The book is concerned with contemporary methodologies used for automatic text summarization. It proposes interesting approaches to solve well-known problems on text-summarization using computational intelligence (CI) techniques including cognitive approaches. A better understanding of the cognitive basis of the summarization task is still an open research issue, an extent of its use in text summarization is highlighted for further exploration. With the ever-growing text and people on research has little time to spare for extensive reading, where, summarized information helps for a better understanding of the context at a shorter time. This book helps students and researchers to automatically summarize the text documents in an efficient and effective way. The computational approaches and the research techniques presented guides to achieve text summarization at ease. The summarized text generated supports readers to learn the context or the domain at a quicker pace. The book is presented with reasonable amount of illustrations and examples convenient for the readers to understand and implement for their use. The book is not to make readers understand what text summarization is, but for people to perform text summarization using various approaches. This also describes measures that can help to evaluate, determine and explore the best possibilities for text summarization to analyse and use for any specific purpose. The illustration is based on social media and healthcare domain, which shows the possibilities to work with any domain for summarization. The new approach for text summarization based on cognitive intelligence is presented for further exploration in the field.

The idea of optimization runs through most parts of control theory. The simplest optimal controls are preplanned (programmed) ones. The problem of constructing optimal preplanned controls has been extensively worked out in literature (see, e. g., the Pontrjagin maximum principle giving necessary conditions of preplanned control optimality). However, the concept of op timality itself has a restrictive character: it is limited by what one means under optimality in each separate case. The internal contradictoriness of the preplanned control optimality ("the better is the enemy of the good") yields that the practical significance of optimal preplanned controls proves to be not great: such controls are usually sensitive to unregistered disturbances (includ ing the round-off errors which are inevitable when computer devices are used for forming controls), as there is the effect of disturbance accumulation in the control process which makes controls to be of little use on large time inter vals. This gap is mainly provoked by oversimplified settings of optimization problems. The outstanding result of control theory established in the end of the first half of our century is that controls in feedback form ensure the weak sensitivity of closed loop systems with respect to "small" unregistered internal and external disturbances acting in them (here we do not need to discuss performance indexes, since the considered phenomenon is of general nature). But by far not all optimal preplanned controls can be represented in a feedback form."

This book presents research on informational and mathematical aspects of networked sensing systems. It brings together internationally reputed researchers from different communities, focused on the common theme of distributed sensing, inferencing, and control over networks. The timeliness of the book is evidenced by the explosion of several independent special sessions devoted to specific aspects of sensor networks in reputed international conferences.

In 1960, R. E. Kalman published his celebrated paper on recursive min imum variance estimation in dynamical systems [14]. This paper, which introduced an algorithm that has since been known as the discrete Kalman filter, produced a virtual revolution in the field of systems engineering. Today, Kalman filters are used in such diverse areas as navigation, guid ance, oil drilling, water and air quality, and geodetic surveys. In addition, Kalman's work led to a multitude of books and papers on minimum vari ance estimation in dynamical systems, including one by Kalman and Bucy on continuous time systems [15]. Most of this work was done outside of the mathematics and statistics communities and, in the spirit of true academic parochialism, was, with a few notable exceptions, ignored by them. This text is my effort toward closing that chasm. For mathematics students, the Kalman filtering theorem is a beautiful illustration of functional analysis in action; Hilbert spaces being used to solve an extremely important problem in applied mathematics. For statistics students, the Kalman filter is a vivid example of Bayesian statistics in action. The present text grew out of a series of graduate courses given by me in the past decade. Most of these courses were given at the University of Mas sachusetts at Amherst.

This volume surveys three decades of modern robot control theory and describes how the work of Suguru Arimoto shaped its development. Twelve survey articles written by experts associated with Suguru Arimoto at various stages in his career treat the subject comprehensively. This book provides an important reference for graduate students and researchers, as well as for mathematicians, engineers and scientists whose work involves robot control theory.

