Note: Intro -- Title Page -- Copyright -- Table of Contents -- Preface -- Acknowledgments -- Abbreviations -- Chapter 1: Introduction: The Origin, Current Status, and Future of Microfluidics -- 1.1 Introduction -- 1.2 Development of Microfluidic Components -- 1.3 Development of Complex Microfluidic Systems -- 1.4 Development of Application-Oriented Microfluidic Systems -- 1.5 Perspective -- References -- Chapter 2: Fundamental Concepts and Physics in Microfluidics -- 2.1 Introduction -- 2.2 Basic Concepts of Liquids and Gases -- 2.3 Mass and Heat Transfer Principles for Fluid -- 2.4 Surfaces and Interfaces in Microfluidics -- 2.5 Development of Driving Forces for Microfluidic Processes -- 2.6 Construction Materials Considerations -- Acknowledgments -- References -- Chapter 3: Microfluidics Devices: Fabrication and Surface Modification -- 3.1 Introduction -- 3.2 Microfluidics Device Fabrication -- 3.3 Surface Modification in Microfluidics Fabrication -- 3.4 Conclusions and Outlook -- References -- Chapter 4: Numerical Simulation in Microfluidics and the Introduction of the Related Software -- 4.1 Introduction -- 4.2 Numerical Simulation Models in Microfluidics -- 4.3 Numerical Simulation Software in Microfluidics -- 4.4 Conclusions -- Acknowledgments -- References -- Chapter 5: Digital Microfluidic Systems: Fundamentals, Configurations, Techniques, and Applications -- 5.1 Introduction to Microfluidic Systems -- 5.2 Types of Digital Microfluidic Systems -- 5.3 DMF Chip Fabrication Techniques -- 5.4 Different Electrode Configurations in DMF Systems -- 5.5 Digital Microfluidic Working Principle -- 5.6 Electrical Signals Used and Their Effect on the DMF Operations -- 5.7 Droplet Metering and Dispensing Techniques in DMF Systems -- 5.8 The Effect of the Gap Height between the Top Plate and the Bottom Plate in DMF Systems. , 5.9 Modeling and Controlling Droplet Operations in DMF Systems -- 5.10 Prospects of Portability in DMF Platforms -- 5.11 Examples for Chemical and Biological Applications Performed on the DMF Platform -- References -- Chapter 6: Microfluidics for Chemical Analysis -- 6.1 Introduction -- 6.2 Microfluidics for Electrochemical Analysis -- 6.3 Advanced Microfluidic Methodologies for Electrochemical Analysis -- 6.4 Numerical Modeling of Electrochemical Microfluidic Technologies -- References -- Chapter 7: Microfluidic Devices for the Isolation of Circulating Tumor Cells (CTCs) -- 7.1 Introduction -- 7.2 Affinity-Based Enrichment of CTCs -- 7.3 Nonaffinity-Based Enrichment of CTCs -- 7.4 Conclusions and Outlook -- References -- Chapter 8: Microfluidics for Disease Diagnosis -- 8.1 Introduction -- 8.2 Protein Analysis -- 8.3 Nucleic Acid Analysis -- 8.4 Cell Detection -- 8.5 Other Species -- 8.6 Summary and Overlook -- References -- Chapter 9: Gene Expression Analysis on Microfluidic Device -- 9.1 Introduction -- 9.2 Analysis Cell Population Gene Expression on Chip -- 9.3 Single-Cell Gene Expression Profiling -- 9.4 Conclusion -- Acknowledgment -- References -- Chapter 10: Computational Microfluidics Applied to Drug Delivery in Pulmonary and Arterial Systems -- 10.1 Introduction -- 10.2 Modeling Methods -- 10.3 Pulmonary Drug Delivery -- 10.4 Intravascular Drug Delivery -- 10.5 Conclusions and Future Work -- References -- Chapter 11: Microfluidic Synthesis of Organics -- 11.1 Introduction -- 11.2 Microfluidic Nebulator for Organic Synthesis -- 11.3 Coiled Tubing Microreactor for Organic Synthesis -- 11.4 Chip-Based Microfluidic Reactor for Organic Synthesis -- 11.5 Packed-Bed Microreactors for Organic Synthesis -- 11.6 Ring-Shaped (Tube-in-Tube) Microfluidic Reactor for Organic Synthesis -- 11.7 Summary and Outlook -- Acknowledgments -- References. , Chapter 12: Microfluidic Approaches for Designing Multifunctional Polymeric Microparticles from Simple Emulsions to Complex Particles -- 12.1 Introduction -- 12.2 Flow Regimes in Microfluidics: Dripping, Jetting, and Coflowing -- 12.3 Design of Multifunctional Microparticles from Emulsions -- 12.4 Conclusions and Outlooks -- References -- Chapter 13: Synthesis of Magnetic Nanomaterials -- 13.1 Introduction -- 13.2 Synthesis of Magnetic Nanomaterials Using Microreactors -- 13.3 Conclusion -- References -- Chapter 14: Microfluidic Synthesis of Metallic Nanomaterials -- 14.1 Introduction -- 14.2 Microfluidic Processes for Metallic Nanomaterial Synthesis -- 14.3 Crystal Structure-Controlled Synthesis of Metallic Nanocrystals -- 14.4 Size- and Shape-Controlled Synthesis of Metallic Nanocrystals -- 14.5 Multi-Hierarchical Microstructure- and Composition-Controlled Synthesis of Metallic Nanocrystals -- 14.6 Summary and Outlook -- Acknowledgments -- References -- Chapter 15: Microfluidic Synthesis of Composites -- 15.1 Introduction -- 15.2 Microfluidic Synthesis Systems and the Design Principles -- 15.3 The Formation Mechanism of Composites -- 15.4 Microfluidic Synthesis of Composites -- 15.5 Summary and Perspectives -- Acknowledgments -- References -- Chapter 16: Microfluidic Synthesis of MOFs and MOF-Based Membranes -- 16.1 Microfluidic Synthesis of Metal-Organic Frameworks (MOFs) -- 16.2 Microfluidic Synthesis of MOF-Based Membranes -- 16.3 Conclusions and Outlook -- Acknowledgments -- References -- Chapter 17: Perspective for Microfluidics -- 17.1 Design, Fabrication, and Assemble of Microfluidic Systems -- 17.2 Precise Control of Critical Device Features for Chemical Analysis and Biomedical Engineering -- 17.3 Control of Critical Kinetic Parameters for Chemical and Materials Synthesis. , 17.4 Development of Fundamental Theory at Micro-/Nanoscale and Fluid Mechanism at Nanoliter-Picoliter for Microfluidic Systems -- Acknowledgments -- References -- Index -- End User License Agreement.

Note: Intro -- Preface -- Organizing Committee -- General Chairs -- Program Chairs -- Organizing Chairs -- Finance Chair -- Publication Chairs -- Publicity Chairs -- Program Committee -- Reviewers -- Contents -- Knowledge Discovery Foundations: Association Rules -- Efficient Algorithm for Maximal Biclique Enumeration on Bipartite Graphs -- 1 Introduction -- 2 Preliminaries -- 2.1 Maximal Bicliques -- 2.2 LCM Algorithm -- 3 Our Algorithm -- 3.1 New Implementation Pruning Technique Based on Stack -- 3.2 Replace the Vertices Label -- 3.3 Manage Candidate Child Nodes -- 3.4 Hybrid Algorithm -- 4 Experiments -- 5 Conclusions -- References -- An Efficient Algorithm to Mine High Average-Utility Sequential Patterns -- 1 Introduction -- 2 Related Work -- 3 Preliminaries -- 4 HAUSPM Algorithm -- 4.1 The Lexicographic Q-Sequences Tree -- 4.2 Concatenations -- 4.3 Pruning Strategies -- 4.4 The HAUSPM Algorithm -- 5 Experiments and Evaluation -- 5.1 Datasets -- 5.2 Performance Test -- 6 Conclusion -- References -- HPM-FSI: A High-Performance Algorithm for Mining Frequent Significance Itemsets -- Abstract -- 1 Introduction -- 2 Background -- 2.1 Mining Frequent Significance Itemsets -- 2.2 Data Structure for Transaction Database -- 3 The Proposed Algorithms -- 3.1 Generating Array Contain Co-occurrence Items of Kernel Item -- 3.2 Generating List NLOOC-Tree -- 3.3 Algorithm Generating All Frequent Significance Itemsets -- 3.4 The Algorithm Diagram HPM-FSI -- 4 Experiments -- 5 Conclusion -- Acknowledgements -- References -- Knowledge Discovery Foundations: Classification -- Bayesian Face Recognition Approach Based on Feature Fusion -- 1 Introduction -- 2 Related Work -- 3 Proposed Method -- 4 Experiments -- 5 Conclusion -- References -- Predictive Model for Brazilian Presidential Election Based on Analysis of Social Media -- 1 Introduction -- 2 Related Work. , 3 Political Scenario and Methodology -- 4 Mathematical Modeling and Proposed Model -- 5 Numerical Results -- 6 Final Considerations -- References -- On Back-Propagation Network to Early Judgment of Seismic Sequences -- Abstract -- 1 Introduction -- 2 Seismic Sequence Data Collection and Preprocessing -- 2.1 Sequence Data Selection and Initial Classification -- 2.2 Selection of Sequence Single Parameter Criterion -- 3 Neural Network Model for Early Prediction of Earthquake Types -- 3.1 BP Neural Network -- 3.2 BP Neural Network Model Construction -- 3.3 BP Neural Network Model Implementation -- 4 The Classification Results -- 4.1 Examination of Inner Coincidence -- 4.2 The Test Sample -- 5 Conclusion and Discussion -- Acknowledgement -- References -- Privacy-Protected KNN Classification Algorithm Based on Negative Database -- Abstract -- 1 Introduction -- 2 Related Work -- 3 Preliminaries -- 3.1 K-Hidden Negative Database Generation Algorithm -- 3.2 European Distance Calculation Formula on Negative Database -- 4 Privacy-Protected KNN Classification Algorithm -- 5 Experiments -- 5.1 Experiments on the Impact of r -- 5.2 