Böcker i Studies in Computational Intelligence-serien

This book contributes to the progress towards intelligent transportation. It emphasizes new data management and machine learning approaches such as big data, deep learning and reinforcement learning. Deep learning and big data are very energetic and vital research topics of today's technology. Road sensors, UAVs, GPS, CCTV and incident reports are sources of massive amount of data which are crucial to make serious traffic decisions. Herewith this substantial volume and velocity of data, it is challenging to build reliable prediction models based on machine learning methods and traditional relational database. Therefore, this book includes recent research works on big data, deep convolution networks and IoT-based smart solutions to limit the vehicle's speed in a particular region, to support autonomous safe driving and to detect animals on roads for mitigating animal-vehicle accidents. This book serves broad readers including researchers, academicians, students and working professional in vehicles manufacturing, health and transportation departments and networking companies.

This book is focused on an emerging area, i.e. combination of IoT and semantic technologies, which should enable breaking the silos of local and/or domain-specific IoT deployments. Taking into account the way that IoT ecosystems are realized, several challenges can be identified. Among them of definite importance are (this list is, obviously, not exhaustive): (i) How to provide common representation and/or shared understanding of data that will enable analysis across (systematically growing) ecosystems? (ii) How to build ecosystems based on data flows? (iii) How to track data provenance? (iv) How to ensure/manage trust? (v) How to search for things/data within ecosystems? (vi) How to store data and assure its quality?Semantic technologies are often considered among the possible ways of addressing these (and other, related) questions. More precisely, in academic research and in industrial practice, semantic technologies materialize in the following contexts (this list is, also, not exhaustive, but indicates the breadth of scope of semantic technology usability): (i) representation of artefacts in IoT ecosystems and IoT networks, (ii) providing interoperability between heterogeneous IoT artefacts, (ii) representation of provenance information, enabling provenance tracking, trust establishment, and quality assessment, (iv) semantic search, enabling flexible access to data originating in different places across the ecosystem, (v) flexible storage of heterogeneous data. Finally, Semantic Web, Web of Things, and Linked Open Data are architectural paradigms, with which the aforementioned solutions are to be integrated, to provide production-ready deployments.

This book comprises carefully selected and reviewed outcomes of the 13th International Workshop on Automated Negotiations (ACAN) held in Vienna, 2022, in conjunction with International Joint Conference on Artificial Intelligence (IJCAI) 2022. It focuses on the applications and challenges of agent-based negotiation including agreement technology, mechanism design, electronic commerce, recommender systems, supply chain management, social choice theory, and others.This book is intended for the academic and industrial researchers of various communities of autonomous agents and multi-agent systems, as well as graduate students studying in those areas or having interest in them.

This edited book presents scientific results of the 21st ACIS International Winter Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD2021-Winter) which was held on January 28-30, at Ho Chi Minh City, Vietnam. The aim of this conference was to bring together researchers and scientists, businessmen and entrepreneurs, teachers, engineers, computer users, and students to discuss the numerous fields of computer science and to share their experiences and exchange new ideas and information in a meaningful way and research results about all aspects (theory, applications, and tools) of computer and information science, and to discuss the practical challenges encountered along the way and the solutions adopted to solve them.The conference organizers selected the best papers from those papers accepted for presentation at the conference. The papers were chosen based on review scores submitted by members of the program committee and underwent further rigorous rounds of review. From this second round of review, 18 of most promising papers are then published in this Springer (SCI) book and not the conference proceedings. We impatiently await the important contributions that we know these authors will bring to the field of computer and information science. 

This book highlights cutting-edge research in the field of network science, offering scientists, researchers, students, and practitioners a unique update on the latest advances in theory and a multitude of applications. It presents the peer-reviewed proceedings of the X International Conference on Complex Networks and their Applications (COMPLEX NETWORKS 2021). The carefully selected papers cover a wide range of theoretical topics such as network models and measures; community structure, network dynamics; diffusion, epidemics and spreading processes; resilience and control as well as all the main network applications, including social and political networks; networks in finance and economics; biological and neuroscience networks, and technological networks.

This book elaborately discusses techniques commonly used to improve generalization performance in classification approaches. The contents highlight methods to improve classification performance in numerous case studies: ranging from datasets of UCI repository to predictive maintenance problems and cancer classification problems. The book specifically provides a detailed tutorial on how to approach time-series classification problems and discusses two real time case studies on condition monitoring. In addition to describing the various aspects a data scientist must consider before finalizing their approach to a classification problem and reviewing the state of the art for improving classification generalization performance, it also discusses in detail the authors own contributions to the field, including MVPC - a classifier with very low VC dimension, a graphical indices based framework for reliable predictive maintenance and a novel general-purpose membership functions for Fuzzy Support Vector Machine which provides state of the art performance with noisy datasets, and a novel scheme to introduce deep learning in Fuzzy Rule based classifiers (FRCs). This volume will serve as a useful reference for researchers and students working on machine learning, health monitoring, predictive maintenance, time-series analysis, gene-expression data classification. 

