This book presents selected papers from the 23rd Asia Pacific Symposium on Intelligent and Evolutionary Systems (IES 2019), which was held in Tottori, Japan, on December 6-8, 2019. Today, various types of intelligent system can be found everywhere. However, none of them can be developed or understood from only one perspective. As such, this book collects unique ways of thinking about intelligent systems. It discusses evolutionary and complex adaptive systems, which have been useful approaches for tackling intelligent systems. It also examines the recent developments in the field of artificial intelligence that are driving research on intelligent systems. Addressing topics related to intelligent transport systems, machine learning and neural networks, data science and decision analytics, evolutionary and nature-inspired computation, and agents and complex systems, this book is a valuable resource for researchers and practitioners wanting to develop or understand intelligent and evolutionary systems.

This book addresses several important aspects of complex automated negotiations and introduces a number of modern approaches for facilitating agents to conduct complex negotiations. It demonstrates that autonomous negotiation is one of the most important areas in the field of autonomous agents and multi-agent systems. Further, it presents complex automated negotiation scenarios that involve negotiation encounters that may have, for instance, a large number of agents, a large number of issues with strong interdependencies and/or real-time constraints.

This book presents new optimization approaches and methods and their application in real-world and industrial problems, and demonstrates how many of the problems arising in engineering, economics and other domains can be formulated as optimization problems. Constituting a comprehensive collection of extended contributions from the 9th International Workshop on Computational Optimization (WCO) held in Gdansk, Poland, September 11-14, 2016, the book discusses important applications such as job scheduling, wildfire modeling, parameter settings for controlling different processes, capital budgeting, data mining, finding the location of sensors in a given network, identifying the conformation of molecules, algorithm correctness, decision support system, and computer memory management. Further, it shows how to develop algorithms for these based on new intelligent methods like evolutionary computations, ant colony optimization and constraint programming. The book is a valuable resource for researchers and practitioners alike.

This present book includes a set of selected revised and extended versions of the best papers presented at the 10th International Joint Conference on Computational Intelligence (IJCCI 2018), held in Seville, Spain, from 18 to 20 September 2018, which covers four thriving fields in Computational Intelligence: Evolutionary Computation, Fuzzy Computation, Neural Computation, and Cognitive and Hybrid Systems. Besides presenting the recent advances in these areas, the book aims, on the one hand, to aggregate new and innovative solutions for confirmed researchers and, on the other hand, to provide a source of information and/or inspiration for young researchers or learners interested in the ever-increasing and current field of Computational Intelligence. This book constitutes a precious provision of knowledge for individual researchers as well as representing a valuable sustenance for collective use in academic libraries (of universities and engineering schools) relating innovative techniques in various fields of applications.

This book explores the significant role of granular computing in advancing machine learning towards in-depth processing of big data. It begins by introducing the main characteristics of big data, i.e., the five Vs-Volume, Velocity, Variety, Veracity and Variability. The book explores granular computing as a response to the fact that learning tasks have become increasingly more complex due to the vast and rapid increase in the size of data, and that traditional machine learning has proven too shallow to adequately deal with big data. Some popular types of traditional machine learning are presented in terms of their key features and limitations in the context of big data. Further, the book discusses why granular-computing-based machine learning is called for, and demonstrates how granular computing concepts can be used in different ways to advance machine learning for big data processing. Several case studies involving big data are presented by using biomedical data and sentiment data, in order to show the advances in big data processing through the shift from traditional machine learning to granular-computing-based machine learning. Finally, the book stresses the theoretical significance, practical importance, methodological impact and philosophical aspects of granular-computing-based machine learning, and suggests several further directions for advancing machine learning to fit the needs of modern industries. This book is aimed at PhD students, postdoctoral researchers and academics who are actively involved in fundamental research on machine learning or applied research on data mining and knowledge discovery, sentiment analysis, pattern recognition, image processing, computer vision and big data analytics. It will also benefit a broader audience of researchers and practitioners who are actively engaged in the research and development of intelligent systems.