Experiments on the Impact of P -- 5.3 Experiments on the Impact of k -- 6 Conclusion -- References -- TruRec: An Improved Trust-Based Recommendation in Cross-Domain -- 1 Introduction -- 2 Problem Description -- 3 Proposed Approach -- 3.1 Generating a Domain-Specific Trust Network -- 3.2 Construct a Uniform Objective Function -- 4 Experiment -- 4.1 Date Set -- 4.2 Parameter Analysis -- 4.3 Comparison on Different Approaches -- 5 Conclusions -- References -- Knowledge Discovery Foundations: Clustering -- Knowledge Matching in Horizontal Collaborative Fuzzy Clustering -- Abstract -- 1 Introduction -- 2 Related Work -- 2.1 Horizontal Collaborative Fuzzy c-Means Clustering Algorithm -- 2.2 Bipartite Graph Matching. , 3 The Improved Horizontal Collaborative Fuzzy c-Means Clustering Algorithm -- 3.1 Problem Description -- 3.2 Knowledge Matching Algorithm -- 3.3 The Improved Horizontal Collaborative Fuzzy c-Means Clustering Algorithm -- 4 Experimental Analysis -- 4.1 Experiment on Artificial Dataset -- 4.2 Experiment on Real Dataset -- 5 Conclusion -- Acknowledgement -- References -- KNN-Based Pseudo-supervised RCNN Framework for Text Clustering -- 1 Introduction -- 2 RCNN -- 3 Proposed Method -- 3.1 Pre-clustering -- 3.2 KNN Analysis -- 3.3 RCNN Training -- 4 Experiment -- 4.1 Database -- 4.2 Evaluation Metrics -- 4.3 Experimental Settings and Results -- 5 Discussion and Conclusions -- References -- Clustering Optimization and Evaluation of Campus Network User Behavior Analysis System -- Abstract -- 1 Introduction -- 2 Literature Review -- 3 The Improved Clustering Algorithm of User Behavior -- 4 User Behavior Clustering Analysis and Evaluation -- 5 Conclusion and Future Work -- References -- Minkowski Metric Based Soft Subspace Clustering with Different Minkowski Exponent and Feature Weight Exponent -- 1 Introduction -- 2 Related Works -- 3 MSSC with Different Minkowski Exponent and Feature Weight Exponent -- 3.1 A General Objective Function of MSSC -- 3.2 An Analysis on the Effect of Minkowski Exponent -- 4 Experimental Results and Analysis -- 4.1 Experiment Setup -- 4.2 The Effects of Feature Weight Exponent -- 4.3 The Effect of Minkowski Exponent and the Robust Property of FPI-MSSC and AFPI-MSSC -- 5 Conclusions -- References -- Knowledge Discovery Foundations: Knowledge Management -- Semantic Knowledge Sharing Mechanism Based on Blockchain -- Abstract -- 1 Introduction -- 2 Semantic Knowledge Sharing Framework Based on Blockchain -- 2.1 Basic Framework -- 2.2 Unicom Interaction -- 2.3 The Global Knowledge Graph Construction Process. , 3 Semantic Knowledge Sharing Algorithm Based on Block Chain -- 3.1 Query Transaction Flow -- 3.2 Smart Contract Design for Trading Processes -- 4 Experimental Analysis -- 4.1 Verification Experiment and Result Analysis -- 4.2 Result Analysis of Comparative Experiment -- 5 Conclusion -- Acknowledgments -- References -- Semantic Retrieval Based on User Intention Recognition in Engineering Domain -- Abstract -- 1 Introduction -- 2 The Overall Technical Framework -- 3 The Glossary Model Construction -- 4 User Retrieval Intention Recognition Method -- 4.1 Retrieval Intention Representation -- 4.2 Recognition of Retrieval Intention -- 4.3 Word Expansion and Semantic Retrieval -- 5 Case Analysis and Conclusions -- Acknowledgment -- References -- Path-Based Knowledge Graph Completion Combining Reinforcement Learning with Soft Rules -- Abstract -- 1 Introduction -- 2 Methodology -- 2.1 Soft Rules -- 2.2 Reinforcement Learning Framework -- 2.3 Training -- 3 Discussion -- 3.1 Effectiveness -- 3.2 Correctness -- 4 Conclusion -- Acknowledgments -- References -- A Model of Trust Knowledge Based on Trust Relationship and Knowledge Sharing -- Abstract -- 1 Introduction -- 2 The UETK Model -- 3 Validation of the UETK Model -- 4 Conclusion -- Acknowledgment -- Knowledge Discovery Foundations: Machine Learning and Artificial Intelligence -- Mathematical Programming for Piecewise Linear Representation of Discrete Time Series -- Abstract -- 1 Introduction -- 2 The \ell 1 Trend Filtering -- 3 The Proposed Model -- 4 Experiments -- 4.1 Online Public Opinion Time Series -- 4.2 Air Quality Time Series -- 5 Conclusion -- Acknowledgements -- References -- Tag2Vec: Tag Embedding for Top-N Recommendation -- 1 Introduction -- 2 Related Work -- 3 Methodology -- 3.1 Tag Embedding Based on Representation