Cognitive Intelligence and Robotics – serie

Noisy optimization is a topic of growing interest for researchers working on mainstream optimization problems. Although several techniques for dealing with stochastic noise in optimization problems are covered in journals and conference proceedings, today there are virtually no books that approach noisy optimization from a layman’s perspective; this book remedies that gap. Beginning with the foundations of evolutionary optimization, the book subsequently explores the principles of noisy optimization in single and multi-objective settings, and presents detailed illustrations of the principles developed for application in real-world multi-agent coordination problems. Special emphasis is given to the design of intelligent algorithms for noisy optimization in real-time applications. The book is unique in terms of its content, writing style and above all its simplicity, which will appeal to readers with a broad range of backgrounds.The book is divided into 7 chapters, the first of which provides an introduction to Swarm and Evolutionary Optimization algorithms. Chapter 2 includes a thorough review of agent architectures for multi-agent coordination. In turn, Chapter 3 provides an extensive review of noisy optimization, while Chapter 4 addresses issues of noise handling in the context of single-objective optimization problems. An illustrative case study on multi-robot path-planning in the presence of measurement noise is also highlighted in this chapter. Chapter 5 deals with noisy multi-objective optimization and includes a case study on noisy multi-robot box-pushing. In Chapter 6, the authors examine the scope of various algorithms in noisy optimization problems. Lastly, Chapter 7 summarizes the main results obtained in the previous chapters and elaborates on the book’s potential with regard to real-world noisy optimization problems.

This book discusses systematic designs of stable adaptive fuzzy logic controllers employing hybridizations of Lyapunov strategy-based approaches/H∞ theory-based approaches and contemporary stochastic optimization techniques. The text demonstrates how candidate stochastic optimization techniques like Particle swarm optimization (PSO), harmony search (HS) algorithms, covariance matrix adaptation (CMA) etc. can be utilized in conjunction with the Lyapunov theory/H∞ theory to develop such hybrid control strategies. The goal of developing a series of such hybridization processes is to combine the strengths of both Lyapunov theory/H∞ theory-based local search methods and stochastic optimization-based global search methods, so as to attain superior control algorithms that can simultaneously achieve desired asymptotic performance and provide improved transient responses. The book also demonstrates how these intelligent adaptive control algorithms can be effectively utilized in real-life applications such as in temperature control for air heater systems with transportation delay, vision-based navigation of mobile robots, intelligent control of robot manipulators etc.

This book shows ways of augmenting the capabilities of Natural Language Processing (NLP) systems by means of cognitive-mode language processing. The authors employ eye-tracking technology to record and analyze shallow cognitive information in the form of gaze patterns of readers/annotators who perform language processing tasks. The insights gained from such measures are subsequently translated into systems that help us (1) assess the actual cognitive load in text annotation, with resulting increase in human text-annotation efficiency, and (2) extract cognitive features that, when added to traditional features, can improve the accuracy of text classifiers. In sum, the authors’ work successfully demonstrates that cognitive information gleaned from human eye-movement data can benefit modern NLP. Currently available Natural Language Processing (NLP) systems are weak AI systems: they seek to capture the functionality of human language processing, without worrying about how thisprocessing is realized in human beings’ hardware. In other words, these systems are oblivious to the actual cognitive processes involved in human language processing. This ignorance, however, is NOT bliss! The accuracy figures of all non-toy NLP systems saturate beyond a certain point, making it abundantly clear that “something different should be done.”

This book presents the basics of search engines and their components. It introduces, for the first time, the concept of Cellular Automata in Web technology and discusses the prerequisites of Cellular Automata. In today’s world, searching data from the World Wide Web is a common phenomenon for virtually everyone. It is also a fact that searching the tremendous amount of data from the Internet is a mammoth task – and handling the data after retrieval is even more challenging. In this context, it is important to understand the need for space efficiency in data storage. Though Cellular Automata has been utilized earlier in many fields, in this book the authors experiment with employing its strong mathematical model to address some critical issues in the field of Web Mining.