This book introduces three key issues: (i) development of a gradient-free method to enable multi-objective self-optimization; (ii) development of a reinforcement learning strategy to carry out self-learning and finally, (iii) experimental evaluation and validation in two micromachining processes (i.e., micro-milling and micro-drilling). The computational architecture (modular, network and reconfigurable for real-time monitoring and control) takes into account the analysis of different types of sensors, processing strategies and methodologies for extracting behavior patterns from representative process' signals. The reconfiguration capability and portability of this architecture are supported by two major levels: the cognitive level (core) and the executive level (direct data exchange with the process). At the same time, the architecture includes different operating modes that interact with the process to be monitored and/or controlled. The cognitive level includes three fundamental modes such as modeling, optimization and learning, which are necessary for decision-making (in the form of control signals) and for the real-time experimental characterization of complex processes. In the specific case of the micromachining processes, a series of models based on linear regression, nonlinear regression and artificial intelligence techniques were obtained. On the other hand, the executive level has a constant interaction with the process to be monitored and/or controlled. This level receives the configuration and parameterization from the cognitive level to perform the desired monitoring and control tasks.

This book primarily illustrates the rationale, design and technical realization/verification for the cooperative guidance and control systems (CGCSs) of missile autonomous formation (MAF). From the seven functions to the five major compositions of CGCS, the book systematically explains the theory and modeling, analysis, synthesis and design of CGCSs for MAF, including bionics-based theories. Further, the book addresses how to create corresponding digital simulation analysis systems, as well as hardware in the loop (HIL) simulation test systems and flight test systems, to evaluate the combat effectiveness of MAF. Lastly, it provides detailed information on digital simulation analysis for a large range of wind tunnel test data, as well as test results of HIL system simulations and embedded systems testing.

Providing the most comprehensive source available, this book surveys the state of the art in artificial intelligence (AI) as it relates to architecture. This book is organized in four parts: theoretical foundations, tools and techniques, AI in research, and AI in architectural practice. It provides a framework for the issues surrounding AI and offers a variety of perspectives. It contains 24 consistently illustrated contributions examining seminal work on AI from around the world, including the United States, Europe, and Asia. It articulates current theoretical and practical methods, offers critical views on tools and techniques, and suggests future directions for meaningful uses of AI technology. Architects and educators who are concerned with the advent of AI and its ramifications for the design industry will find this book an essential reference.

The volume, complexity, and irregularity of computational data in modern algorithms and simulations necessitates an unorthodox approach to computing. Understanding the facets and possibilities of soft computing algorithms is necessary for the accurate and timely processing of complex data. Research Advances in the Integration of Big Data and Smart Computing builds on the available literature in the realm of Big Data while providing further research opportunities in this dynamic field. This publication provides the resources necessary for technology developers, scientists, and policymakers to adopt and implement new paradigms in computational methods across the globe. The chapters in this publication advance the body of knowledge on soft computing techniques through topics such as transmission control protocol for mobile ad hoc networks, feature extraction, comparative analysis of filtering techniques, big data in economic policy, and advanced dimensionality reduction methods.

This book shows how mathematics, computer science and science can be usefully and seamlessly intertwined. It begins with a general model of cognitive processes in a network of computational nodes, such as neurons, using a variety of tools from mathematics, computational science and neurobiology. It then moves on to solve the diffusion model from a low-level random walk point of view. It also demonstrates how this idea can be used in a new approach to solving the cable equation, in order to better understand the neural computation approximations. It introduces specialized data for emotional content, which allows a brain model to be built using MatLab tools, and also highlights a simple model of cognitive dysfunction.