The book covers several entity and relation extraction techniques starting from the traditional feature-based techniques to the recent techniques using deep neural models. Two important focus areas of the book are - i) joint extraction techniques where the tasks of entity and relation extraction are jointly solved, and ii) extraction of complex relations where relation types can be N-ary and cross-sentence. The first part of the book introduces the entity and relation extraction tasks and explains the motivation in detail. It covers all the background machine learning concepts necessary to understand the entity and relation extraction techniques explained later. The second part of the book provides a detailed survey of the traditional entity and relation extraction problems covering several techniques proposed in the last two decades. The third part of the book focuses on joint extraction techniques which attempt to address both the tasks of entity and relation extraction jointly. Several joint extraction techniques are surveyed and summarized in the book. It also covers two joint extraction techniques in detail which are based on the authors' work. The fourth and the last part of the book focus on complex relation extraction, where the relation types may be N-ary (having more than two entity arguments) and cross-sentence (entity arguments may span multiple sentences). The book highlights several challenges and some recent techniques developed for the extraction of such complex relations including the authors' technique. The book also covers a few domain-specific applications where the techniques for joint extraction as well as complex relation extraction are applied. 

This contributed volume consists of 11 chapters that specifically cover the security aspects of the latest technologies such as Blockchain, IoT, and DevOps, and how to effectively deal with them using Intelligent techniques. Moreover, machine learning (ML) and deep learning (DL) algorithms are also not secured and often manipulated by attackers for data stealing. This book also discusses the types of attacks and offers novel solutions to counter the attacks on ML and DL algorithms. This book describes the concepts and issues with figures and the supporting arguments with facts and charts. In addition to that, the book provides the comparison of different security solutions in terms of experimental results with tables and charts. Besides, the book also provides the future directions for each chapter and novel alternative approaches, wherever applicable. Often the existing literature provides domain-specific knowledge such as the description of security aspects. However, the readers find it difficult to understand how to tackle the application-specific security issues. This book takes one step forward and offers the security issues, current trends, and technologies supported by alternate solutions. Moreover, the book provides thorough guidance on the applicability of ML and DL algorithms to deal with application-specific security issues followed by novel approaches to counter threats to ML and DL algorithms. The book includes contributions from academicians, researchers, security experts, security architectures, and practitioners and provides an in-depth understanding of the mentioned issues.

This book contains select papers presented at the 3rd International Conference on Engineering Mathematics and Computing (ICEMC 2020), held at the Haldia Institute of Technology, Purba Midnapur, West Bengal, India, from 5-7 February 2020. The book discusses new developments and advances in the areas of neural networks, connectionist systems, genetic algorithms, evolutionary computation, artificial intelligence, cellular automata, self-organizing systems, soft computing, fuzzy systems, hybrid intelligent systems, etc. The book, containing 19 chapters, is useful to the researchers, scholars, and practising engineers as well as graduate students of engineering and applied sciences.

This book meets the present and future needs for the interaction between various science and technology/engineering areas on the one hand and different branches of soft computing on the other. Soft computing is the recent development about the computing methods which include fuzzy set theory/logic, evolutionary computation (EC), probabilistic reasoning, artificial neural networks, machine learning, expert systems, etc. Soft computing refers to a partnership of computational techniques in computer science, artificial intelligence, machine learning, and some other engineering disciplines, which attempt to study, model, and analyze complex problems from different interdisciplinary problems. This, as opposed to traditional computing, deals with approximate models and gives solutions to complex real-life problems. Unlike hard computing, soft computing is tolerant of imprecision, uncertainty, partial truth, and approximations. Interdisciplinary sciences include various challenging problems of science and engineering. Recent developments in soft computing are the bridge to handle different interdisciplinary science and engineering problems. In recent years, the correspondingly increased dialog between these disciplines has led to this new book. This is done, firstly, by encouraging the ways that soft computing may be applied in traditional areas, as well as point towards new and innovative areas of applications and secondly, by encouraging other scientific disciplines to engage in a dialog with the above computation algorithms outlining their problems to both access new methods as well as to suggest innovative developments within itself.

