%{search_type} search results

• Machine generated contents note: Invited Papers
• A Probabilistic Rating System for Team Competitions with Individual Contributions / Sergey Nikolenko
• Sequential Hierarchical Image Recognition Based on the Pyramid Histograms of Oriented Gradients with Small Samples / Natalya S. Belova
• Discerning Depression Propensity Among Participants of Suicide and Depression-Related Groups of Vk.com / Maxim Kharchenko
• Tutorial
• Normalization of Non-standard Words with Finite State Transducers for Russian Speech Synthesis / Artem Lukanin
• Analysis of Images and Videos
• Transform Coding Method for Hyperspectral Data: Influence of Block Characteristics to Compression Quality / Ruslan Yuzkiv
• Frechet Filters for Color and Hyperspectral Images Filtering / Tat'yana Fedorova
• Fast Global Image Denoising Algorithm on the Basis of Nonstationary Gamma-Normal Statistical Model / Olga Krasotkina.

• Note continued: Theoretical Approach to Developing Efficient Algorithms of Fingerprint Enhancement / Maxim Pasynkov
• Remote Sensing Data Verification Using Model-Oriented Descriptors / Vladislav Myasnikov
• New Bi-, Tri-, and Fourlateral Filters for Color and Hyperspectral Images Filtering / Ivan Artemov
• Frequency Analysis of Gradient Descent Method and Accuracy of Iterative Image Restoration / Vladislav Kuznetsov
• Shape Matching Based on Skeletonization and Alignment of Primitive Chains / Oleg Seredin
• Color Image Restoration with Fuzzy Gaussian Mixture Model Driven Nonlocal Filter / Radhakrishnan Delhibabu
• A Phase Unwrapping Algorithm for Interferometric Phase Images / Andrey Sosnovsky
• Robust Image Watermarking on Triangle Grid of Feature Points / Victor Fedoseev
• Pattern Recognition and Machine Learning
• Traffic Flow Forecasting Algorithm Based on Combination of Adaptive Elementary Predictors / Vladislav Myasnikov.

• Note continued: Analysis of the Adaptive Nature of Collaborative Filtering Techniques in Dynamic Environment / Sheikh Muhammad Sarwar
• A Texture Fuzzy Classifier Based on the Training Set Clustering by a Self-Organizing Neural Network / Dmitry Lykom
• Learning Representations in Directed Networks / Sergey O. Bartunov
• Distorted High-Dimensional Binary Patterns Search by Scalar Neural Network Tree / Magomed Malsagov
• Hybrid Classification Approach to Decision Support for Endoscopy in Gastrointestinal Tract / Olga A. Buntseva
• User Similarity Computation for Collaborative Filtering Using Dynamic Implicit Trust / Mahamudul Hasan
• Similarity Aggregation for Collaborative Filtering / Dmitry I. Ignatov
• Distributed Coordinate Descent for L1-regularized Logistic Regression / Alexander Genkin
• Social Network Analysis
• Building Profiles of Blog Users Based on Comment Graph Analysis: The Habrahabr.ru Case / Rostislav Yavorskiy.

• Note continued: Formation and Evolution Mechanisms in Online Network of Students: The Vkontakte Case / Maria Yudkevich
• Large-Scale Parallel Matching of Social Network Profiles / Sergei Obiedkov
• Identification of Autopoietic Communication Patterns in Social and Economic Networks / Olga M. Zvereva
• Text Mining and Natural Language Processing
• A Heuristic Strategy for Extracting Terms from Scientific Texts / Natalia E. Efremova
• Text Analysis with Enhanced Annotated Suffix Trees: Algorithms and Implementation / Mikhail Dubov
• Morphological Analyzer and Generator for Russian and Ukrainian Languages / Mikhail Korobov
• Semantic Role Labeling for Russian Language Based on Russian FrameBank / Ilya Kuznetsov
• Supervised Approach to Finding Most Frequent Senses in Russian / Ilia Chetviorkin
• FrameBank: A Database of Russian Lexical Constructions / Egor Kashkin
• TagBag: Annotating a Foreign Language Lexical Resource with Pictures ... / Dmitry Ustalov.

• Note continued: BigARTM: Open Source Library for Regularized Multimodal Topic Modeling of Large Collections / Marina Dudarenko
• Industry Talk
• ATM Service Cost Optimization Using Predictive Encashment Strategy / Alois Knoll
• Industry Papers
• Comparison of Deep Learning Libraries on the Problem of Handwritten Digit Classification / Pavel Druzhkov
• Methods of Localization of Some Anthropometric Features of Face / Svetlana Volkova
• Ontological Representation of Networks for IDS in Cyber-Physical Systems / Vasily A. Sartakov
• Determination of the Relative Position of Space Vehicles by Detection and Tracking of Natural Visual Features with the Existing TV-Cameras / Filipp Gundelakh
• Implementation of Agile Concepts in Recommender Systems for Data Processing and Analyses / Nataly Zhukova.

This book constitutes the proceedings of the Fourth International Conference on Analysis of Images, Social Networks and Texts, AIST 2015, held in Yekaterinburg, Russia, in April 2015. The 24 full and 8 short papers were carefully reviewed and selected from 140 submissions. The papers are organized in topical sections on analysis of images and videos; pattern recognition and machine learning; social network analysis; text mining and natural language processing.
(source: Nielsen Book Data)

• Natural language processing
• General topics of data analysis
• Analysis of images and video
• Optimization problems on graphs and network structures
• Analysis of dynamic behavior through event data
• Social network analysis.