Learning -- 3.2 Algorithm Description -- 4 Experiments -- 4.1 Datasets. , 4.2 Baselines -- 4.3 Evaluation Metrics -- 4.4 Evaluation -- 5 Conclusion -- References -- Enhance Target Features in Real-Time Arbitrary Style Transfer -- Abstract -- 1 Introduction -- 2 Related Works -- 3 Proposed Method -- 3.1 AdaIN Module -- 3.2 WCT Module -- 3.3 Architecture -- 4 Experiments Verification -- 5 Results Analysis -- 6 Conclusion and Future Work -- References -- Cross-Projection for Embedding Translation in Knowledge Graph Completion -- Abstract -- 1 Introduction -- 2 Our Model -- 2.1 Relation Conflicts and Effect Transitivity of Triple -- 2.2 CpTE Model -- 3 Experiments and Analysis -- 3.1 Data Sets for Experiment -- 3.2 Link Prediction -- 3.3 Triple Classification -- 4 Conclusions and Future Work -- Acknowledgments -- References -- Topological Data Analysis for Time Series Changing Point Detection -- Abstract -- 1 Introduction -- 2 Methods -- 2.1 Time Series Pattern Changing Detection -- 2.2 Method I: Rips-Filtration of Sliding Windows -- 2.3 Method II: Piecewise Linear Complex Filtration of Sliding Windows -- 3 Experimental Results -- 3.1 Synthetic Time Series -- 3.2 Real-World Time Series -- 3.3 Rips-Filtration Applied to the Synthetic Time Series -- 3.4 Piecewise Linear Filtration Applied to Synthetic Time Series -- 3.5 Rips-Filtration Applied to Real-World Time Series -- 3.6 Piecewise Linear Filtration Applied to Real-World Time Series -- 4 Conclusions -- References -- Hyperspectral Remote Sensing Images Feature Extraction Based on Weighted Classwise Non-locality Preserving Projection -- Abstract -- 1 Introduction -- 2 Principle of Algorithm -- 2.1 CNLPP -- 2.2 WCNLPP -- 3 Experiments -- 3.1 Experiment Data Sets -- 3.2 Experiment Results -- 4 Conclusion -- Acknowledgements -- References -- Sample Generation Combining Generative Adversarial Networks and Residual Dense Networks -- Abstract -- 1 Introduction -- 2 RDGAN. , 3 Experiments.

Note: Intro -- Preface -- Organizing Committee -- General Chairs -- Program Chairs -- Organizing Chairs -- Publication Chairs -- Publicity Chairs -- Program Committee -- Contents -- Natural Computation: Theory and Algorithms -- RRS: An Explainable Model Scale Search Strategy -- 1 Introduction -- 2 Model Scale Search Strategy -- 2.1 Explainable Preprocessing Method -- 2.2 Episodic Reinforced Sequence -- 3 Experiment -- 3.1 Comparative Verification Based on Interpretable Denoising Algorithms -- 3.2 Correctness Verification Based on Episodic Enhanced Sequence -- 3.3 Comparative Verification Analysis Based on Episodic Enhanced Sequence Method -- 3.4 Conclusion -- References -- Detection of Small Targets in Aerial Images Based on Feature Fusion -- 1 Introduction -- 2 MF-SSD Small Target Detection Network -- 2.1 Small Target Detection Processing Model MF-SSD -- 2.2 Design of Feature Fusion Sub-network -- 2.3 The Receptive Field Enhancement Module -- 2.4 Improved Feature Extraction Network -- 3 Experiment and Analysis of Target Detection in Aerial Images -- 3.1 Experimental Environment and Settings -- 3.2 Experimental Results and Analysis -- 4 Conclusion -- References -- Intrusion Detection Based on LSTM and Random Forests -- 1 Introduction -- 2 Model Design -- 3 Dataset -- 4 Binary Classification Algorithm -- 4.1 Activation Function -- 4.2 Pooling Layer -- 4.3 LSTM Layer -- 4.4 Experimental Results -- 5 Multiple Classification Algorithms -- 5.1 Decision Tree -- 5.2 Random Forests Model -- 5.3 Experimental Results -- 6 Conclusion -- References -- Research and Hardware Implementation of Binocular Vision Obstacle Avoidance for UAV -- 1 Introduction -- 2 Principle of Binocular Stereo Vision -- 3 Binocular Camera Calibration -- 4 Canny Operator Edge Detection -- 5 OpenCV-Based Binocular Vision Stereo Matching -- 5.1 Stereo Matching Algorithm. , 5.2 Stereo Calibration and Stereo Matching -- 6 Conclusion -- References -- Parameter Estimation of Equivalent Circuit Model for Lithium Batteries -- 1 Introduction -- 2 A Second-order RC Equivalent Circuit Model -- 3 External Characteristics Experiment -- 3.1 Different Multiplier Discharge Test -- 3.2 Charging Experiment at Different Temperature -- 4 Model System Estimation -- 4.1 HPPC Discharge Test -- 4.2 Parameter Estimation -- 4.3 Model Building and Validation -- 5 Conclusion -- References -- Improved U-Net Network for Segmentation on Femur