Supervised sequence labelling is a vital area of machine learning, encompassing tasks such as speech, handwriting and gesture recognition, protein secondary structure prediction and part-of-speech tagging. Recurrent neural networks are powerful sequence learning tools-robust to input noise and distortion, able to exploit long-range contextual information-that would seem ideally suited to such problems. However their role in large-scale sequence labelling systems has so far been auxiliary. The goal of this book is a complete framework for classifying and transcribing sequential data with recurrent neural networks only. Three main innovations are introduced in order to realise this goal. Firstly, the connectionist temporal classification output layer allows the framework to be trained with unsegmented target sequences, such as phoneme-level speech transcriptions; this is in contrast to previous connectionist approaches, which were dependent on error-prone prior segmentation. Secondly, multidimensional recurrent neural networks extend the framework in a natural way to data with more than one spatio-temporal dimension, such as images and videos. Thirdly, the use of hierarchical subsampling makes it feasible to apply the framework to very large or high resolution sequences, such as raw audio or video. Experimental validation is provided by state-of-the-art results in speech and handwriting recognition.

This book presents studies involving algorithms in the machine learning paradigms. It discusses a variety of learning problems with diverse applications, including prediction, concept learning, explanation-based learning, case-based (exemplar-based) learning, statistical rule-based learning, feature extraction-based learning, optimization-based learning, quantum-inspired learning, multi-criteria-based learning and hybrid intelligence-based learning.

The last decades have seen the emergence of Complex Networks as the language with which a wide range of complex phenomena in fields as diverse as Physics, Computer Science, and Medicine (to name just a few) can be properly described and understood. This book provides a view of the state of the art in this dynamic field and covers topics ranging from network controllability, social structure, online behavior, recommendation systems, and network structure. This book includes the peer-reviewed list of works presented at the 7th Workshop on Complex Networks CompleNet 2016 which was hosted by the Universite de Bourgogne, France, from March 23-25, 2016. The 28 carefully reviewed and selected contributions in this book address many topics related to complex networks and have been organized in seven major groups: (1) Theory of Complex Networks, (2) Multilayer networks, (3) Controllability of networks, (4) Algorithms for networks, (5) Community detection, (6) Dynamics and spreading phenomena on networks, (7) Applications of Networks.

The book consists of 19 extended and revised chapters based on original works presented during a poster session organized within the 5th International Conference on Computational Collective Intelligence that was held between 11 and 13 of September 2013 in Craiova, Romania. The book is divided into three parts. The first part is titled "Agents and Multi-Agent Systems" and consists of 8 chapters that concentrate on many problems related to agent and multi-agent systems, including: formal models, agent autonomy, emergent properties, agent programming, agent-based simulation and planning. The second part of the book is titled "Intelligent Computational Methods" and consists of 6 chapters. The authors present applications of various intelligent computational methods like neural networks, mathematical optimization and multistage decision processes in areas like cooperation, character recognition, wireless networks, transport, and metal structures. The third part of the book is titled "Language and Knowledge Processing Systems," and consists of 5 papers devoted to processing methods for knowledge and language information in various applications, including: language identification, corpus comparison, opinion classification, group decision making, and rule bases.

This book presents non-linear image enhancement approaches to mammograms as a robust computer-aided analysis solution for the early detection of breast cancer, and provides a compendium of non-linear mammogram enhancement approaches: from the fundamentals to research challenges, practical implementations, validation, and advances in applications. The book includes a comprehensive discussion on breast cancer, mammography, breast anomalies, and computer-aided analysis of mammograms. It also addresses fundamental concepts of mammogram enhancement and associated challenges, and features a detailed review of various state-of-the-art approaches to the enhancement of mammographic images and emerging research gaps. Given its scope, the book offers a valuable asset for radiologists and medical experts (oncologists), as mammogram visualization can enhance the precision of their diagnostic analyses; and for researchers and engineers, as the analysis of non-linear filters is one of the most challenging research domains in image processing.

Vision-based control of wheeled mobile robots is an interesting field of research from a scientific and even social point of view due to its potential applicability. This book presents a formal treatment of some aspects of control theory applied to the problem of vision-based pose regulation of wheeled mobile robots. In this problem, the robot has to reach a desired position and orientation, which are specified by a target image. It is faced in such a way that vision and control are unified to achieve stability of the closed loop, a large region of convergence, without local minima and good robustness against parametric uncertainty. Three different control schemes that rely on monocular vision as unique sensor are presented and evaluated experimentally. A common benefit of these approaches is that they are valid for imaging systems obeying approximately a central projection model, e.g., conventional cameras, catadioptric systems and some fisheye cameras. Thus, the presented control schemes are generic approaches. A minimum set of visual measurements, integrated in adequate task functions, are taken from a geometric constraint imposed between corresponding image features. Particularly, the epipolar geometry and the trifocal tensor are exploited since they can be used for generic scenes. A detailed experimental evaluation is presented for each control scheme.