This book constitutes the proceedings of the 6th International Conference on Analysis of Images, Social Networks and Texts, AIST 2017, held in Moscow, Russia, in July 2017. The 29 full papers and 8 short papers were carefully reviewed and selected from 127 submissions. The papers are organized in topical sections on natural language processing; general topics of data analysis; analysis of images and video; optimization problems on graphs and network structures; analysis of dynamic behavior through event data; social network analysis.

• Introduction.-
• On the Role of Compliance and Geometry in Mechanical Stability of the Humans and Robots.-
• Teleimpedance Control of a Robotic Arm.-
• Human-like Impedance Control of a Dual-Arm Manipulator.-
• Teleimpedance Control of a Robotic Hand.-
• Teleimpedance Control of a Compliant Knee Exoskeleton.
• (source: Nielsen Book Data)

This book introduces novel thinking and techniques to the control of robotic manipulation. In particular, the concept of teleimpedance control as an alternative method to bilateral force-reflecting teleoperation control for robotic manipulation is introduced. In teleimpedance control, a compound reference command is sent to the slave robot including both the desired motion trajectory and impedance profile, which are then realized by the remote controller. This concept forms a basis for the development of the controllers for a robotic arm, a dual-arm setup, a synergy-driven robotic hand, and a compliant exoskeleton for improved interaction performance.
(source: Nielsen Book Data)

• Preface.- Introduction.- Data Analytics.- Basic Learning Algorithms.- Fuzzy Logic.- Artificial Neural Networks.- Genetic Algorithms and Evolutionary Computing.- Other Metaheuristics and Classification Approaches.- Analytics and Big Data.- Data Analytics Using R.-
• Appendix I: Tools for Data Science.-
• Appendix II: Tools for Computational Intelligence.
• (source: Nielsen Book Data)

This textbook provides readers with the tools, techniques and cases required to excel with modern artificial intelligence methods. These embrace the family of neural networks, fuzzy systems and evolutionary computing in addition to other fields within machine learning, and will help in identifying, visualizing, classifying and analyzing data to support business decisions./p> The authors, discuss advantages and drawbacks of different approaches, and present a sound foundation for the reader to design and implement data analytic solutions for real-world applications in an intelligent manner. Intelligent Techniques for Data Science also provides real-world cases of extracting value from data in various domains such as retail, health, aviation, telecommunication and tourism.
(source: Nielsen Book Data)

Within artificial intelligence, the need to create sophisticated, intelligent behaviour based on common-sense reasoning has long been recognized. Research has demonstrated that formalism for dealing with common sense reasoning require nonmonotonic capabilities where, typically, inferences based on incomplete knowledge need to be revised in light of later information which fills in some of the gaps.
(source: Nielsen Book Data)

• Machine generated contents note: pt. 1 State of the Art
• ch. 1 Introduction
• 1.1. Organization of the book
• 1.2. Utterance corpus
• 1.3. Datasets from the UCI repository
• 1.3.1. Wine dataset (wine)
• 1.3.2. Wisconsin breast cancer dataset (breast)
• 1.3.3. Handwritten digits dataset (Pendig)
• 1.3.4. Pima Indians diabetes (diabetes)
• 1.3.5. Iris dataset (Iris)
• 1.4. Microarray dataset
• 1.5. Simulated datasets
• 1.5.1. Mixtures of Gaussians
• 1.5.2. Spatial datasets with non-homogeneous inter-cluster distance
• ch. 2 State of the Art in Clustering and Semi-Supervised Techniques
• 2.1. Introduction
• 2.2. Unsupervised machine learning (clustering)
• 2.3. A brief history of cluster analysis
• 2.4. Cluster algorithms
• 2.4.1. Hierarchical algorithms
• 2.4.1.1. Agglomerative clustering
• 2.4.1.2. Divisive algorithms
• 2.4.2. Model-based clustering
• 2.4.2.1. The expectation maximization (EM) algorithm
• 2.4.3. Partitional competitive models.

• 2.4.3.1. K-means
• 2.4.3.2. Neural gas
• 2.4.3.3. Partitioning around Medoids (PAM)
• 2.4.3.4. Self-organizing maps
• 2.4.4. Density-based clustering
• 2.4.4.1. Direct density reachability
• 2.4.4.2. Density reachability
• 2.4.4.3. Density connection
• 2.4.4.4. Border points
• 2.4.4.5. Noise points
• 2.4.4.6. DBSCAN algorithm
• 2.4.5. Graph-based clustering
• 2.4.5.1. Pole-based overlapping clustering
• 2.4.6. Affectation stage
• 2.4.6.1. Advantages and drawbacks
• 2.5. Applications of cluster analysis
• 2.5.1. Image segmentation
• 2.5.2. Molecular biology
• 2.5.2.1. Biological considerations
• 2.5.3. Information retrieval and document clustering
• 2.5.3.1. Document pre-processing
• 2.5.3.2. Boolean model representation
• 2.5.3.3. Vector space model
• 2.5.3.4. Term weighting
• 2.5.3.5. Probabilistic models
• 2.5.4. Clustering documents in information retrieval
• 2.5.4.1. Clustering of presented results
• 2.5.4.2. Post-retrieval document browsing (Scatter-Gather)
• 2.6. Evaluation methods.