Images -- 1 Introduction -- 2 Improved U-Net Model -- 2.1 Improved Residual Module -- 2.2 Improved Jump Connection -- 2.3 Improved Loss Function -- 3 Experiment and Analysis -- 3.1 Dataset -- 3.2 Evaluation Indicators -- 3.3 Network Structure Improvement Comparison Experiment -- 3.4 Loss Function Comparison Experiment -- 3.5 Comparison Experiments with Existing Methods -- 4 Conclusion -- References -- A 14-Bit 2MS/s Digital Self-calibrating SAR ADC Design and Simulation -- 1 Introduction -- 2 14Bit Self-calibrating SAR ADC Structure and Working Principle -- 2.1 Overall Structure -- 2.2 Calibrate DAC -- 2.3 Working Principle -- 2.4 Calibration Mode -- 3 Simulation Results -- 4 Conclusion -- References -- A Windowed Interpolation Algorithm for High-Precision ADC Spectrum Testing -- 1 Introduction -- 2 The Principle and Design of Windowing Function -- 2.1 Window Function Principle -- 2.2 Design of Five-Term Fourth Order Hanning Window Functions -- 3 Four Spectral Lines with Window Interpolation Algorithm -- 3.1 A Windowed Interpolation Algorithm -- 3.2 Analysis and Design of Four Spectral Line Interpolation Algorithm -- 4 Simulation Experiment Analysis -- 4.1 Test Basic Process -- 4.2 Test Results and Analysis -- 5 Conclusions -- References. , Temperature Compensation Algorithms Based on Digital Infrared Thermopile Sensors Systems -- 1 Introduction -- 2 Infrared Temperature Sensors System Design -- 2.1 Thermopile Temperature Sensors -- 2.2 Design of Infrared Temperature Measurement Systems -- 3 Experimental Platform Construction and Testing -- 4 Algorithm Fitting and Analysis -- 4.1 GA-BP Neural Network Algorithm -- 4.2 Comparative Analysis of Experimental Data -- 5 Conclusion -- References -- Optimizing Deep-Learning Inference Operations -- 1 Introduction -- 2 Related Work -- 3 Method -- 3.1 Uniform Symmetric Quantizer -- 3.2 Weight Sharing -- 4 Experimental Results -- 4.1 Datasets -- 4.2 Evaluation Criteria -- 4.3 Statistics on the Distribution of Weight Values in Different Networks -- 5 Conclusion -- References -- An Efficient MRI Impulse Noise Multi-stage Hybrid Filter Based on Cartesian Genetic Programming -- 1 Introduction -- 2 CGP Detection -- 2.1 Feature Extraction Phase -- 2.2 Cartesian Genetic Programming Model -- 3 Noise Elimination Phase -- 3.1 Adaptive Median Filter -- 3.2 Shrinking Window Filter -- 3.3 Edge-Preserving Filter -- 4 Denoising Performance -- 5 Conclusion -- References -- Multi-objective Strategy Based on Rational Particle Swarm Optimization for Environmental/Economic Dispatch -- 1 Introduction -- 2 Brief Reviews -- 2.1 Environmental Economic Dispatch Issues -- 2.2 Objective Function -- 2.3 Constraints -- 2.4 Aggregate Objective Function -- 2.5 Particle Swarm Algorithm -- 2.6 Response Surface Method -- 3 Improved Multi-objective Particle Swarm Algorithm -- 3.1 The Second-Order Approximation Model -- 3.2 Integrated Algorithm Model -- 3.3 Algorithm Description -- 3.4 Pareto Frontier Eclectic Solution Selection -- 4 Algorithm Simulation and Analysis -- 4.1 Analysis of Results -- 5 Conclusions -- References. , Express Service Composition Optimization Based on Improved Ant Colony Algorithm -- 1 Introduction -- 2 Proposed Problem -- 3 Construction of Express Service Composition Models -- 3.1 QoS Evaluation Model of Express Service -- 3.2 The Objective Function and Constraints of Express Service Composition -- 4 Improvement of Solution Algorithm -- 4.1 Introduction of Ant Colony Algorithm -- 4.2 Improvement of Ant Colony Algorithm -- 5 Case Study and Its Result -- 5.1 Experimental Design -- 5.2 Data of the Experimental Example -- 5.3 Experimental Results of Traditional Ant Colony Algorithm -- 5.4 Experimental Results of Improved Ant Colony Algorithm -- 5.5 Results Analysis -- 6 Conclusion -- References -- A Dynamic Multi-objective Evolutionary Algorithm Assisted by Kernel Ridge Regression -- 1 Introduction -- 2 Background Knowledge -- 2.1 The Definition of the DMOPs -- 2.2 Kernel Ridge Regression -- 3 Proposed Algorithm -- 3.1 Kernel Ridge Regression-Based Prediction Strategy -- 3.2 MOEA/D-KRR Algorithm -- 4 Computational Experiments -- 4.1 Experimental Settings -- 4.2 Experimental Results -- 5 Conclusions -- References -- Higher Order Preference on the Evolution of Cooperation on Barabási-Albert Scale-Free Network -- 1 Introduction -- 2 Model -- 2.1 The Definition of Game Neighbor -- 