Collaboratively Constructed Language Resources (CCLRs) such as Wikipedia, Wiktionary, Linked Open Data, and various resources developed using crowdsourcing techniques such as Games with a Purpose and Mechanical Turk have substantially contributed to the research in natural language processing (NLP). Various NLP tasks utilize such resources to substitute for or supplement conventional lexical semantic resources and linguistically annotated corpora. These resources also provide an extensive body of texts from which valuable knowledge is mined. There are an increasing number of community efforts to link and maintain multiple linguistic resources.
This book aims offers comprehensive coverage of CCLR-related topics, including their construction, utilization in NLP tasks, and interlinkage and management.Various Bachelor/Master/Ph.D. programs in natural language processing, computational linguistics, and knowledge discovery can use this book both as the main text and as a supplementary reading.The bookalso provides a valuable reference guide for researchers and professionalsforthe above topics."

This volume contains a contemporary, integrated description of the processes of language. These range from fast scales (fractions of a second) to slow ones (over a million years). The contributors, all experts in their fields, address language in the brain, production of sentences and dialogues, language learning, transmission and evolutionary processes that happen over centuries or millenia, the relation between language and genes, the origins of language, self-organization, and language competition and death. The book as a whole will help to show how processes at different scales affect each other, thus presenting language as a dynamic, complex and profoundly human phenomenon.

There isn't a facet of human life that has not been touched and influenced by robots and automation. What makes robots and machines versatile is their computational intelligence. While modern intelligent sensors and powerful hardware capabilities have given a huge fillip to the growth of intelligent machines, the progress in the development of algorithms for smart interaction, collaboration and pro-activeness will result in the next quantum jump.

This book deals with the recent advancements in design methodologies, algorithms and implementation techniques to incorporate intelligence in "robots and automation systems." Several articles deal with navigation, localization and mapping of mobile robots, a problem that engineers and researchers are grappling with all the time. Fuzzy logic, neural networks and neuro-fuzzy based techniques for real world applications have been detailed in a few articles.

This edited volume is targeted to present the latest state-of-the-art computational intelligence techniques in Robotics and Automation. It is a compilation of the extended versions of the very best papers selected from the many that were presented at the 5th International Conference on Automation, Robotics and Applications (ICARA 2011) which was held in Wellington, New Zealand from 6-8 December, 2011. Scientists and engineers who work with robots and automation systems will find this book very useful and stimulating.

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.

Decision trees and decision rule systems are widely used in different applications as algorithms for problem solving, as predictors, and as a way for knowledge representation. Reducts play key role in the problem of attribute (feature) selection. The aims of this book are (i) the consideration of the sets of decision trees, rules and reducts; (ii) study of relationships among these objects; (iii) design of algorithms for construction of trees, rules and reducts; and (iv) obtaining bounds on their complexity. Applications for supervised machine learning, discrete optimization, analysis of acyclic programs, fault diagnosis, and pattern recognition are considered also. This is a mixture of research monograph and lecture notes. It contains many unpublished results. However, proofs are carefully selected to be understandable for students. The results considered in this book can be useful for researchers in machine learning, data mining and knowledge discovery, especially for those who are working in rough set theory, test theory and logical analysis of data. The book can be used in the creation of courses for graduate students.

The book presents a knowledge discovery based approach to build a recommender system supporting a physician in treating tinnitus patients with the highly successful method called Tinnitus Retraining Therapy. It describes experiments on extracting novel knowledge from the historical dataset of patients treated by Dr. P. Jastreboff so that to better understand factors behind therapy's effectiveness and better personalize treatments for different profiles of patients. The book is a response for a growing demand of an advanced data analytics in the healthcare industry in order to provide better care with the data driven decision-making solutions. The potential economic benefits of applying computerized clinical decision support systems include not only improved efficiency in health care delivery (by reducing costs, improving quality of care and patient safety), but also enhancement in treatment's standardization, objectivity and availability in places of scarce expert's knowledge on this difficult to treat hearing disorder. Furthermore, described approach could be used in assessment of the clinical effectiveness of evidence-based intervention of various proposed treatments for tinnitus.

The recommendation of products, content and services cannot be considered newly born, although its widespread application is still in full swing. While its growing success in numerous sectors, the progress of the Social Web has revolutionized the architecture of participation and relationship in the Web, making it necessary to restate recommendation and reconciling it with "Collaborative Tagging," as the popularization of authoring in the Web, and "Social Networking," as the translation of personal relationships to the Web. Precisely, the convergence of recommendation with the above "Social Web" pillars is what motivates this book, which has collected contributions from well-known experts in the academy and the industry to provide a broader view of the problems that "Social Recommenders" might face with. If recommender systems have proven their key role in facilitating the user access to resources on the Web, when sharing resources has become social, it is natural for recommendation strategies in the Social Web era take into account the users' point of view and the relationships among users to calculate their predictions. This book aims to help readers to discover and understand the interplay among legal issues such as privacy; technical aspects such as interoperability and scalability; and social aspects such as the influence of affinity, trust, reputation and likeness, when the goal is to offer recommendations that are truly useful to both the user and the provider."