• 2.7. Internal cluster evaluation
• 2.7.1. Entropy
• 2.7.2. Purity
• 2.7.3. Normalized mutual information
• 2.8. External cluster validation
• 2.8.1. Hartigan
• 2.8.2. Davies Bouldin index
• 2.8.3. Krzanowski and Lai index
• 2.8.4. Silhouette
• 2.8.5. Gap statistic
• 2.9. Semi-supervised learning
• 2.9.1. Self training
• 2.9.2. Co-training
• 2.9.3. Generative models
• 2.10. Summary
• pt. 2 Approaches to Semi-Supervised Classification
• ch. 3 Semi-Supervised Classification Using Prior Word Clustering
• 3.1. Introduction
• 3.2. Dataset
• 3.3. Utterance classification scheme
• 3.3.1. Pre-processing
• 3.3.1.1. Utterance vector representation
• 3.3.2. Utterance classification
• 3.4. Semi-supervised approach based on term clustering
• 3.4.1. Term clustering
• 3.4.2. Semantic term dissimilarity
• 3.4.2.1. Term vector of lexical co-occurrences
• 3.4.2.2. Metric of dissimilarity
• 3.4.3. Term vector truncation
• 3.4.4. Term clustering
• 3.4.5. Feature extraction and utterance feature vector.

• 3.4.6. Evaluation
• 3.5. Disambiguation
• 3.5.1. Evaluation
• 3.6. Summary
• ch. 4 Semi-Supervised Classification Using Pattern Clustering
• 4.1. Introduction
• 4.2. New semi-supervised algorithm using the cluster and label strategy
• 4.2.1. Block diagram
• 4.2.1.1. Dataset
• 4.2.1.2. Clustering
• 4.2.1.3. Optimum cluster labeling
• 4.2.1.4. Classification
• 4.3. Optimum cluster labeling
• 4.3.1. Problem definition
• 4.3.2. The Hungarian algorithm
• 4.3.2.1. Weighted complete bipartite graph
• 4.3.2.2. Matching, perfect matching and maximum weight matching
• 4.3.2.3. Objective of Hungarian method
• 4.3.2.4. Complexity considerations
• 4.3.3. Genetic algorithms
• 4.3.3.1. Reproduction operators
• 4.3.3.2. Forming the next generation
• 4.3.3.3. GAs applied to optimum cluster labeling
• 4.3.3.4. Comparison of methods
• 4.4. Supervised classification block
• 4.4.1. Support vector machines
• 4.4.1.1. The kernel trick for nonlinearly separable classes
• 4.4.1.2. Multi-class classification
• 4.4.2. Example.

• 4.5. Datasets
• 4.5.1. Mixtures of Gaussians
• 4.5.2. Datasets from the UCI repository
• 4.5.2.1. Iris dataset (Iris)
• 4.5.2.2. Wine dataset (wine)
• 4.5.2.3. Wisconsin breast cancer dataset (breast)
• 4.5.2.4. Handwritten digits dataset (Pendig)
• 4.5.2.5. Pima Indians diabetes (diabetes)
• 4.5.3. Utterance dataset
• 4.6. An analysis of the bounds for the cluster and label approaches
• 4.7. Extension through cluster pruning
• 4.7.1. Determination of silhouette thresholds
• 4.7.2. Evaluation of the cluster pruning approach
• 4.8. Simulations and results
• 4.9. Summary
• pt. 3 Contributions to Unsupervised Classification -- Algorithms to Detect the Optimal Number of Clusters
• ch. 5 Detection of the Number of Clusters through Non-Parametric Clustering Algorithms
• 5.1. Introduction
• 5.2. New hierarchical pole-based clustering algorithm
• 5.2.1. Pole-based clustering basis module
• 5.2.2. Hierarchical pole-based clustering
• 5.3. Evaluation
• 5.3.1. Cluster evaluation metrics
• 5.4. Datasets.

• 5.4.1. Results
• 5.4.2. Complexity considerations for large databases
• 5.5. Summary
• ch. 6 Detecting the Number of Clusters through Cluster Validation
• 6.1. Introduction
• 6.2. Cluster validation methods
• 6.2.1. Dunn index
• 6.2.2. Hartigan
• 6.2.3. Davies Bouldin index
• 6.2.4. Krzanowski and Lai index
• 6.2.5. Silhouette
• 6.2.6. Hubert's & gamma;
• 6.2.7. Gap statistic
• 6.3. Combination approach based on quantiles
• 6.4. Datasets
• 6.4.1. Mixtures of Gaussians
• 6.4.2. Cancer DNA-microarray dataset
• 6.4.3. Iris dataset
• 6.5. Results
• 6.5.1. Validation results of the five Gaussian dataset
• 6.5.2. Validation results of the mixture of seven Gaussians
• 6.5.3. Validation results of the NCI60 dataset
• 6.5.4. Validation results of the Iris dataset
• 6.5.5. Discussion
• 6.6. Application of speech utterances
• 6.7. Summary.

"This book provides a detailed and up-to-date overview on classification and data mining methods. The first part is focused on supervised classification algorithms and their applications, including recent research on the combination of classifiers. The second part deals with unsupervised data mining and knowledge discovery, with special attention to text mining. Discovering the underlying structure on a data set has been a key research topic associated to unsupervised techniques with multiple applications and challenges, from web-content mining to the inference of cancer subtypes in genomic microarray data. Among those, the book focuses on a new application for dialog systems which can be thereby made adaptable and portable to different domains. Clustering evaluation metrics and new approaches, such as the ensembles of clustering algorithms, are also described"-- Provided by publisher