This book discusses systematic designs of stable adaptive fuzzy logic controllers employing hybridizations of Lyapunov strategy-based approaches/H∞ theory-based approaches and contemporary stochastic optimization techniques. The text demonstrates how candidate stochastic optimization techniques like Particle swarm optimization (PSO), harmony search (HS) algorithms, covariance matrix adaptation (CMA) etc. can be utilized in conjunction with the Lyapunov theory/H∞ theory to develop such hybrid control strategies. The goal of developing a series of such hybridization processes is to combine the strengths of both Lyapunov theory/H∞ theory-based local search methods and stochastic optimization-based global search methods, so as to attain superior control algorithms that can simultaneously achieve desired asymptotic performance and provide improved transient responses. The book also demonstrates how these intelligent adaptive control algorithms can be effectively utilized in real-life applications such as in temperature control for air heater systems with transportation delay, vision-based navigation of mobile robots, intelligent control of robot manipulators etc.

This book shows ways of augmenting the capabilities of Natural Language Processing (NLP) systems by means of cognitive-mode language processing. The authors employ eye-tracking technology to record and analyze shallow cognitive information in the form of gaze patterns of readers/annotators who perform language processing tasks. The insights gained from such measures are subsequently translated into systems that help us (1) assess the actual cognitive load in text annotation, with resulting increase in human text-annotation efficiency, and (2) extract cognitive features that, when added to traditional features, can improve the accuracy of text classifiers. In sum, the authors’ work successfully demonstrates that cognitive information gleaned from human eye-movement data can benefit modern NLP. Currently available Natural Language Processing (NLP) systems are weak AI systems: they seek to capture the functionality of human language processing, without worrying about how thisprocessing is realized in human beings’ hardware. In other words, these systems are oblivious to the actual cognitive processes involved in human language processing. This ignorance, however, is NOT bliss! The accuracy figures of all non-toy NLP systems saturate beyond a certain point, making it abundantly clear that “something different should be done.”

This book presents state-of-the-art research on intrusion detection using reinforcement learning, fuzzy and rough set theories, and genetic algorithm. Reinforcement learning is employed to incrementally learn the computer network behavior, while rough and fuzzy sets are utilized to handle the uncertainty involved in the detection of traffic anomaly to secure data resources from possible attack. Genetic algorithms make it possible to optimally select the network traffic parameters to reduce the risk of network intrusion. The book is unique in terms of its content, organization, and writing style. Primarily intended for graduate electrical and computer engineering students, it is also useful for doctoral students pursuing research in intrusion detection and practitioners interested in network security and administration. The book covers a wide range of applications, from general computer security to server, network, and cloud security.

This book presents state-of-the-art research on intrusion detection using reinforcement learning, fuzzy and rough set theories, and genetic algorithm. Reinforcement learning is employed to incrementally learn the computer network behavior, while rough and fuzzy sets are utilized to handle the uncertainty involved in the detection of traffic anomaly to secure data resources from possible attack. Genetic algorithms make it possible to optimally select the network traffic parameters to reduce the risk of network intrusion. The book is unique in terms of its content, organization, and writing style. Primarily intended for graduate electrical and computer engineering students, it is also useful for doctoral students pursuing research in intrusion detection and practitioners interested in network security and administration. The book covers a wide range of applications, from general computer security to server, network, and cloud security.

This book describes the development of an integrated approach for generating the path and gait of realistic hexapod robotic systems. It discusses in detail locomation with straight-ahead, crab and turning motion capabilities in varying terrains, like sloping surfaces, staircases, and various user-defined rough terrains. It also presents computer simulations and validation using Virtual Prototyping (VP) tools and real-world experiments. The book also explores improving solutions by applying the developed nonlinear, constrained inverse dynamics model of the system formulated as a coupled dynamical problem based on the Newton–Euler (NE) approach and taking into account realistic environmental conditions. The approach is developed on the basis of rigid multi-body modelling and the concept that there is no change in the configuration of the system in the short time span of collisions.