This book explains the application of recent advances in computational intelligence - algorithms, design methodologies, and synthesis techniques - to the design of integrated circuits and systems. It highlights new biasing and sizing approaches and optimization techniques and their application to the design of high-performance digital, VLSI, radio-frequency, and mixed-signal circuits and systems. This second of two related volumes addresses digital and network designs and applications, with 12 chapters grouped into parts on digital circuit design, network optimization, and applications. It will be of interest to practitioners and researchers in computer science and electronics engineering engaged with the design of electronic circuits.

This is a textbook for courses commonly called neural networks in departments of computer and information science. This unique neural network book will describe novel architectures and learning mechanisms of model-based neural networks that utilize and intriguing concept of an internal "world" model. This concept combines a prior knowledge of models with adaptive learning and addresses the most perplexing problems in the fields of neural networks: fast learning and robust generalization. The author provides an overview of neural networks and artificial intelligence fields, relating hundreds of seemingly disparate techniques to several basic mathematical concepts. He then analyzes fundamental computational concepts of major neural network paradigms, and relates them to concepts of mind in philosophy, pschology, and linguistics. Relationships of these mathematical concepts to the concepts of philosophy will help students and researchers determine the directions of future research. This book can also be used as a supplementary text in a graduate course on Neural Networks.

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.

This book is dedicated to the memory of Professor Zdzis{\l}aw Pawlak who passed away almost six year ago. He is the founder of the Polish school of Artificial Intelligence and one of the pioneers in Computer Engineering and Computer Science with worldwide influence. He was a truly great scientist, researcher, teacher and a human being. This book prepared in two volumes contains more than 50 chapters. This demonstrates that the scientific approaches discovered by of Professor Zdzis{\l}aw Pawlak, especially the rough set approach as a tool for dealing with imperfect knowledge, are vivid and intensively explored by many researchers in many places throughout the world. The submitted papers prove that interest in rough set research is growing and is possible to see many new excellent results both on theoretical foundations and applications of rough sets alone or in combination with other approaches. We are proud to offer the readers this book.

This book presents recent applications and approaches as well as challenges in digital forensic science. One of the evolving challenges that is covered in the book is the cloud forensic analysis which applies the digital forensic science over the cloud computing paradigm for conducting either live or static investigations within the cloud environment. The book also covers the theme of multimedia forensics and watermarking in the area of information security. That includes highlights on intelligence techniques designed for detecting significant changes in image and video sequences. Moreover, the theme proposes recent robust and computationally efficient digital watermarking techniques. The last part of the book provides several digital forensics related applications, including areas such as evidence acquisition enhancement, evidence evaluation, cryptography, and finally, live investigation through the importance of reconstructing the botnet attack scenario to show the malicious activities and files as evidences to be presented in a court.

This edited book presents the scientific outcomes of the 17th International Conference on Software Engineering, Artificial Intelligence Research, Management and Applications (SERA 2019) held on May 29-31, 2019 in Honolulu, Hawaii. The aim of the 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. This book includes 13 of the conference's most promising papers featuring recent research in software engineering, management and applications

This book not only discusses the important topics in the area of machine learning and combinatorial optimization, it also combines them into one. This was decisive for choosing the material to be included in the book and determining its order of presentation. Decision trees are a popular method of classification as well as of knowledge representation. At the same time, they are easy to implement as the building blocks of an ensemble of classifiers. Admittedly, however, the task of constructing a near-optimal decision tree is a very complex process. The good results typically achieved by the ant colony optimization algorithms when dealing with combinatorial optimization problems suggest the possibility of also using that approach for effectively constructing decision trees. The underlying rationale is that both problem classes can be presented as graphs. This fact leads to option of considering a larger spectrum of solutions than those based on the heuristic. Moreover, ant colony optimization algorithms can be used to advantage when building ensembles of classifiers. This book is a combination of a research monograph and a textbook. It can be used in graduate courses, but is also of interest to researchers, both specialists in machine learning and those applying machine learning methods to cope with problems from any field of R&D.