This book presents the latest research advances in complex network structure analytics based on computational intelligence (CI) approaches, particularly evolutionary optimization. Most if not all network issues are actually optimization problems, which are mostly NP-hard and challenge conventional optimization techniques. To effectively and efficiently solve these hard optimization problems, CI based network structure analytics offer significant advantages over conventional network analytics techniques. Meanwhile, using CI techniques may facilitate smart decision making by providing multiple options to choose from, while conventional methods can only offer a decision maker a single suggestion. In addition, CI based network structure analytics can greatly facilitate network modeling and analysis. And employing CI techniques to resolve network issues is likely to inspire other fields of study such as recommender systems, system biology, etc., which will in turn expand CI's scope and applications. As a comprehensive text, the book covers a range of key topics, including network community discovery, evolutionary optimization, network structure balance analytics, network robustness analytics, community-based personalized recommendation, influence maximization, and biological network alignment. Offering a rich blend of theory and practice, the book is suitable for students, researchers and practitioners interested in network analytics and computational intelligence, both as a textbook and as a reference work.

This research volume presents a sample of recent contributions related to the issue of quality-assessment for Web Based information in the context of information access, retrieval, and filtering systems.

The advent of the Web and the uncontrolled process of documents' generation have raised the problem of declining quality assessment to information on the Web, by considering both the nature of documents (texts, images, video, sounds, and so on), the genre of documents ( news, geographic information, ontologies, medical records, products records, and so on), the reputation of information sources and sites, and, last but not least the actions performed on documents (content indexing, retrieval and ranking, collaborative filtering, and so on).

The volume constitutes a compendium of both heterogeneous approaches and sample applications focusing specific aspects of the quality assessment for Web-based information for researchers, PhD students and practitioners carrying out their research activity in the field of Web information retrieval and filtering, Web information mining, information quality representation and management.

Computational and mathematical models provide us with the opportunities to investigate the complexities of real world problems. They allow us to apply our best analytical methods to define problems in a clearly mathematical manner and exhaustively test our solutions before committing expensive resources. This is made possible by assuming parameter(s) in a bounded environment, allowing for controllable experimentation, not always possible in live scenarios. For example, simulation of computational models allows the testing of theories in a manner that is both fundamentally deductive and experimental in nature. The main ingredients for such research ideas come from multiple disciplines and the importance of interdisciplinary research is well recognized by the scientific community. This book provides a window to the novel endeavours of the research communities to present their works by highlighting the value of computational modelling as a research tool when investigating complex systems. We hope that the readers will have stimulating experiences to pursue research in these directions.

This book focuses on open issues of new intelligent control paradigms and their usage. Industry 4.0 requires new approaches in the context of secure connection, control, and maintenance of robotic systems, as well as enhancing their interaction with humans. The book presents recent advances in industrial robotics, and robotic design and modeling for various domains, and discusses the methodological foundations of the collaborative robotics concept as a breakthrough in modern industrial technologies. It also describes the implementation of multi-agent models, programs and methods that could be used in future processes for control, condition assessment, diagnostics, prognostication, and proactive maintenance. Further, the book addresses the issue of ensuring the space robotics systems and proposes reliable novel solutions. The authors also illustrate the integration of deep-learning methods and mathematical modeling based on examples of successful robotic systems in various countries, and analyze the connections between robotic modeling and design from the positions of new industrial challenges. The book is intended for practitioners and enterprise representatives, as well as scientists and Ph.D. and Master's students pursuing research in the area of cyber-physical system development and implementation in various domains.