• Machine generated contents note: pt. 1 State of the Art
• ch. 1 Introduction
• 1.1. Organization of the book
• 1.2. Utterance corpus
• 1.3. Datasets from the UCI repository
• 1.3.1. Wine dataset (wine)
• 1.3.2. Wisconsin breast cancer dataset (breast)
• 1.3.3. Handwritten digits dataset (Pendig)
• 1.3.4. Pima Indians diabetes (diabetes)
• 1.3.5. Iris dataset (Iris)
• 1.4. Microarray dataset
• 1.5. Simulated datasets
• 1.5.1. Mixtures of Gaussians
• 1.5.2. Spatial datasets with non-homogeneous inter-cluster distance
• ch. 2 State of the Art in Clustering and Semi-Supervised Techniques
• 2.1. Introduction
• 2.2. Unsupervised machine learning (clustering)
• 2.3. A brief history of cluster analysis
• 2.4. Cluster algorithms
• 2.4.1. Hierarchical algorithms
• 2.4.1.1. Agglomerative clustering
• 2.4.1.2. Divisive algorithms
• 2.4.2. Model-based clustering
• 2.4.2.1. The expectation maximization (EM) algorithm
• 2.4.3. Partitional competitive models.

• 2.4.3.1. K-means
• 2.4.3.2. Neural gas
• 2.4.3.3. Partitioning around Medoids (PAM)
• 2.4.3.4. Self-organizing maps
• 2.4.4. Density-based clustering
• 2.4.4.1. Direct density reachability
• 2.4.4.2. Density reachability
• 2.4.4.3. Density connection
• 2.4.4.4. Border points
• 2.4.4.5. Noise points
• 2.4.4.6. DBSCAN algorithm
• 2.4.5. Graph-based clustering
• 2.4.5.1. Pole-based overlapping clustering
• 2.4.6. Affectation stage
• 2.4.6.1. Advantages and drawbacks
• 2.5. Applications of cluster analysis
• 2.5.1. Image segmentation
• 2.5.2. Molecular biology
• 2.5.2.1. Biological considerations
• 2.5.3. Information retrieval and document clustering
• 2.5.3.1. Document pre-processing
• 2.5.3.2. Boolean model representation
• 2.5.3.3. Vector space model
• 2.5.3.4. Term weighting
• 2.5.3.5. Probabilistic models
• 2.5.4. Clustering documents in information retrieval
• 2.5.4.1. Clustering of presented results
• 2.5.4.2. Post-retrieval document browsing (Scatter-Gather)
• 2.6. Evaluation methods.

• 2.7. Internal cluster evaluation
• 2.7.1. Entropy
• 2.7.2. Purity
• 2.7.3. Normalized mutual information
• 2.8. External cluster validation
• 2.8.1. Hartigan
• 2.8.2. Davies Bouldin index
• 2.8.3. Krzanowski and Lai index
• 2.8.4. Silhouette
• 2.8.5. Gap statistic
• 2.9. Semi-supervised learning
• 2.9.1. Self training
• 2.9.2. Co-training
• 2.9.3. Generative models
• 2.10. Summary
• pt. 2 Approaches to Semi-Supervised Classification
• ch. 3 Semi-Supervised Classification Using Prior Word Clustering
• 3.1. Introduction
• 3.2. Dataset
• 3.3. Utterance classification scheme
• 3.3.1. Pre-processing
• 3.3.1.1. Utterance vector representation
• 3.3.2. Utterance classification
• 3.4. Semi-supervised approach based on term clustering
• 3.4.1. Term clustering
• 3.4.2. Semantic term dissimilarity
• 3.4.2.1. Term vector of lexical co-occurrences
• 3.4.2.2. Metric of dissimilarity
• 3.4.3. Term vector truncation
• 3.4.4. Term clustering
• 3.4.5. Feature extraction and utterance feature vector.

• 3.4.6. Evaluation
• 3.5. Disambiguation
• 3.5.1. Evaluation
• 3.6. Summary
• ch. 4 Semi-Supervised Classification Using Pattern Clustering
• 4.1. Introduction
• 4.2. New semi-supervised algorithm using the cluster and label strategy
• 4.2.1. Block diagram
• 4.2.1.1. Dataset
• 4.2.1.2. Clustering
• 4.2.1.3. Optimum cluster labeling
• 4.2.1.4. Classification
• 4.3. Optimum cluster labeling
• 4.3.1. Problem definition
• 4.3.2. The Hungarian algorithm
• 4.3.2.1. Weighted complete bipartite graph
• 4.3.2.2. Matching, perfect matching and maximum weight matching
• 4.3.2.3. Objective of Hungarian method
• 4.3.2.4. Complexity considerations
• 4.3.3. Genetic algorithms
• 4.3.3.1. Reproduction operators
• 4.3.3.2. Forming the next generation
• 4.3.3.3. GAs applied to optimum cluster labeling
• 4.3.3.4. Comparison of methods
• 4.4. Supervised classification block
• 4.4.1. Support vector machines
• 4.4.1.1. The kernel trick for nonlinearly separable classes
• 4.4.1.2. Multi-class classification
• 4.4.2. Example.

• 4.5. Datasets
• 4.5.1. Mixtures of Gaussians
• 4.5.2. Datasets from the UCI repository
• 4.5.2.1. Iris dataset (Iris)
• 4.5.2.2. Wine dataset (wine)
• 4.5.2.3. Wisconsin breast cancer dataset (breast)
• 4.5.2.4. Handwritten digits dataset (Pendig)
• 4.5.2.5. Pima Indians diabetes (diabetes)
• 4.5.3. Utterance dataset
• 4.6. An analysis of the bounds for the cluster and label approaches
• 4.7. Extension through cluster pruning
• 4.7.1. Determination of silhouette thresholds
• 4.7.2. Evaluation of the cluster pruning approach
• 4.8. Simulations and results
• 4.9. Summary
• pt. 3 Contributions to Unsupervised Classification -- Algorithms to Detect the Optimal Number of Clusters
• ch. 5 Detection of the Number of Clusters through Non-Parametric Clustering Algorithms
• 5.1. Introduction
• 5.2. New hierarchical pole-based clustering algorithm
• 5.2.1. Pole-based clustering basis module
• 5.2.2. Hierarchical pole-based clustering
• 5.3. Evaluation
• 5.3.1. Cluster evaluation metrics
• 5.4. Datasets.