The amount of data used in the business world has been growing at a rapid and exponential rate. These large volumes of data have led not only to the rise of big data analytics, but to the need for improvements and advancements in the management of it. Recent Advances in Intelligent Technologies and Information Systems brings together current practices and innovations in the management and processing of diverse big data sets through technological integration. Focusing on concepts such as semantic technologies, open source tools, and soft computing, this book is an integral reference source for professionals, researchers, and practitioners interested in the application of technological advancements.

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.

Context-aware ranking is an important task with many applications. E.g. in recommender systems items (products, movies, ...) and for search engines webpages should be ranked. In all these applications, the ranking is not global (i.e. always the same) but depends on the context. Simple examples for context are the user for recommender systems and the query for search engines. More complicated context includes time, last actions, etc. The major problem is that typically the variable domains (e.g. customers, products) are categorical and huge, the observations are very sparse and only positive events are observed. In this book, a generic method for context-aware ranking as well as its application are presented. For modelling a new factorization based on pairwise interactions is proposed and compared to other tensor factorization approaches. For learning, the `Bayesian Context-aware Ranking' framework consisting of an optimization criterion and algorithm is developed. The second main part of the book applies this general theory to the three scenarios of item, tag and sequential-set recommendation. Furthermore extensions of time-variant factors and one-class problems are studied. This book generalizes and builds on work that has received the `WWW 2010 Best Paper Award', the `WSDM 2010 Best Student Paper Award' and the `ECML/PKDD 2009 Best Discovery Challenge Award'.

This monograph comprises work on network-based Intrusion Detection (ID) that is grounded in visualisation and hybrid Artificial Intelligence (AI). It has led to the design of MOVICAB-IDS (MObile VIsualisation Connectionist Agent-Based IDS), a novel Intrusion Detection System (IDS), which is comprehensively described in this book. This novel IDS combines different AI paradigms to visualise network traffic for ID at packet level. It is based on a dynamic Multiagent System (MAS), which integrates an unsupervised neural projection model and the Case-Based Reasoning (CBR) paradigm through the use of deliberative agents that are capable of learning and evolving with the environment. The proposed novel hybrid IDS provides security personnel with a synthetic, intuitive snapshot of network traffic and protocol interactions. This visualisation interface supports the straightforward detection of anomalous situations and their subsequent identification. The performance of MOVICAB-IDS was tested through a novel mutation-based testing method in different real domains which entailed several attacks and anomalous situations.

This book contains the combined proceedings of the 4th International Conference on Ubiquitous Computing Application and Wireless Sensor Network (UCAWSN-15) and the 16th International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT-15). The combined proceedings present peer-reviewed contributions from academic and industrial researchers in fields including ubiquitous and context-aware computing, context-awareness reasoning and representation, location awareness services, and architectures, protocols and algorithms, energy, management and control of wireless sensor networks. The book includes the latest research results, practical developments and applications in parallel/distributed architectures, wireless networks and mobile computing, formal methods and programming languages, network routing and communication algorithms, database applications and data mining, access control and authorization and privacy preserving computation.

Over the last several years there has been a growing interest in developing computational methodologies for modeling and analyzing movements and behaviors of 'crowds' of people. This interest spans several scientific areas that includes Computer Vision, Computer Graphics, and Pedestrian Evacuation Dynamics. Despite the fact that these different scientific fields are trying to model the same physical entity (i.e. a crowd of people), research ideas have evolved independently. As a result each discipline has developed techniques and perspectives that are characteristically their own. The goal of this book is to provide the readers a comprehensive map towards the common goal of better analyzing and synthesizing the pedestrian movement in dense, heterogeneous crowds. The book is organized into different parts that consolidate various aspects of research towards this common goal, namely the modeling, simulation, and visual analysis of crowds. Through this book, readers will see the common ideas and vision as well as the different challenges and techniques, that will stimulate novel approaches to fully grasping "crowds."

Computer Vision and Pattern Recognition (CVPR) together play an important role in the processes involved in environmental informatics due to their pervasive, non-destructive, effective, and efficient natures. As a result, CVPR has made significant contributions to the field of environmental informatics by enabling multi-modal data fusion and feature extraction, supporting fast and reliable object detection and classification, and mining the intrinsic relationship between different aspects of environmental data. Computer Vision and Pattern Recognition in Environmental Informatics describes a number of methods and tools for image interpretation and analysis, which enables observation, modelling, and understanding of environmental targets. In addition to case studies on monitoring and modeling plant, soil, insect, and aquatic animals, this publication includes discussions on innovative new ideas related to environmental monitoring, automatic fish segmentation and recognition, real-time motion tracking systems, sparse coding and decision fusion, and cell phone image-based classification and provides useful references for professionals, researchers, engineers, and students with various backgrounds within a multitude of communities.