This book describes the development of an integrated approach for generating the path and gait of realistic hexapod robotic systems. It discusses in detail locomation with straight-ahead, crab and turning motion capabilities in varying terrains, like sloping surfaces, staircases, and various user-defined rough terrains. It also presents computer simulations and validation using Virtual Prototyping (VP) tools and real-world experiments. The book also explores improving solutions by applying the developed nonlinear, constrained inverse dynamics model of the system formulated as a coupled dynamical problem based on the Newton–Euler (NE) approach and taking into account realistic environmental conditions. The approach is developed on the basis of rigid multi-body modelling and the concept that there is no change in the configuration of the system in the short time span of collisions.

This book discusses human emotion recognition from face images using different modalities, highlighting key topics in facial expression recognition, such as the grid formation, distance signature, shape signature, texture signature, feature selection, classifier design, and the combination of signatures to improve emotion recognition. The book explains how six basic human emotions can be recognized in various face images of the same person, as well as those available from benchmark face image databases like CK+, JAFFE, MMI, and MUG. The authors present the concept of signatures for different characteristics such as distance and shape texture, and describe the use of associated stability indices as features, supplementing the feature set with statistical parameters such as range, skewedness, kurtosis, and entropy. In addition, they demonstrate that experiments with such feature choices offer impressive results, and that performance can be further improved by combining thesignatures rather than using them individually.There is an increasing demand for emotion recognition in diverse fields, including psychotherapy, biomedicine, and security in government, public and private agencies. This book offers a valuable resource for researchers working in these areas.

This book discusses human emotion recognition from face images using different modalities, highlighting key topics in facial expression recognition, such as the grid formation, distance signature, shape signature, texture signature, feature selection, classifier design, and the combination of signatures to improve emotion recognition. The book explains how six basic human emotions can be recognized in various face images of the same person, as well as those available from benchmark face image databases like CK+, JAFFE, MMI, and MUG. The authors present the concept of signatures for different characteristics such as distance and shape texture, and describe the use of associated stability indices as features, supplementing the feature set with statistical parameters such as range, skewedness, kurtosis, and entropy. In addition, they demonstrate that experiments with such feature choices offer impressive results, and that performance can be further improved by combining thesignatures rather than using them individually.There is an increasing demand for emotion recognition in diverse fields, including psychotherapy, biomedicine, and security in government, public and private agencies. This book offers a valuable resource for researchers working in these areas.

This book systematically introduces readers to the theory of deep learning and explores its practical applications based on the MindSpore AI computing framework. Divided into 14 chapters, the book covers deep learning, deep neural networks (DNNs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), unsupervised learning, deep reinforcement learning, automated machine learning, device-cloud collaboration, deep learning visualization, and data preparation for deep learning. To help clarify the complex topics discussed, this book includes numerous examples and links to online resources.

This book systematically introduces readers to the theory of deep learning and explores its practical applications based on the MindSpore AI computing framework. Divided into 14 chapters, the book covers deep learning, deep neural networks (DNNs), convolutional neural networks (CNNs), recurrent neural networks (RNNs), unsupervised learning, deep reinforcement learning, automated machine learning, device-cloud collaboration, deep learning visualization, and data preparation for deep learning. To help clarify the complex topics discussed, this book includes numerous examples and links to online resources.

Autonomous underwater vehicles (AUVs) are emerging as a promising solution to help us explore and understand the ocean. The global market for AUVs is predicted to grow from 638 million dollars in 2020 to 1,638 million dollars by 2025 – a compound annual growth rate of 20.8 percent. To make AUVs suitable for a wider range of application-specific missions, it is necessary to deploy multiple AUVs to cooperatively perform the localization, tracking and formation tasks. However, weak underwater acoustic communication and the model uncertainty of AUVs make achieving this challenging. This book presents cutting-edge results regarding localization, tracking and formation for AUVs, highlighting the latest research on commonly encountered AUV systems. It also showcases several joint localization and tracking solutions for AUVs. Lastly, it discusses future research directions and provides guidance on the design of future localization, tracking and formation schemes for AUVs. Representing a substantial contribution to nonlinear system theory, robotic control theory, and underwater acoustic communication system, this book will appeal to university researchers, scientists, engineers, and graduate students in control theory and control engineering who wish to learn about the core principles, methods, algorithms, and applications of AUVs. Moreover, the practical localization, tracking and formation schemes presented provide guidance on exploring the ocean. The book is intended for those with an understanding of nonlinear system theory, robotic control theory, and underwater acoustic communication systems.