• 5.4.1. Results
• 5.4.2. Complexity considerations for large databases
• 5.5. Summary
• ch. 6 Detecting the Number of Clusters through Cluster Validation
• 6.1. Introduction
• 6.2. Cluster validation methods
• 6.2.1. Dunn index
• 6.2.2. Hartigan
• 6.2.3. Davies Bouldin index
• 6.2.4. Krzanowski and Lai index
• 6.2.5. Silhouette
• 6.2.6. Hubert's & gamma;
• 6.2.7. Gap statistic
• 6.3. Combination approach based on quantiles
• 6.4. Datasets
• 6.4.1. Mixtures of Gaussians
• 6.4.2. Cancer DNA-microarray dataset
• 6.4.3. Iris dataset
• 6.5. Results
• 6.5.1. Validation results of the five Gaussian dataset
• 6.5.2. Validation results of the mixture of seven Gaussians
• 6.5.3. Validation results of the NCI60 dataset
• 6.5.4. Validation results of the Iris dataset
• 6.5.5. Discussion
• 6.6. Application of speech utterances
• 6.7. Summary.

"This book provides a detailed and up-to-date overview on classification and data mining methods. The first part is focused on supervised classification algorithms and their applications, including recent research on the combination of classifiers. The second part deals with unsupervised data mining and knowledge discovery, with special attention to text mining. Discovering the underlying structure on a data set has been a key research topic associated to unsupervised techniques with multiple applications and challenges, from web-content mining to the inference of cancer subtypes in genomic microarray data. Among those, the book focuses on a new application for dialog systems which can be thereby made adaptable and portable to different domains. Clustering evaluation metrics and new approaches, such as the ensembles of clustering algorithms, are also described"-- Provided by publisher.

• Phylogenetics.- Sequence Rearrangement and Analysis.- Systems Biology and Other Biological Processes.
• (source: Nielsen Book Data)

This book constitutes the proceedings of the 5th InternationalConference on Algorithms for Computational Biology, AlCoB 2018, held in Hong Kong, China, in June 2018. The 11 full papers presented together with 1 invited paper were carefully reviewed and selected from 20 submissions. They are organized in the following topical sections: Phylogenetics, Sequence Rearrangement and Analysis, Systems Biology and Other Biological Processes. .
(source: Nielsen Book Data)

• AUTHORS' NOTES AND ACKNOWLEDGEMENTS; INTRODUCTION; 1.1. Objectives of this Book; 1.2. The Seeing Eye and the Knowing Eye
• 1 IMAGE AND COMPUTER; 1.1. A Short History; 1.2. The Computer's Eye; 1.3. A Beetle and an Ant-Hill; 1.4. Features and Models; 2 HOW HUMANS SEE THE WORLD; 2.1. The Eye and the Brain; 2.2. The Level of Preattention; 2.3. Right and Left Vision; 2.4. Images and Words; 3 CONVERSATIONS WITH A COMPUTER; 3.1. From a Point to a Region; 3.2. From a Region to an Object; 3.3. From an Object to a Situation; 4 AN APOLOGIA FOR VISION; 4.1. The Evolution of Vision.

• 4
• .2. Vision and Thinking4
• .3. Recollection of the Future; 4
• .4. Cognition through Vision; 5 CREATING A NEW WORLD; 5
• .1. From Elements to the System; 5
• .2. Back to Nature; 5
• .3. Who Do We Think They Are?; CONCLUSIONS; PLATES; REFERENCES; ILLUSTRATIONS; INDEX.

This book considers computer vision to be an integral part of the artificial intelligence system. The core of the book is an analysis of possible approaches to the creation of artificial vision systems, which simulate human visual perception. Much attention is paid to the latest achievements in visual psychology and physiology, the description of the functional and structural organization of the human perception mechanism, the peculiarities of artistic perception and the expression of reality. Computer vision models based on these data are investigated. They include the processes of external data analysis, internal environmental model synthesis, and the generating of behavioristic responses based on external and internal models comparison. Computer vision system evolution resulting from environmental effects is also considered. A unique feature of this book is the authors' use of black and white, and colour prints of traditional and contemporary Russian art to illustrate their principal theses. In doing so, they introduce the reader to a particularly Russian view of the world.
(source: Nielsen Book Data)

• Tutorials
• Algorithmic Aspects of Large-Scale Data Stores
• Software Tools and Distributed Architectures for Cloud-based Data Management.

This book constitutes the thoroughly refereed post-conference proceedings of the First International Workshop on Algorithmic Aspects of Cloud Computing, ALGOCLOUD 2015, held in Patras, Greece, in September 2015 in conjunction with ALGO 2015. The 13 revised full papers presented together with 2 tutorial papers were carefully reviewed and selected from 37 initial submissions. They cover a wide range of topics in two main tracks: algorithmic aspects of large-scale data stores, and software tools and distributed architectures for cloud-based data management.