This authoritative reference work will provide readers with a complete overview of artificial intelligence (AI), including its historic development and current status, existing and projected AI applications, and present and potential future impact on the United States and the world. Some people believe that artificial intelligence (AI) will revolutionize modern life in ways that improve human existence. Others say that the promise of AI is overblown. Still others contend that AI applications could pose a grave threat to the economic security of millions of people by taking their jobs and otherwise rendering them "obsolete"-or, even worse, that AI could actually spell the end of the human race. This volume will help users understand the reasons AI development has both spirited defenders and alarmed critics; explain theories and innovations like Moore's Law, mindcloning, and Technological Singularity that drive AI research and debate; and give readers the information they need to make their own informed judgment about the promise and peril of this technology. All of this coverage is presented using language and terminology accessible to a lay audience. Introduction explaining the historical evolution of AI Chronology of important AI-related events Authoritative entries on leading pioneers, entrepreneurs, and thinkers; AI concepts and theories; AI's potential impact on different facets of society; and major movies and other cultural touchstones exploring AI technology

This book reports on the latest findings in the application of the wide area measurement systems (WAMS) in the analysis and control of power systems. The book collects new research ideas and achievements including a delay-dependent robust design method, a wide area robust coordination strategy, a hybrid assessment and choice method for wide area signals, a free-weighting matrices method and its application, as well as the online identification methods for low-frequency oscillations. The main original research results of this book are a comprehensive summary of the authors' latest six-year study. The book will be of interest to academic researchers, R&D engineers and graduate students in power systems who wish to learn the core principles, methods, algorithms, and applications of the WAMS.

The interest in control of nonlinear partial differential equation (PDE) sys tems has been triggered by the need to achieve tight distributed control of transport-reaction processes that exhibit highly nonlinear behavior and strong spatial variations. Drawing from recent advances in dynamics of PDE systems and nonlinear control theory, control of nonlinear PDEs has evolved into a very active research area of systems and control. This book the first of its kind- presents general methods for the synthesis of nonlinear and robust feedback controllers for broad classes of nonlinear PDE sys tems and illustrates their applications to transport-reaction processes of industrial interest. Specifically, our attention focuses on quasi-linear hyperbolic and parabolic PDE systems for which the manipulated inputs and measured and controlled outputs are distributed in space and bounded. We use geometric and Lyapunov-based control techniques to synthesize nonlinear and robust controllers that use a finite number of measurement sensors and control actuators to achieve stabilization of the closed-loop system, output track ing, and attenuation of the effect of model uncertainty. The controllers are successfully applied to numerous convection-reaction and diffusion-reaction processes, including a rapid thermal chemical vapor deposition reactor and a Czochralski crystal growth process. The book includes comparisons of the proposed nonlinear and robust control methods with other approaches and discussions of practical implementation issues."

] Starting with the research of G. Bogelsack in the 1970s, the analysis of biological locomotion andmanipulation systemsandtheirtechnical realizationhas beenan- portant research eld within the Faculty of Mechanical Engineering at the Ilmenau University of Technology. In 1996, the German Research Foundation (DFG) funded the Innovation College "Motion Systems" at the University of Jena in a coope- tion with engineers at the Ilmenau University of Technology. Thus, research was able to be intensi ed and extended. Of course, the whole spectrum of biologically inspired systems is much too wide, so the analysis was still focused on locomotion and manipulation systems. At this stage J. Steigenberger from the Faculty of Mathematics and Natural S- ences at the Ilmenau University of Technology contributed important studies of worm-like locomotion systems with much dedication and technical competence. Moreover, he conceived and carried out a lecture series entitled "Mathematical Basics for Locomotion Systems," which was based on his evaluation of national and international research developments in this eld. I. Zeidis and K. Zimmermann contributed many publications on the mechanics of worm-like locomotion systems based on continuum and rigid-body models as well as asymptotic methods. Since 2004 the German Research Foundation has supported a series of projects led by K. Zimmermann dedicated to biologically inspired robotics. In addition to these activities, the Department of Technical Mechanics and the Department of Computer Application in Mechanical Engineering (M. Weiss) together with masters and doctoral students started the development of mobile robots for the RoboCup Small-Size League in 1998."