2.2 Prisoner's Dilemma Game Model Based on High-Order Preference -- 3 Simulation Experiment Design and Results -- 3.1 Simulation Experiment Design -- 3.2 Simulation Experiment Results -- 4 Analysis of Experimental Results -- 4.1 Analysis of the Impact of High-Order Preference on the Cooperative Behavior of Different Connected Groups -- 4.2 Analysis of the Relationship Between the Micro-Evolution and Macro-Performance of Individual Games -- 5 Conclusion -- References -- Nearest Neighbor Synthesis of CNOT Circuit Based on Matrix Transformation -- 1 Introduction -- 2 Background. , 3 Feasible Strategies Analysis Based on Matrix Transformation -- 3.1 NN Synthesis Based on the Boolean Matrix Flipped by the Center -- 3.2 NN Synthesis Based on the Transpose Boolean Matrix -- 4 Parallel NN Synthesis of CNOT Circuits -- 5 Experiments and Result Analysis -- 6 Conclusions -- References -- State of Charge Estimation of Lithium Batteries Based on Extended Kalman Filter and Temperature Compensation -- 1 Introduction -- 2 Related Work -- 3 Lithium Battery Model Establishment and Parameter Identification -- 3.1 State-of-Charge Estimation Model -- 3.2 Lithium Battery Equivalent Model -- 3.3 Battery Model Identification Parameters -- 3.4 Battery Model Identification Parameters -- 3.5 EKF Algorithm -- 4 Experimental Verification and Simulation Analysis -- 5 Conclusion -- References -- Improved GAN for Abnormal Flame Recognition Based on Siamese Network Structure -- 1 Introduction -- 2 Related Work -- 3 Proposed Method -- 3.1 Network Structure -- 3.2 Loss Function -- 3.3 Model Testing -- 4 Experiments -- 4.1 Dataset Preparation -- 4.2 Results -- 5 Conclusions -- References -- Nine Electrodes Human Body Composition Model Based on SVM(SVM-BCM9) -- 1 Introduction -- 2 Data Acquisition System -- 3 Raw Data Preprocessing -- 3.1 Five Segment Model of Human Body -- 3.2 BC Index -- 4 SVM-BCM9 -- 4.1 SVM-BCM9 Algorithm Flow -- 5 Experimental Results and Analysis -- 5.1 Data Acquisition and Measurement -- 5.2 Parameters Setting -- 5.3 Comparison and Analysis of Human Experiment Results -- 6 Conclusion -- References -- A Self-adaptive Intrusion Detection Model Based on Bi-LSTM-CRF with Historical Access Logs -- 1 Introduction -- 2 Related Works -- 3 Model and Training Process -- 3.1 LSTM Layer -- 3.2 Bi-LSTM Layer -- 3.3 CRF Layer -- 4 Experiment -- 4.1 Dataset Preparation -- 4.2 Process Description -- 4.3 Results Discussion -- 5 Conclusion -- References. , A Left-Looking Sparse Cholesky Parallel Algorithm for Shared Memory Multiprocessors.

Note: Intro -- Preface -- Organization -- Organizing Committee -- General Chairs -- Program Chairs -- Organizing Chairs -- Finance Chair -- Publication Chairs -- Publicity Chairs -- Program Committee -- Reviewers -- Contents -- Natural Computation: Theory and Algorithms - Deep Learning and Feedforward Neural Networks -- Optimizing Convolutional Neural Network Architecture Using a Self-adaptive Harmony Search Algorithm -- Abstract -- 1 Introduction -- 2 System Overviews -- 3 Phase-1 Process -- 3.1 Phase-1 Algorithm -- 3.2 Generating CNN Candidates Using the HM1 Mechanism -- 3.3 Building a CNN Derived from Vgg16 -- 4 Phase-2 Process -- 4.1 Phase-2 Algorithm -- 4.2 Generating a Fine-Tuned CNN Using the HM2 Mechanism -- 4.3 Building an Optimized CNN -- 5 Experiments -- 5.1 Experimental Environments -- 5.2 Experimental Results -- 6 Conclusions -- References -- Global Features of Fused Frame Relationships Help Video Classification -- 1 Introduction -- 2 Related Work -- 3 Global Feature Module -- 3.1 Inter-frame Relation -- 3.2 Global Feature Fusion -- 4 Experiments -- 4.1 Dataset and Implementation Details -- 4.2 Improving ECO-full Baseline -- 5 Conclusion -- References -- A Comparison and Strategy of Semantic Segmentation on Remote Sensing Images -- 1 Introduction -- 2 Methods Comparison -- 2.1 FCN -- 2.2 U-Net -- 2.3 SegNet -- 2.4 DeepLab -- 2.5 PSPNet -- 3 Experiments and Results -- 3.1 Datasets -- 3.2 Experimental Results -- 4 On-Orbit Semantic Segmentation Strategy for TianZhi-2 -- 5 Conclusions -- References -- Att-ConvLSTM: PM2.5 Prediction Model and Application -- Abstract -- 1 Introduction -- 2 Data and Methods -- 2.1 Data Description -- 2.2 ConvLSTM -- 2.3 Spatiotemporal Attention Mechanism -- 2.4 ε-Insensitive Loss Function -- 3 Development of Att-ConvLSTM Model -- 4 Result and Analysis -- 4.1 Time Series Prediction. , 4.2 Comparison of Attention Mechanisms Models -- 4.3 Application Experiment of the Model -- 5 Conclusion -- References -- SAR Ship Detection Method Based on Convolutional Neural Network and Multi-layer Feature Fusion -- Abstract -- 1 Introduction -- 2 Method -- 2.1 Base Network -- 2.2 Feature Fusion -- 2.3 Output Network -- 2.4 Training -- 3 Experiment Results and Analysis -- 3.1 Sentinel-1A Dataset and Performance Evaluation Metrics -- 3.2 Fusion Feature Comparison -- 3.3 Different Base Network -- 3.4 Comparison with Other Methods -- 4 Conclusion -- References -- Deep Learning Training Management Platform Based on Distributed Technologies in Resource-Constrained Scenarios -- 1 Introduction -- 2 Platform Architecture -- 2.1 Distributed Cluster Management Layer -- 2.2 Deep Learning Management Layer -- 2.3 Visual Interaction Layer -- 3 Core Algorithms -- 3.1 Multi-task Scheduling Algorithm -- 3.2 Allocation Algorithm -- 3.3 Fault-Tolerant Algorithm -- 4 Conclusion -- References -- A Deep Learning Based Reasoner for Global Consistency in Named Entity Recognition -- 1 Introduction -- 2 Related Works -- 3 The NE-Reasoner Model -- 3.1 Overall Architecture -- 3.2 Encoder and Decoder -- 3.3 Candidate Pool -- 3.4 Reasoner and the Next Layer -- 4 Experimental Results -- 4.1 Dateset and Parameters Setting -- 4.2 Result -- 4.3 Analysis -- 5 Conclusions and Future Work -- References -- Multi-level Feature Combination in Dialogue State Tracking -- 1 Introduction -- 2 Related Works -- 3 Model Framework -- 3.1 Memory-Network Module -- 3.2 Bi-LSTM+Self-attention Module -- 3.3 Score-Module -- 4 Experiments -- 4.1 Data Set -- 4.2 The Implementation of Model Framework -- 4.3 Comparison of Experimental Results -- 4.4 Analysis -- 5 Summary -- References -- Unmanned Aerial Vehicles Path Planning Based on Deep Reinforcement Learning -- 1 Introduction. , 2 Problem Formulation -- 3 Approach -- 4 Experiments -- 5 Conclusion -- References -- Apple Freshness Recognition Technology Based on Gas Sensors -- Abstract -- 1 Introduction -- 2 Apple Freshness Detection Technology -- 2.1 Dielectric Property Freshness Detection -- 2.2 Sensory Quality Evaluation -- 2.3 Odor Recognition -- 3 Information Collection System -- 3.1 Experimental Devices and Processes -- 3.2 Data Processing -- 4 Freshness Evaluation -- 4.1 Fuzzy Comprehensive Evaluation Scheme for Sensory Quality of Apple -- 4.2 Establishment of Factor Sets, Comment Sets, and Weighted Sets -- 4.3 Results and Analysis -- 4.4 Gas Freshness Identification -- 5 Conclusion and Future Work -- References -- A Review of the Theory and Method for New Developed Feedforward Neural Networks -- 1 Introduction -- 2 Algebraic Algorithm of Feedforward Neural Networks -- 2.1 Network Structure -- 2.2 Basic Theories and Algorithms -- 2.3 Time Complexity of Algebraic Algorithm -- 3 Weight Function Neural Network Theories and Methods -- 3.1 Network Structure -- 3.2 Basic Theories and Algorithms -- 3.3 Error Analysis -- 3.4 Computational Complexity -- 4 Summary and Prospect -- References -- Awareness Learning for Balancing Performance and Diversity in Neural Network Ensembles -- 1 Introduction -- 2 Awareness in Negative Correlation Learning -- 3 Relations Between Diversity and Cooperations -- 3.1 Descriptions of Experimental Setup -- 3.2 Results of NCLA on the Card Data -- 4 Conclusions -- References -- Natural Computation: Theory and Algorithms - Genetic and Evolutionary Algorithms -- A Model and an Algorithm for Empty Car Distribution in Railway Transportation -- 1 Introduction -- 2 Fuzzy Empty Car Distribution Problem -- 2.1 Some Symbols -- 2.2 Car Distribution Model -- 2.3 Equivalent Crisp Model -- 3 Design of GA -- 3.1 The First Stage -- 3.2 The Second Stage. , 3.3 Global Algorithm Procedure -- 4 Numerical Example -- 5 Conclusions -- References -- Levelized Cost of Energy Optimization Method for the Dish Solar Thermal Power Generation System -- Abstract -- 1 Introduction -- 2 Mathematical Model of Dish-Stirling Optical Thermal Power Generation System -- 2.1 Capacity Modeling of Dish-Stirling Optical Thermal Power Generation System -- 2.2 Generation Cost Modeling of Dish-Stirling Optical Thermal Power Generation System -- 3 Optimization Algorithms -- 4 Simulation and Analysis -- 4.1 Model Parameter -- 4.2 Impact of Generation Capacity on LCOE -- 4.3 Effect of