• Plane and Planarity Thresholds for Random Geometric Graphs.- Connectivity of a dense mesh of randomly oriented directional antennas under a realistic fading model.- Maintaining Intruder Detection Capability in a Rectangular Domain with Sensors.- The Weakest Oracle for Symmetric Consensus in Population Protocols.- Exact and Approximation Algorithms for Data Mule Scheduling in a Sensor Network.- Limitations of Current Wireless Scheduling Algorithms.- Deterministic rendezvous with detection using beeps.- Minimizing total sensor movement for barrier coverage by non-uniform sensors on a line.- A comprehensive and lightweight security architecture to secure the IoT throughout the lifecycle of a device based on HIMMO.- Maximizing Throughput in Energy-Harvesting Sensor Nodes.- On verifying and maintaining connectivity of interval temporal networks.- Beachcombing on Strips and Islands.- Radio Aggregation Scheduling.- Gathering of Robots on Meeting-Points.- Mutual Visibility with an Optimal Number of Colors.- Mobile Agents Rendezvous in spite of a Malicious Agent.
• (source: Nielsen Book Data)

This book constitutes revised selected papers from the 11th International Symposium on Algorithms and Experiments for Wireless Sensor Networks, ALGOSENSORS 2015, held in Patras, Greece, in September 2015. The 16 full papers presented in this volume were carefully reviewed and selected from 30 submissions. The deal with algorithms analysis and problem complexity; computer communication networks; computation by abstract devices; and mathematics of computing.
(source: Nielsen Book Data)

• Multi-Message Broadcast in Dynamic Radio Networks.- Global Synchronization and Consensus Using Beeps in a Fault-Prone MAC 16.- Vertex Coloring with Communication and Local Memory Constraints in Synchronous Broadcast Networks.- A New Kind of Selectors, and Their Applications to Conflict Resolution in Wireless Multi-channels Networks.- The Impact of the Gabriel Sub-graph of the Visibility Graph on the Gathering of Mobile Autonomous Robots.- Search-and-Fetch with One Robot on a Disk.- A 2-Approximation Algorithm for Barrier Coverage by Weighted Non-uniform Sensors on a Line.- Flexible Cell Selection in Cellular Networks.- The Euclidean k-Supplier Problem in IR2.
• (source: Nielsen Book Data)

This book constitutes revised selected papers from the 12th International Symposium on Algorithms and Experiments for Wireless Sensor Networks, ALGOSENSORS 2016, held in Aarhus, Denmark, in August 2016. The 9 full papers presented in this volume were carefully reviewed and selected from 19 submissions. This year papers were solicited into three tracks: Distributed and Mobile, Experiments and Applications, and Wireless and Geometry.
(source: Nielsen Book Data)

• Learning and evolution
• Human interaction
• Robotic simulation.

This book constitutes the refereed proceedings of the First International Symposium on Artificial Life and Intelligent Agents, ALIA 2014, held in Bangor, UK, in November 2014. The 10 revised full papers were carefully reviewed and selected from 20 submissions. The papers are organized in topical sections on learning and evolution; human interaction; robotic simulation.

The goal of machine learning is to program computers to use example data or past experience to solve a given problem. Many successful applications of machine learning exist already, including systems that analyze past sales data to predict customer behavior, optimize robot behavior so that a task can be completed using minimum resources, and extract knowledge from bioinformatics data. The second edition of Introduction to Machine Learning is a comprehensive textbook on the subject, covering a broad array of topics not usually included in introductory machine learning texts. In order to present a unified treatment of machine learning problems and solutions, it discusses many methods from different fields, including statistics, pattern recognition, neural networks, artificial intelligence, signal processing, control, and data mining. All learning algorithms are explained so that the student can easily move from the equations in the book to a computer program. The text covers such topics as supervised learning, Bayesian decision theory, parametric methods, multivariate methods, multilayer perceptrons, local models, hidden Markov models, assessing and comparing classification algorithms, and reinforcement learning. New to the second edition are chapters on kernel machines, graphical models, and Bayesian estimation; expanded coverage of statistical tests in a chapter on design and analysis of machine learning experiments; case studies available on the Web (with downloadable results for instructors); and many additional exercises. All chapters have been revised and updated. Introduction to Machine Learning can be used by advanced undergraduates and graduate students who have completed courses in computer programming, probability, calculus, and linear algebra. It will also be of interest to engineers in the field who are concerned with the application of machine learning methods.
(source: Nielsen Book Data)

The goal of machine learning is to program computers to use example data or past experience to solve a given problem. Many successful applications of machine learning exist already, including systems that analyze past sales data to predict customer behavior, optimize robot behavior so that a task can be completed using minimum resources, and extract knowledge from bioinformatics data. The second edition of Introduction to Machine Learning is a comprehensive textbook on the subject, covering a broad array of topics not usually included in introductory machine learning texts. In order to present a unified treatment of machine learning problems and solutions, it discusses many methods from different fields, including statistics, pattern recognition, neural networks, artificial intelligence, signal processing, control, and data mining. All learning algorithms are explained so that the student can easily move from the equations in the book to a computer program. The text covers such topics as supervised learning, Bayesian decision theory, parametric methods, multivariate methods, multilayer perceptrons, local models, hidden Markov models, assessing and comparing classification algorithms, and reinforcement learning. New to the second edition are chapters on kernel machines, graphical models, and Bayesian estimation; expanded coverage of statistical tests in a chapter on design and analysis of machine learning experiments; case studies available on the Web (with downloadable results for instructors); and many additional exercises. All chapters have been revised and updated. Introduction to Machine Learning can be used by advanced undergraduates and graduate students who have completed courses in computer programming, probability, calculus, and linear algebra. It will also be of interest to engineers in the field who are concerned with the application of machine learning methods.
(source: Nielsen Book Data)

• Error bounds, sample compression schemes
• Statistical learning, theory, evolvability
• Exact and interactive learning
• Complexity of teaching models
• Inductive inference
• Online learning
• Bandits and reinforcement learning
• Clustering.