This book presents practical optimization techniques used in image processing and computer vision problems. Ill-posed problems are introduced and used as examples to show how each type of problem is related to typical image processing and computer vision problems. Unconstrained optimization gives the best solution based on numerical minimization of a single, scalar-valued objective function or cost function. Unconstrained optimization problems have been intensively studied, and many algorithms and tools have been developed to solve them. Most practical optimization problems, however, arise with a set of constraints. Typical examples of constraints include: (i) pre-specified pixel intensity range, (ii) smoothness or correlation with neighboring information, (iii) existence on a certain contour of lines or curves, and (iv) given statistical or spectral characteristics of the solution. Regularized optimization is a special method used to solve a class of constrained optimization problems. The term regularization refers to the transformation of an objective function with constraints into a different objective function, automatically reflecting constraints in the unconstrained minimization process. Because of its simplicity and efficiency, regularized optimization has many application areas, such as image restoration, image reconstruction, optical flow estimation, etc. Optimization plays a major role in a wide variety of theories for image processing and computer vision. Various optimization techniques are used at different levels for these problems, and this volume summarizes and explains these techniques as applied to image processing and computer vision.

This book develops a coherent and quite general theoretical approach to algorithm design for iterative learning control based on the use of operator representations and quadratic optimization concepts including the related ideas of inverse model control and gradient-based design. Using detailed examples taken from linear, discrete and continuous-time systems, the author gives the reader access to theories based on either signal or parameter optimization. Although the two approaches are shown to be related in a formal mathematical sense, the text presents them separately as their relevant algorithm design issues are distinct and give rise to different performance capabilities. Together with algorithm design, the text demonstrates the underlying robustness of the paradigm and also includes new control laws that are capable of incorporating input and output constraints, enable the algorithm to reconfigure systematically in order to meet the requirements of different reference and auxiliary signals and also to support new properties such as spectral annihilation. Iterative Learning Control will interest academics and graduate students working in control who will find it a useful reference to the current status of a powerful and increasingly popular method of control. The depth of background theory and links to practical systems will be of use to engineers responsible for precision repetitive processes.

This book presents an overview of a variety of contemporary statistical, mathematical and computer science techniques which are used to further the knowledge in the medical domain. The authors focus on applying data mining to the medical domain, including mining the sets of clinical data typically found in patient's medical records, image mining, medical mining, data mining and machine learning applied to generic genomic data and more. This work also introduces modeling behavior of cancer cells, multi-scale computational models and simulations of blood flow through vessels by using patient-specific models. The authors cover different imaging techniques used to generate patient-specific models. This is used in computational fluid dynamics software to analyze fluid flow. Case studies are provided at the end of each chapter. Professionals and researchers with quantitative backgrounds will find Computational Medicine in Data Mining and Modeling useful as a reference. Advanced-level students studying computer science, mathematics, statistics and biomedicine will also find this book valuable as a reference or secondary text book.

This volume introduces new approaches in intelligent control area from both the viewpoints of theory and application. It consists of eleven contributions by prominent authors from all over the world and an introductory chapter. This volume is strongly connected to another volume entitled "New Approaches in Intelligent Image Analysis" (Eds. Roumen Kountchev and Kazumi Nakamatsu). The chapters of this volume are self-contained and include summary, conclusion and future works. Some of the chapters introduce specific case studies of various intelligent control systems and others focus on intelligent theory based control techniques with applications. A remarkable specificity of this volume is that three chapters are dealing with intelligent control based on paraconsistent logics.

This book provides an insight on the importance that Internet of Vehicles (IoV) solutions can have in taking care of vehicular safety through internetworking and automation. Key features of the book are the inclusion and elaboration of recent and emerging developments in various specializations of intelligent transportation systems and their solutions by incorporating IoT (Internet of Things) and IoV. This book presents to its readers useful IoV applications and architectures that cater to their improved driving requirements and lead towards autonomous driving. The application domains have a large range in which vehicular networking, communication technology, sensor devices, computing materials and devices, IoT communication, vehicular and on-road safety, data security and other topics are included.