Autonomous underwater vehicles (AUVs) are emerging as a promising solution to help us explore and understand the ocean. The global market for AUVs is predicted to grow from 638 million dollars in 2020 to 1,638 million dollars by 2025 – a compound annual growth rate of 20.8 percent. To make AUVs suitable for a wider range of application-specific missions, it is necessary to deploy multiple AUVs to cooperatively perform the localization, tracking and formation tasks. However, weak underwater acoustic communication and the model uncertainty of AUVs make achieving this challenging. This book presents cutting-edge results regarding localization, tracking and formation for AUVs, highlighting the latest research on commonly encountered AUV systems. It also showcases several joint localization and tracking solutions for AUVs. Lastly, it discusses future research directions and provides guidance on the design of future localization, tracking and formation schemes for AUVs. Representing a substantial contribution to nonlinear system theory, robotic control theory, and underwater acoustic communication system, this book will appeal to university researchers, scientists, engineers, and graduate students in control theory and control engineering who wish to learn about the core principles, methods, algorithms, and applications of AUVs. Moreover, the practical localization, tracking and formation schemes presented provide guidance on exploring the ocean. The book is intended for those with an understanding of nonlinear system theory, robotic control theory, and underwater acoustic communication systems.

As technologies are fast advancing, the importance of text detection and recognition is receiving special attention from the researchers. Thus, one can see several real-time applications of video text processing which requires cognitive-based methods to find a solution. The main applications are (1) retrieving and indexing video based on semantic of the content of the video, (2) machine translation to assist foreigners, (3) assisting blind people to walk on the road freely without aid, (4) automatic vehicle driving, (5) license plate tracing to catch vehicles which violate the traffic signals, (6) monitoring the images posted on social media based on text and content of the images, (7) identifying the location based on the address of the street and shops, etc., (8) tracing players in the sports based on the jersey/bib number or text, and (9) in the same way, tracing the bib number in case of marathon and other events. For the above-mentioned applications, text detection and recognitionin video and natural scene images is an integral part of the system.

As technologies are fast advancing, the importance of text detection and recognition is receiving special attention from the researchers. Thus, one can see several real-time applications of video text processing which requires cognitive-based methods to find a solution. The main applications are (1) retrieving and indexing video based on semantic of the content of the video, (2) machine translation to assist foreigners, (3) assisting blind people to walk on the road freely without aid, (4) automatic vehicle driving, (5) license plate tracing to catch vehicles which violate the traffic signals, (6) monitoring the images posted on social media based on text and content of the images, (7) identifying the location based on the address of the street and shops, etc., (8) tracing players in the sports based on the jersey/bib number or text, and (9) in the same way, tracing the bib number in case of marathon and other events. For the above-mentioned applications, text detection and recognitionin video and natural scene images is an integral part of the system.

This book is dedicated for engineers and researchers who would like to increase the knowledge in area of mobile mapping systems. Therefore, the flow of the derived information is divided into subproblems corresponding to certain mobile mapping data and related observations’ equations. The proposed methodology is not fulfilling all SLAM aspects evident in the literature, but it is based on the experience within the context of the pragmatic and realistic applications. Thus, it can be supportive information for those who are familiar with SLAM and would like to have broader overview in the subject.The novelty is a complete and interdisciplinary methodology for large-scale mobile mapping applications. The contribution is a set of programming examples available as supportive complementary material for this book. All observation equations are implemented, and for each, the programming example is provided. The programming examples are simple C++ implementationsthat can be elaborated by students or engineers; therefore, the experience in coding is not mandatory.Moreover, since the implementation does not require many additional external programming libraries, it can be easily integrated with any mobile mapping framework. Finally, the purpose of this book is to collect all necessary observation equations and solvers to build computational system capable providing large-scale maps.