This book constitutes the refereed proceedings of the 27th International Conference on Algorithmic Learning Theory, ALT 2016, held in Bari, Italy, in October 2016, co-located with the 19th International Conference on Discovery Science, DS 2016. The 24 regular papers presented in this volume were carefully reviewed and selected from 45 submissions. In addition the book contains 5 abstracts of invited talks. The papers are organized in topical sections named: error bounds, sample compression schemes; statistical learning, theory, evolvability; exact and interactive learning; complexity of teaching models; inductive inference; online learning; bandits and reinforcement learning; and clustering.

• Introduction to Swarm Search.- Cooperative "Swarm Cleaning" of Stationary Domains.- Swarm Search of Expanding Regions in Grids: Lower Bounds.- Swarm Search of Expanding Regions in Grids: Upper Bounds.- The Search Complexity of Collaborative Swarms Expanding Z2 Grid Regions.
• (source: Nielsen Book Data)

This book offers a comprehensive analysis of the theory and tools needed for the development of an efficient and robust infrastructure for the design of collaborative patrolling unmanned aerial vehicle (UAV) swarms, focusing on its applications for tactical intelligence drones. It discusses frameworks for robustly and near-optimally analyzing flocks of semi-autonomous vehicles designed to efficiently perform the ongoing dynamic patrolling and scanning of pre-defined "search regions". It discusses the theoretical limitations of such systems, as well as the trade-offs between the systems' various economic and operational parameters. Current UAV systems rely mainly on human operators for the design and adaptation of drones' flying routes. However, recent technological advances have introduced new systems, comprised of a small number of self-organizing vehicles, manually guided at the swarm level by a human operator. With the growing complexity of such man-supervised architectures, it is becoming increasingly harder to guarantee a pre-defined level of performance. The use of large scale swarms of UAVs as a combat and reconnaissance platform therefore necessitates the development of an efficient optimization mechanism of their utilization, specifically in the design and maintenance of their patrolling routes. The book is intended for researchers and engineers in the fields of swarms systems and autonomous drones. .
(source: Nielsen Book Data)

• Intro
• Preface
• Organization
• Contents
• Mammographic Mass Segmentation Using Fuzzy C-means and Decision Trees
• 1 Introduction
• 2 Segmentation of Masses in Mammograms Using Fuzzy C-means and Decision Trees
• 2.1 Fuzzy C-means Based on Gray Levels Histogram
• 2.2 Reduction of False Positive ROIs
• 2.3 Feature Extraction
• 2.4 Binary Decision Tree
• 3 Experimentation
• 3.1 Results and Discussion
• 4 Conclusions
• References
• Refining the Pose: Training and Use of Deep Recurrent Autoencoders for Improving Human Pose Estimation
• 1 Introduction

• 2 Deep Architecture for 3D Human Pose Refinement
• 2.1 Denoising Recurrent Autoencoder
• 2.2 Convolutional Network for Pose Prediction
• 2.3 Pose Refinement Training
• 2.4 Cost Function
• 3 Experiments
• 3.1 Evaluation on HumanEva-I
• 3.2 Evaluation on Human 3.6 Million
• 3.3 Ablation Experiments
• 3.4 Conclusions
• References
• How Can Deep Neural Networks Be Generated Efficiently for Devices with Limited Resources?
• 1 Introduction
• 2 Background
• 3 Parameter Pruning
• 4 Quantization
• 5 Low-Rank Factorization
• 6 Compact Network Design
• 7 Neural Model Deployment

• 7.1 Compact Network Design
• 7.2 Training and Pruning
• 7.3 Quantize Model
• 7.4 Inference Optimization
• 8 Conclusion
• References
• Controlling a Smartphone with Brain-Computer Interfaces: A Preliminary Study
• 1 Introduction
• 2 Subjects and Methods
• 2.1 Acquisition
• 2.2 Processing
• 2.3 Application
• 2.4 Evaluation Procedure
• 3 Results
• 4 Discussion
• 5 Conclusion
• References
• Capturing Industrial Machinery into Virtual Reality
• 1 Introduction
• 2 Related Work
• 3 System Design
• 3.1 Initialisation
• 3.2 Capturing Images
• 3.3 Calibration
• 3.4 Visualisation

• 4 Results
• 5 Conclusion
• References
• Leishmaniasis Parasite Segmentation and Classification Using Deep Learning
• 1 Introduction
• 2 Data
• 3 Method
• 4 Results
• 5 Conclusions
• References
• Robust Pedestrian Detection for Semi-automatic Construction of a Crowded Person Re-Identification Dataset
• 1 Introduction
• 2 The JNU Dataset
• 3 Automatic Pedestrian Detection
• 4 Automatic Data Association
• 5 Evaluation
• 6 Conclusion
• References
• Shape and Appearance Based Sequenced Convnets to Detect Real-Time Face Attributes on Mobile Devices
• 1 Introduction
• 2 Related Work

• 3 Datasets and Data Preparation
• 3.1 FER-2013 and FER+ Datasets
• 3.2 Data Preprocessing
• 4 Proposed CNN Architecture
• 4.1 Sequenced CNN Models
• 4.2 Face Heatmap Image Construction
• 4.3 CNN Models
• 4.4 Learning with a Shape Heatmap Image
• 5 Results and Applications
• 5.1 Effects of Data Preparation and Alignment
• 5.2 Combining Face Shape and Appearance with VGG
• 5.3 Combining Face Shape and Appearance with Mobilenet
• 5.4 Implementation
• 6 Conclusions
• References
• Image Colorization Using Generative Adversarial Networks
• 1 Introduction