This book focuses on two challenges posed in robot control by the increasing adoption of robots in the everyday human environment: uncertainty and networked communication. Part I of the book describes learning control to address environmental uncertainty. Part II discusses state estimation, active sensing, and complex scenario perception to tackle sensing uncertainty. Part III completes the book with control of networked robots and multi-robot teams. Each chapter features in-depth technical coverage and case studies highlighting the applicability of the techniques, with real robots or in simulation. Platforms include mobile ground, aerial, and underwater robots, as well as humanoid robots and robot arms. Source code and experimental data are available at http://extras.springer.com. The text gathers contributions from academic and industry experts, and offers a valuable resource for researchers or graduate students in robot control and perception. It also benefits researchers in related areas, such as computer vision, nonlinear and learning control, and multi-agent systems.

With businesses becoming ever more competitive, marketing strategies need to be more precise and performance oriented. Companies are investing considerably in analytical infrastructure for marketing. This new volume, Marketing Analytics: A Machine Learning Approach, enlightens readers on the application of analytics in marketing and the process of analytics, providing a foundation on the concepts and algorithms of machine learning and statistics. The book simplifies analytics for businesses and explains its uses in different aspects of marketing in a way that even marketers with no prior analytics experience will find it easy to follow, giving them to tools to make better business decisions. This volume gives a comprehensive overview of marketing analytics, incorporating machine learning methods of data analysis that automates analytical model building. The volume covers the important aspects of marketing analytics, including segmentation and targeting analysis, statistics for marketing, marketing metrics, consumer buying behavior, neuromarketing techniques for consumer analytics, new product development, forecasting sales and price, web and social media analytics, and much more. This well-organized and straight-forward volume will be valuable for marketers, managers, decision makers, and research scholars, and faculty in business marketing and information technology and would also be suitable for classroom use.

Industrial PID Controller Tuning presents a different view of the servo/regulator compromise that has been studied for a long time in industrial control research. Optimal tuning generally involves comparison of cost functions (e.g., a quadratic function of the error or a time-weighted absolute value of the error) but without taking advantage of available multi-objective optimization methods. The book does make use of multi-objective optimization to account for several sources of disturbance, applying them to a more realistic problem: how to select the tuning of a controller when both servo and regulator responses are important. The authors review the different deterministic multi-objective optimization methods. In order to ameliorate the consequences of the computational expense typically involved in their use-specifically the generation of multiple solutions among which the control engineer still has to choose-algorithms for two-degree-of-freedom PID control are implemented in MATLAB (R). MATLAB code and a MATLAB-compatible program are provided for download and will help readers to adapt the ideas presented in the text for use in their own systems. Further practical guidance is offered by the inclusion of several examples of common industrial processes amenable to the use of the authors' methods. Researchers interested in non-heuristic approaches to controller tuning or in decision-making after a Pareto set has been established and graduate students interested in beginning a career working with PID control and/or industrial controller tuning will find this book a valuable reference and source of ideas. Advances in Industrial Control reports and encourages the transfer of technology in control engineering. The rapid development of control technology has an impact on all areas of the control discipline. The series offers an opportunity for researchers to present an extended exposition of new work in all aspects of industrial control.

While sailing has a long tradition, both as a means of transportation and as a sport, robotic sailing is a fairly new area of research. One of its unique characteristics is the use of wind for propulsion. On the one hand, this allows for long range and long term autonomy. On the other hand, the dependency on changing winds presents a serious challenge for short and long term planning, collision avoidance, and boat control. Moreover, building a robust and seaworthy sailing robot is no simple task, leading to a truly interdisciplinary engineering problem. These proceedings summarize the state of the art as presented at the International Robotic Sailing Conference 2011. Following an overview of the history of autonomous sailing a number of recent boat designs is presented, ranging from small one-design boats to vessels built to cross the Atlantic Ocean. Subsequently, various aspects of system design and validation are discussed, further highlighting the interdisciplinary nature of the field. Finally, methods for collision avoidance, localization and route planning are covered.

