural robotics, such as automatic steering, safeguarding, mapping, and precision agriculture applications. The eight chapters include numerous figures, each designed to improve the reader's comprehension of subjects such as: * automatic steering systems; * navigation systems; * vehicle architecture; * image processing and vision; and * three-dimensional perception and localization. Mechatronics and Intelligent Systems for Off-road Vehicles will be of great interest to professional engineers and researchers in vehicle automation, robotics, and the application of artificial intelligence to mobile equipment; as well as to graduate students of mechanical, electrical, and agricultural engineering.

Processing data streams has raised new research challenges over the last few years. This book provides the reader with a comprehensive overview of stream data processing, including famous prototype implementations like the Nile system and the TinyOS operating system. Applications in security, the natural sciences, and education are presented. The huge bibliography offers an excellent starting point for further reading and future research.

This monograph focuses on the use of analysis and processing methods for images from the Corvis (R) ST tonometer. The presented analysis is associated with the quantitative, repeatable and fully automatic evaluation of the response of the eye, eyeball and cornea to an air-puff. All the described algorithms were practically implemented in MATLAB (R). The monograph also describes and provides the full source code designed to perform the discussed calculations. As a result, this monograph is intended for scientists, graduate students and students of computer science and bioengineering as well as doctors wishing to expand their knowledge of modern diagnostic methods assisted by various image analysis and processing methods.

This book presents a discussion of problems encountered in the deployment of Intelligent Transport Systems (ITS). It puts emphasis on the early tasks of designing and proofing the concept of integration of technologies in Intelligent Transport Systems. In its first part the book concentrates on the design problems of urban ITS. The second part of the book features case studies representative for the different modes of transport. These are freight transport, rail transport and aerospace transport encompassing also space stations. The book provides ideas for deployment which may be developed by scientists and engineers engaged in the design of Intelligent Transport Systems. It can also be used in the training of specialists, students and post-graduate students in universities and transport high schools.

In this book for the first time two scientific fields - consensus formation and synchronization of communications - are presented together and examined through their interrelational aspects, of rapidly growing importance. Both fields have indeed attracted enormous research interest especially in relation to complex networks.
In networks of dynamic systems (or agents), consensus means to reach an agreement regarding a certain quantity of interest that depends on the state of all dynamical systems (agents). Consensus problems have a long history in control theory and computer sciences, and form the foundation of the field of distributed computing. Synchronization, which defines correlated-in-time behavior between different processes and roots going back to Huygens to the least, is now a highly popular, exciting and rapidly developing topic, with applications ranging from biological networks to mathematical epidemiology, and from processing information in the brain to engineering of communications devices.
The book reviews recent finding in both fields and describes novel approaches to consensus formation, where consensus is realized as an instance of the nonlinear dynamics paradigm of chaos synchronization. The chapters are written by world-known experts in both fields and cover topics ranging from fundaments to various applications of consensus and synchronization."

Machine Translation (MT) is both an engineering technology and a measure of all things to do with languages and computersa "whenever a new theory of language or linguistics is offered, an important criteria for its success is whether or not it will improve machine translation.

This book presents a history of machine translation (MT) from the point of view of a major writer and innovator in the subject. It describes and contrasts a range of approaches to the challenges and problems of this remarkable technology by means of a combination of historic papers along with commentaries to update their significance, both at the time of their writing and now. This volume chronicles the evolution of conflicting approaches to MT towards a somewhat skeptical consensus on future progress. Also included is a discussion of the most recent developments in the field and prospects for the future, which have been much changed by the arrival of the World Wide Web.

This book provides a comprehensive and timely report in the area of non-additive measures and integrals. It is based on a panel session on fuzzy measures, fuzzy integrals and aggregation operators held during the 9th International Conference on Modeling Decisions for Artificial Intelligence (MDAI 2012) in Girona, Spain, November 21-23, 2012. The book complements the MDAI 2012 proceedings book, published in Lecture Notes in Computer Science (LNCS) in 2012. The individual chapters, written by key researchers in the field, cover fundamental concepts and important definitions (e.g. the Sugeno integral, definition of entropy for non-additive measures) as well some important applications (e.g. to economics and game theory) of non-additive measures and integrals. The book addresses students, researchers and practitioners working at the forefront of their field.

This is the sixth volume of a sub series on Road Vehicle Automation published within the Lecture Notes in Mobility. The contents have been provided by researchers, engineers and analysts from all around the world. Topics covered include public sector activities, human factors and challenges, ethical, legal, energy and technology perspectives, vehicle systems development, as well as transportation infrastructure and planning. The book is based on the Automated Vehicles Symposium held on July 9-12, 2018 in San Francisco, CA (USA).

Recent years have seen the widespread application of Natural Computing algorithms (broadly defined in this context as computer algorithms whose design draws inspiration from phenomena in the natural world) for the purposes of financial modelling and optimisation. A related stream of work has also seen the application of learning mechanisms drawn from Natural Computing algorithms for the purposes of agent-based modelling in finance and economics. In this book we have collected a series of chapters which illustrate these two faces of Natural Computing. The first part of the book illustrates how algorithms inspired by the natural world can be used as problem solvers to uncover and optimise financial models. The second part of the book examines a number agent-based simulations of financial systems.

This book follows on from Natural Computing in Computational Finance (Volume 100 in Springer's Studies in Computational Intelligence series) which in turn arose from the success of EvoFIN 2007, the very first European Workshop on Evolutionary Computation in Finance & Economics held in Valencia, Spain in April 2007.