This book is dedicated for engineers and researchers who would like to increase the knowledge in area of mobile mapping systems. Therefore, the flow of the derived information is divided into subproblems corresponding to certain mobile mapping data and related observations’ equations. The proposed methodology is not fulfilling all SLAM aspects evident in the literature, but it is based on the experience within the context of the pragmatic and realistic applications. Thus, it can be supportive information for those who are familiar with SLAM and would like to have broader overview in the subject.The novelty is a complete and interdisciplinary methodology for large-scale mobile mapping applications. The contribution is a set of programming examples available as supportive complementary material for this book. All observation equations are implemented, and for each, the programming example is provided. The programming examples are simple C++ implementationsthat can be elaborated by students or engineers; therefore, the experience in coding is not mandatory.Moreover, since the implementation does not require many additional external programming libraries, it can be easily integrated with any mobile mapping framework. Finally, the purpose of this book is to collect all necessary observation equations and solvers to build computational system capable providing large-scale maps.

Instead of focusing on the mathematical properties of moments, this book is a compendium of research that demonstrates the effectiveness of orthogonal moment-based features in face recognition, expression recognition, fingerprint recognition and iris recognition. The usefulness of moments and their invariants in pattern recognition is well known. What is less well known is how orthogonal moments may be applied to specific problems in human-centric visual pattern recognition. Unlike previous books, this work highlights the fundamental issues involved in moment-based pattern recognition, from the selection of discriminative features in a high-dimensional setting, to addressing the question of how to classify a large number of patterns based on small training samples. In addition to offering new concepts that illustrate the use of statistical methods in addressing some of these issues, the book presents recent results and provides guidance on implementing the methods. Accordingly, it will be of interest to researchers and graduate students working in the broad areas of computer vision and visual pattern recognition.

Instead of focusing on the mathematical properties of moments, this book is a compendium of research that demonstrates the effectiveness of orthogonal moment-based features in face recognition, expression recognition, fingerprint recognition and iris recognition. The usefulness of moments and their invariants in pattern recognition is well known. What is less well known is how orthogonal moments may be applied to specific problems in human-centric visual pattern recognition. Unlike previous books, this work highlights the fundamental issues involved in moment-based pattern recognition, from the selection of discriminative features in a high-dimensional setting, to addressing the question of how to classify a large number of patterns based on small training samples. In addition to offering new concepts that illustrate the use of statistical methods in addressing some of these issues, the book presents recent results and provides guidance on implementing the methods. Accordingly, it will be of interest to researchers and graduate students working in the broad areas of computer vision and visual pattern recognition.

With the rapid development of robotics and communication technologies, maritime unmanned systems (MUSs) have emerged as a critical research domain due to their unprecedented capabilities in oceanographic data collection, environmental monitoring, and marine ecosystem studies. Specifically, MUSs refer to interoperable robotic systems operating synergistically in aerial, surface and underwater environments. At present, MUSs exhibit the characteristics of diversified sensing resources, decentralized architectures, and systematic coordination, making the detection-communication-control crucial for efficient operations and multi-mission adaptability. However, the traditional research predominantly adopts separate design approaches for detection, communication and control in MUSs. The separate design creates dual constraints: the detection-communication interactions lack effective feedback mechanisms while the control commands become vulnerable to information incompleteness. To address the above issue, it is urgent to co-design the detection, communication and control for MUSs. This research direction has profound strategic significance and long-term value for the future development and application of marine technology.This book is devoted to present the cutting-edge results on the integrated design of detection, communication, and control for MUSs. It first elaborates on the basic concepts of detection, communication and control in maritime environment. After that, it presents several integrated design solutions for the detection, communication, and control in MUSs, including detection-communication integration, detection-control integration, communication-control integration, and detection-communication-control integration. Finally, this book concludes with practical applications of these integrated design methodologies in modern port monitoring systems, demonstrating their effectiveness in real-world maritime scenarios.The book provides actionable insights of developing next-generation MUSs for the researchers, engineers, and practitioners in maritime robotics, autonomous systems, and networked control. A background in control theory, signal processing, or wireless communication is recommended to fully grasp the advanced techniques. Whether you're advancing academic research or optimizing industrial systems, this book equips you with cutting-edge tools to push the boundaries of maritime autonomy.