Modern AI techniques -- especially deep learning -- provide, in many cases, very good recommendations: where a self-driving car should go, whether to give a company a loan, etc. The problem is that not all these recommendations are good -- and since deep learning provides no explanations, we cannot tell which recommendations are good. It is therefore desirable to provide natural-language explanation of the numerical AI recommendations. The need to connect natural language rules and numerical decisions is known since 1960s, when the need emerged to incorporate expert knowledge -- described by imprecise words like "e;small"e; -- into control and decision making. For this incorporation, a special "e;fuzzy"e; technique was invented, that led to many successful applications. This book described how this technique can help to make AI more explainable.The book can be recommended for students, researchers, and practitioners interested in explainable AI.

This book brings the recent collection of smart technologies. Smart cities challenges and key requirements are discussed through the technological solutions, IoT, cloud computing, block chain and artificial intelligence. Firstly, the key technologies contributing to the smart cities research are identified. Then, the most popular ones are covered in context to their theoretical and practical applications.Smart cities technologies are one of the recent research areas. Every day new technological solutions are coming to make smart cities more sustainable. The book explores the integration of main key technologies for smart cities which are IoT & cloud computing, data science, AI and block chain & Industry 4.0. Moreover, some integrated solutions using AI, data science and IoT will attract the attention of end users.Primary market of the book is aimed toward the undergraduate and master students. IoT, cloud computing, artificial intelligence and block chain are elective courses at the bachelor level in the engineering domain, and its application areas in context to smart cities are covered in this book.The book is a good source of reference for their master dissertations. Ph.D. students or scholars who are working on these key technologies like IoT & cloud, AI, data science, block chain & Industry 4.0 will find this book as a constant source of reference for their ongoing research.Smart city planners, architects and municipal experts may also find this book useful.

This book presents explainability in edge AI, an amalgamation of edge computing and AI. The issues of transparency, fairness, accountability, explainability, interpretability, data-fusion, and comprehensibility that are significant for edge AI are being addressed in this book through explainable models and techniques. The concept of explainable edge AI is new in front of the academic and research community, and consequently, it will undoubtedly explore multiple research dimensions. The book presents the concept of explainability in edge AI which is the amalgamation of edge computing and AI. In the futuristic computing scenario, the goal of explainable edge AI will be to execute the AI tasks and produce explainable results at the edge. First, this book explains the fundamental concepts of explainable artificial intelligence (XAI), then it describes the concept of explainable edge AI, and finally, it elaborates on the technicalities of explainability in edge AI. Owing to the quick transition in the current computing scenario and integration with the latest AI-based technologies, it is significant to facilitate people-centric computing through explainable edge AI. Explainable edge AI will facilitate enhanced prediction accuracy with the comprehensible decision and traceability of actions performed at the edge and have a significant impact on futuristic computing scenarios. This book is highly relevant to graduate/postgraduate students, academicians, researchers, engineers, professionals, and other personnel working in artificial intelligence, machine learning, and intelligent systems.

This book is a collection of various methodologies that make it possible for metaheuristics and hyper-heuristics to solve problems that occur in the real world. This book contains chapters that make use of metaheuristics techniques. The application fields range from image processing to transmission power control, and case studies and literature reviews are included to assist the reader. Furthermore, some chapters present cutting-edge methods for load frequency control and IoT implementations. In this sense, the book offers both theoretical and practical contents in the form of metaheuristic algorithms. The researchers used several stochastic optimization methods in this book, including evolutionary algorithms and Swarm-based algorithms. The chapters were written from a scientific standpoint. As a result, the book is primarily aimed at undergraduate and postgraduate students of Science, Engineering, and Computational Mathematics, but it can also be used in courses on Artificial Intelligence, among other things. Similarly, the material may be beneficial to research in evolutionary computation and artificial intelligence communities.

This book provides a comprehensive discussion and new insights about linear optimization of content metrics to improve the automatic Evaluation of Text Summaries (ETS). The reader is first introduced to the background and fundamentals of the ETS. Afterward, state-of-the-art evaluation methods that require or do not require human references are described. Based on how linear optimization has improved other natural language processing tasks, we developed a new methodology based on genetic algorithms that optimize content metrics linearly. Under this optimization, we propose SECO-SEVA as an automatic evaluation metric available for research purposes. Finally, the text finishes with a consideration of directions in which automatic evaluation could be improved in the future. The information provided in this book is self-contained. Therefore, the reader does not require an exhaustive background in this area. Moreover, we consider this book the first one that deals with the ETS in depth.