Tele operation systems, in which robots are controlled remotely, are a potential solution to performing tasks in remote, small, and hazardous environments. However, there is a big disadvantage to these systems; as the direct connection between the human and the environment is lost and operators are deprived of their sense of touch. The recreation of touch feedback through haptic devices is a possible solution, however haptic devices are far from perfect and improving their design is usually a slow trial-and-error process. This book describes 7 scientific studies that try to break this slow loop by using a deductive approach. Through investigating fundamental properties of human haptic perception using psychophysical paradigms, general knowledge on haptic perception of force, position, movement and hardness was gained. The resulting information can be applied to many different haptic devices. Consequently haptic systems can be more easily designed in an intuitive, human-centered way.

This self-contained book, written by leading experts, offers a cutting-edge, in-depth overview of the filtering and control of wireless networked systems. It addresses the energy constraint and filter/controller gain variation problems, and presents both the centralized and the distributed solutions. The first two chapters provide an introduction to networked control systems and basic information on system analysis. Chapters (3-6) then discuss the centralized filtering of wireless networked systems, presenting different approaches to deal with energy efficiency and filter/controller gain variation problems. The next part (chapters 7-10) explores the distributed filtering of wireless networked systems, addressing the main problems of energy constraint and filter gain variation. The final part (chapters 11-14) focuses on the distributed control of wireless networked systems. In view of the rapid deployment and development of wireless networked systems for communication and control applications, the book represents a timely contribution and provides valuable insights, useful methods and effective algorithms for the analysis and design of wireless networked control systems. It is a valuable resource for researchers in the control and communication communities

The present book includes a set of selected papers from the third "International Conference on Informatics in Control Automation and Robotics" (ICINCO 2006), held in Setubal, Portugal, from 1 to 5 August 2006, sponsored by the Institute for Systems and Technologies of Information, Control and Communication (INSTICC). The conference was organized in three simultaneous tracks: "Intelligent Control Systems and Optimization," "Robotics and Automation" and "Systems Modeling, Signal Processing and Control." The book is based on the same structure. Although ICINCO 2006 received 309 paper submissions, from more than 50 different countries in all continents, only 31 where accepted as full papers. From those, only 23 were selected for inclusion in this book, based on the classifications provided by the Program Committee. The selected papers also reflect the interdisciplinary nature of the conference. The diversity of topics is an important feature of this conference, enabling an overall perception of several important scientific and technological trends. These high quality standards will be maintained and reinforced at ICINCO 2007, to be held in Angers, France, and in future editions of this conference."

Surveillance systems have become increasingly popular. Full involvement of human operators has led to shortcomings, e.g. high labor cost, limited capability for multiple screens, inconsistency in long-duration, etc. Intelligent surveillance systems (ISSs) can supplement or even replace traditional ones. In ISSs, computer vision, pattern recognition, and artificial intelligence technologies are used to identify abnormal behaviours in videos. They present the development of real-time behaviour-based intelligent surveillance systems. The book focuses on the detection of individual abnormal behaviour based on learning and the analysis of dangerous crowd behaviour based on texture and optical flow. Practical systems include a real-time face classification and counting system, a surveillance robot system that utilizes video and audio information for intelligent interaction, and a robust person counting system for crowded environments.

The book gives an introduction to networked control systems and describes new modeling paradigms, analysis methods for event-driven, digitally networked systems, and design methods for distributed estimation and control. Networked model predictive control is developed as a means to tolerate time delays and packet loss brought about by the communication network. In event-based control the traditional periodic sampling is replaced by state-dependent triggering schemes. Novel methods for multi-agent systems ensure complete or clustered synchrony of agents with identical or with individual dynamics. The book includes numerous references to the most recent literature. Many methods are illustrated by numerical examples or experimental results.

Real-Time Systems in Mechatronic Applications brings together in one place important contributions and up-to-date research results in this fast moving area. Real-Time Systems in Mechatronic Applications serves as an excellent reference, providing insight into some of the most challenging research issues in the field.