This book constitutes the refereed proceedings of the 10th International Conference on Articulated Motion and Deformable Objects, AMDO 2018, held in Palma de Mallorca, Spain, in July 2018. The 12 papers presented were carefully reviewed and selected from 26 submissions. The papers address the following topics: advanced computer graphics and immersive videogames; human modeling and animation; human motion analysis and tracking; 3D human reconstruction and recognition; multimodal user interaction and applications; ubiquitous and social computing; design tools; input technology; programming user interfaces; 3D medical deformable models and visualization; deep learning methods for computer vision and graphics; and multibiometric.
(source: Nielsen Book Data)

• Intro; Preface; Organization; Contents; An Ecological View of Smart Home Technologies; Abstract; 1 Introduction; 2 Domotics as Home Automation; 3 The Ecology of the Smart Home; 3.1 A Smart Home Is not a HaaS; 3.2 Traditional Home Services; 3.3 The Smart Home as an Inside-Out Autonomous Robot; 4 Intelligent Services for the Smart Home; 4.1 Tool Services; 4.2 Housekeeping Services; 4.3 Advisor Services; 4.4 Media Services; 4.5 Categories of Service Are Based on Interaction; 5 Qualities and Show Stoppers for Smart Home Services; 5.1 Controllability; 5.2 Reliability and Maintainability

• 5.3 Usability5.4 Durability; 5.5 Security, Privacy and Trustworthiness; 6 Concluding Remarks; References; Modeling and Assessing Young Children Abilities and Development in Ambient Intelligence; Abstract; 1 Introduction; 2 Related Work; 2.1 Modelling User Abilities and Performance in Ambient Intelligence; 2.2 Software Assessment Tools; 3 Background; 3.1 Play and Its Contribution to Child's Development; 3.2 Knowledge Models and Assessment Tools; 4 The BEAN Framework; 4.1 Bean Model: A Knowledge-Based Data Model; 4.2 Reasoning Mechanism; 4.3 Reporting Facilities; 5 A Case Study: The Tower Game

• 6 Conclusions and Future WorkAcknowledgments; References; Augmented Home Inventories; Abstract; 1 Introduction; 2 Home Inventories: A Brief History; 3 New Household Items; 4 Emerging Home Entities and Societies; 5 Challenging the Home Inventory; 6 Conclusions; References; Ambient Intelligence from Senior Citizens' Perspectives: Understanding Privacy Concerns, Technology Acceptance, and Expectations; 1 Introduction; 2 Related Work; 3 Methods; 3.1 Sample; 3.2 Questionnaire Design; 4 Results; 4.1 Importance of Ambient Intelligence Features; 4.2 Acceptable System Limitations

• 4.3 Fears Associated with the Use of Ambient Intelligence Technologies4.4 Detailed Feature Comparison; 4.5 Comparison of Four Ambient Intelligence System Types; 5 Discussion and Summary; 5.1 Limitations; 5.2 Main Findings; 6 Summary; References; Person Identification by Analyzing Door Accelerations in Time and Frequency Domain; Abstract; 1 Introduction; 2 Background; 2.1 Physics and Acceleration Signal Description; 2.2 Related Work; 3 Time Domain Identification; 3.1 Feature-Based Identification; 3.2 Signal-Based Identification; 4 Frequency Domain Identification

• 4.1 Feature-Based Identification4.2 Signal-Based Identification; 5 Experiments; 5.1 Time Domain; 5.2 Frequency Domain; 5.3 Combining the Time and Frequency Domain Methods; 6 Conclusions; Acknowledgements; References; Design Factors for Flexible Capacitive Sensors in Ambient Intelligence; 1 Introduction; 2 Related Work; 3 Evaluating Flexible Capacitive Sensors; 4 Electrode Material Evaluation; 4.1 Measurement Setup; 4.2 Electrode Materials; 5 Results; 5.1 Self Capacitance Measurements; 5.2 Mutual Capacitance Measurements; 6 Design Factors; 6.1 On Materials; 6.2 On Size; 6.3 On Modes

This book constitutes the refereed proceedings of the 12th European Conference on Ambient Intelligence, AmI 2015, held in Athens, Greece, in November 2015. The 21 revised full papers presented together with 5 short papers were carefully reviewed and selected from 48 submissions. Over the past 20 years, the vision of Ambient Intelligence has gradually materialized into a plethora of technologies and devices, which are being introduced into almost every aspect of everyday life, thus affecting our abilities, activities, behavior and in the end, shaping a new way of thinking.
(source: Nielsen Book Data)

• Technologies for implementing AmIHealth environments.- Frameworks related with AmIHealth environments.- Applied algorithms in e-Health systems.- Interactions within the AmIHealth environments.- Applications and case studies of AmIHealth environments.- Metrics for Health environments.
• (source: Nielsen Book Data)

This book constitutes the refereed conference proceedings of the First International Conference on Ambient Intelligence for Health, AmIHEALTH 2015, held in Puerto Varas, Chile, in December 2015. The 20 revised full papers and 9 short papers were reviewed and selected from 32 submissions and cover topics on technologies for implementing AmIHealth environments; frameworks related with AmIHealth environments; applied algorithms in e-Health systems; interactions within the AmIHealth environments; applications and case studies of AmIHealth environments; and metrics for health environments.
(source: Nielsen Book Data)