This book is about the generalization and modernization of approximation by neural network operators. Functions under approximation and the neural networks are Banach space valued. These are induced by a great variety of activation functions deriving from the arctangent, algebraic, Gudermannian, and generalized symmetric sigmoid functions. Ordinary, fractional, fuzzy, and stochastic approximations are exhibited at the univariate, fractional, and multivariate levels. Iterated-sequential approximations are also covered. The book's results are expected to find applications in the many areas of applied mathematics, computer science and engineering, especially in artificial intelligence and machine learning. Other possible applications can be in applied sciences like statistics, economics, etc. Therefore, this book is suitable for researchers, graduate students, practitioners, and seminars of the above disciplines, also to be in all science and engineering libraries.

This book tackles the recent research trends on the role of AI in advancing automotive manufacturing, augmented reality, sustainable development in smart cities, telemedicine, and robotics. It sheds light on the recent AI innovations in classical machine learning, deep learning, Internet of Things (IoT), Blockchain, knowledge representation, knowledge management, big data, and natural language processing (NLP). The edited book covers empirical and reviews studies that primarily concentrate on the aforementioned issues, which would assist scholars in pursuing future research in the domain and identifying the possible future developments of AI applications.

The BCI technology finds newer and newer implementations. Year by year, the number of publications in this field grows exponentially. This book attempts to describe the implementation of the brain-computer technology based on both STM32 and Arduino microcontrollers. In addition, the application of BCI technology in the field of intelligent houses, robotic lines as well as in the field of bionic prostheses was presented. One of the chapters of the monograph also discusses the issue of fMRI in the context of the possibility of analyzing images made as part of fMRI through solutions based on machine learning. A practical implementation of the TensorFlow framework was presented. The fMRI technique is also often implemented in BCI solutions. The conducted literature studies show that the technology of BCI is undoubtedly a technology of the future. However, there is a need for continuous development of biomedical signal processing methods in order to obtain the most efficient implementations in the case of non-invasive implementation of BCI technology based on EEG. The further development of BCI technology has a huge impact on the techniques of rehabilitation of people with disabilities. Nowadays, wheelchairs are being constructed, thanks to which a disabled person is physically able to direct his position in a certain direction and at a certain speed. Thanks to BCI, it is also possible to create an individual speech synthesizer, with the help of which a paralyzed person will be able to communicate with the outside world. New limb prostheses that will replace the lost locomotor system in almost one hundred percent are still being developed. Some prostheses are connected to the human nervous system, thanks to which they are able to send feedback to our brain about the shape, hardness and temperature of the object held in the artificial limb.

This book is about turning data into smart decisions, knowledge into wisdom and business into business intelligence and insight. It explores diverse paradigms, methodologies, models, tools and techniques of the emerging knowledge domain of digitalized business analytics applications.The book covers almost every crucial aspect of applied artificial intelligence in business, smart mobile and digital services in business administration, marketing, accounting, logistics, finance and IT management.This book aids researchers, practitioners and decisions makers to gain enough knowledge and insight on how to effectively leverage data into competitive intelligence.

The main purpose of the present book is to develop a general framework for population-based metaheuristics based on some basic concepts of set theory. The idea of the framework is to divide the population of individuals into subpopulations of identical sizes. Therefore, in each iteration of the search process, different subpopulations explore the search space independently but simultaneously. The framework aims to provide a suitable balance between exploration and exploitation during the search process. A few chapters containing algorithm-specific modifications of some state-of-the-art metaheuristics are also included to further enrich the book.The present book is addressed to those scientists, engineers, and students who wish to explore the potentials of newly developed metaheuristics. The proposed metaheuristics are not only applicable to structural optimization problems but can also be used for other engineering optimization applications. The book is likely to be of interest to a wide range of engineers and students who deal with engineering optimization problems.

Manifold optimization is an emerging field of contemporary optimization that constructs efficient and robust algorithms by exploiting the specific geometrical structure of the search space. In our case the search space takes the form of a manifold. Manifold optimization methods mainly focus on adapting existing optimization methods from the usual "e;easy-to-deal-with"e; Euclidean search spaces to manifolds whose local geometry can be defined e.g. by a Riemannian structure. In this way the form of the adapted algorithms can stay unchanged. However, to accommodate the adaptation process, assumptions on the search space manifold often have to be made. In addition, the computations and estimations are confined by the local geometry.This book presents a framework for population-based optimization on Riemannian manifolds that overcomes both the constraints of locality and additional assumptions. Multi-modal, black-box manifold optimization problems on Riemannian manifolds can be tackled using zero-order stochastic optimization methods from a geometrical perspective, utilizing both the statistical geometry of the decision space and Riemannian geometry of the search space.This monograph presents in a self-contained manner both theoretical and empirical aspects of stochastic population-based optimization on abstract Riemannian manifolds.