This book focuses on the practical challenges in the process of UAV cooperative control from three aspects: the first to satisfy the task requirement of convergence time for multi-UAV system, the second to fit the actual capability of transmission, computation and communication for multi-UAV system, the third to ensure safety in the presence of strong disturbances and DoS attack for multi-UAV system. In addition, this book presents the cooperative control design from inner-loop velocity and attitude tracking to outer-loop position motions of multiple UAVs. It offers readers with deep understanding and insights on reliability, adaptability and safety of multi-UAV system and the corresponding control designs.The advanced cooperative control methods presented in this book can provide guidelines for engineers to improve the reliability, adaptability and safety of aerospace engineering systems and some other related fields. This book is suitable for scientists and researchers, aerospace engineers, control engineers, lecturers and teachers, postgraduates, undergraduates in the system and control community, especially those engaged in the field of UAV cooperation and multi-agent systems.

Anomaly detection in video surveillance stands at the core of numerous real-world applications that have broad impact and generate significant academic and industrial value. The key advantage of writing the book at this point in time is that the vast amount of work done by computer scientists over the last few decades has remained largely untouched by a formal book on the subject, although these techniques significantly advance existing methods of image and video analysis and understanding by taking advantage of anomaly detection in the data mining community and visual analysis in the computer vision community. The proposed book provides a comprehensive coverage of the advances in video based anomaly detection, including topics such as the theories of anomaly detection and machine perception for the functional analysis of abnormal events in general, the identification of abnormal behaviour and crowd abnormal behaviour in particular, the current understanding of computer vision development, and the application of this present understanding towards improving video-based anomaly detection in theory and coding with OpenCV. The book also provides a perspective on deep learning on human action recognition and behaviour analysis, laying the groundwork for future advances in these areas. Overall, the chapters of this book have been carefully organized with extensive bibliographic notes attached to each chapter. One of the goals is to provide the first systematic and comprehensive description of the range of data-driven solutions currently being developed up to date for such purposes. Another is to serve a dual purpose so that students and practitioners can use it as a textbook while researchers can use it as a reference book. A final goal is to provide a comprehensive exposition of the topic of anomaly detection in video media from multiple points of view.

Multi-robot coordinated fencing, where a team of robots forms a protective formation around a target, has garnered significant attention and proven useful in practical applications such as area convoying. However, real-world scenarios often involve complex target characteristics, including varying dynamics and multiple targets, which can pose challenges in maintaining the formation. Additionally, due to sensor costs and environmental constraints, robots may only have access to directional constraint information, presenting further challenges.This book highlights cooperative fencing approaches for multi-robot systems and their practical applications to different unmanned surface (ground) vehicles, providing an overview of research trends and future directions in coordinated fencing. Firstly, a basic fencing controller using neighboring angle repulsion for a constant-velocity target is designed, laying the groundwork for complex fencing missions. Then, for more complex fencing with an evenly rotating formation, a distributed controller is developed using input-to-state stability, achieving coordinated fencing under intermittently varying topologies. For more complex varying-velocity targets, a distributed fencing controller based on output regulation theory is proposed. For general target fencing missions in both 2D and 3D, a formal long-term task execution framework is developed using control barrier functions. Moreover, unlike previous methods that rely on the relative position between the robot and the target, a distributed bearing-only fencing control algorithm based on the persistent-excitation condition is developed, requiring only comparatively inexpensive sensors. Finally, this exploration into the theory and application of coordinated fencing control provides guidelines for robust, efficient, and complex practical implementations of multi-robot missions.