This book is devoted to a novel conceptual theoretical framework of neuro science and is an attempt to show that we can postulate a very small number of assumptions and utilize their heuristics to explain a very large spectrum of brain phenomena. The major assumption made in this book is that inborn and acquired neural automatisms are generated according to the same func tional principles. Accordingly, the principles that have been revealed experi mentally to govern inborn motor automatisms, such as locomotion and scratching, are used to elucidate the nature of acquired or learned automat isms. This approach allowed me to apply the language of control theory to describe functions of biological neural networks. You, the reader, can judge the logic of the conclusions regarding brain phenomena that the book derives from these assumptions. If you find the argument flawless, one can call it common sense and consider that to be the best praise for a chain of logical conclusions. For the sake of clarity, I have attempted to make this monograph as readable as possible. Special attention has been given to describing some of the concepts of optimal control theory in such a way that it will be under standable to a biologist or physician. I have also included plenty of illustra tive examples and references designed to demonstrate the appropriateness and applicability of these conceptual theoretical notions for the neurosciences."

Real-world supply chains and networks are inherently complex, formed by a large number of self-governing interconnected agents which dynamically update their behavior rules and connections based on context and environment changes. Oftentimes, these complex systems fail, almost inexplicably, due to unforeseen events leading to disruption. Exploration and research of the mechanisms behind the failure of supply chains and networks have revealed that those capable of surviving are not only robust, but resilient. The purpose of this book is to explain the meaning of resilience and its design in the broad context, and with a focus on the design and management of supply chains and supply networks. Written by Dr. Reyes Levalle, an experienced supply chains designer and supply networks engineer, the book is intended for beginners and advanced professionals, students, designers, policy makers, and managers. It is a pioneering effort to base resilience engineering and management on CCT, the collaborative control theory and tools.

This book provides a comprehensive treatment of the principles underlying optimal constrained control and estimation. The contents progress from optimisation theory, fixed-horizon discrete optimal control, receding-horizon implementations and stability conditions to explicit solutions and numerical algorithms, moving horizon estimation, and connections between constrained estimation and control. Several case studies and further developments illustrate and expand the core principles.

Specific topics covered include:

a [ An overview of optimisation theory.

a [ Links to optimal control theory, including the discrete-minimum principle.

a [ Linear and nonlinear receding-horizon constrained control including stability.

a [ Constrained control solutions having a finite parameterisation for specific classes of problems.

a [ Numerical procedures for solving constrained optimisation problems.

a [ Output feedback optimal constrained control.

a [ Constrained state estimation.

a [ Duality between constrained estimation and control.

a [ Applications to finite alphabet control and estimation problems, cross-directional control, rudder-roll stabilisation of ships, and control over communication networks.

Constrained Control and Estimation is a self-contained treatment assuming that the reader has a basic background in systems theory, including linear control, stability and state-space methods. It is suitable for use in senior-level courses and as material for reference and self-study. A companion website is continually updated by the authors.

Neural Networks in Robotics is the first book to present an integrated view of both the application of artificial neural networks to robot control and the neuromuscular models from which robots were created. The behavior of biological systems provides both the inspiration and the challenge for robotics. The goal is to build robots which can emulate the ability of living organisms to integrate perceptual inputs smoothly with motor responses, even in the presence of novel stimuli and changes in the environment. The ability of living systems to learn and to adapt provides the standard against which robotic systems are judged. In order to emulate these abilities, a number of investigators have attempted to create robot controllers which are modelled on known processes in the brain and musculo-skeletal system. Several of these models are described in this book. On the other hand, connectionist (artificial neural network) formulations are attractive for the computation of inverse kinematics and dynamics of robots, because they can be trained for this purpose without explicit programming. Some of the computational advantages and problems of this approach are also presented. For any serious student of robotics, Neural Networks in Robotics provides an indispensable reference to the work of major researchers in the field. Similarly, since robotics is an outstanding application area for artificial neural networks, Neural Networks in Robotics is equally important to workers in connectionism and to students for sensormonitor control in living systems.