Different Heat Storage Fluids on LCOE -- 4.4 Effect of Different Heat Storage Time on LCOE -- 5 Conclusion -- Acknowledgment -- References -- A Novel Ant Colony Optimization Algorithm with Dynamic Control Population for Community Detecting -- 1 Introduction -- 2 Related Work -- 2.1 Community Mining -- 2.2 Optimization Algorithms of Ant Colony Algorithms for Community Mining -- 3 Dynamic Population Control for Ant Colony Optimization -- 3.1 The Rule Trigging the Delete Operation -- 3.2 Deleting Rule -- 4 Experiments -- 4.1 Datasets -- 4.2 Experiment Results -- 5 Conclusion -- References -- A Hybrid Bat Algorithm Based on Combined Semantic Measures for Word Sense Disambiguation -- 1 Introduction -- 2 Proposed Method -- 3 Experimental Results -- 4 Conclusion -- References -- A Multi-objective Optimization Algorithm Based on Monarch Butterfly Optimization -- Abstract -- 1 Introduction -- 2 Monarch Butterfly Optimization -- 3 The Hybrid Multi-objective MBO -- 3.1 The New Migration Operator -- 3.2 The Combination with Operations in NSGA-II -- 4 Experiments -- 4.1 Comparisons with Basic Algorithms -- 4.2 Comparisons with Other Algorithms -- 5 Conclusion -- Acknowledgement -- References. , An Improved Quantum Genetic Algorithm Based on Population Partition and Dynamic Probability Amplitude -- Abstract -- 1 Introduction -- 2 Quantum Genetic Algorithm (QGA) -- 3 Dynamic Inverse Probability Amplitude -- 4 Bidirectional Decoding Operator -- 5 Population Partition Strategy -- 6 Quantum Variation -- 7 Algorithm Description -- 8 Experimental Design and Results -- 9 Analysis of Results -- 10 Conclusion -- References -- Natural Computation: Theory and Algorithms - Nonlinear Phenomena, Chaos, Complex Networks and Systems -- Sink Location Privacy Protection Algorithm Based on Tangential Path in WSN -- Abstract -- 1 Introduction -- 1.1 Attacker Model -- 1.2 Concept Definition -- 2 ABTP Algorithm -- 2.1 ABTP Algorithm Description -- 2.2 Algorithm Proceeding -- 3 Theoretical Analysis of Selecting Fake Sinks -- 4 Simulation Experiment -- 4.1 Transmission Delay -- 4.2 Protection Strength -- 4.3 Communication Overhead -- 5 Concluding Remarks -- References -- Study on the Energy Dissipation of Two Lane Traffic Flow with Lane Reduction -- Abstract -- 1 Introduction -- 2 Model of Reduced Lane and Energy Dissipation -- 3 Simulation and Analysis -- 3.1 Influence of the Length of the Reduced Lane on the Road Capacity in the Periodic Boundary Condition -- 3.2 Influence of the Length of the Reduced Lane and the Maximum Speed and the Vehicle Length on the Energy Dissipation in the Periodic Boundary Condition -- 3.3 Influence of the Injection Rate σ and β on the Energy Dissipation in the Periodic Boundary Condition -- 4 Summary and Conclusion -- Acknowledgment -- References -- Chaos and Quasi-period in Erbium-Doped Fiber Laser -- Abstract -- 1 Introduction -- 2 Dynamical Model -- 3 Result and Discussion -- 3.1 A Path to Chaos via Varying the Modulation Depths -- 3.2 Another Path to Chaos via Varying the Modulation Frequencies. , 3.3 Effect of Er-Doped Concentration on the Dynamics.

Note: Intro -- Foreword -- Preface -- Book Website and Resources -- To the Instructors -- To the Readers -- Acknowledgements -- Editor Biography -- List of Contributors -- Contents -- Terminologies -- 1 Basic concepts of Graphs -- 2 Machine Learning on Graphs -- 3 Graph Neural Networks -- Notations -- Numbers, Arrays, and Matrices -- Graph Basics -- Basic Operations -- Functions -- Probablistic Theory -- Part I Introduction -- Chapter 1 Representation Learning -- 1.1 Representation Learning: An Introduction -- 1.2 Representation Learning in Different Areas -- 1.2.1 Representation Learning for Image Processing -- 1.2.2 Representation Learning for Speech Recognition -- 1.2.3 Representation Learning for Natural Language Processing -- 1.2.4 Representation Learning for Networks -- 1.3 Summary -- Chapter 2 Graph Representation Learning -- 2.1 Graph Representation Learning: An Introduction -- 2.2 Traditional Graph Embedding -- 2.3 Modern Graph Embedding -- 2.3.1 Structure-Property Preserving Graph Representation Learning -- 2.3.1.1 Structure Preserving Graph Representation Learning -- 2.3.1.2 Property Preserving Graph Representation Learning -- 2.3.2 Graph Representation Learning with Side Information -- 2.3.3 Advanced Information Preserving Graph Representation Learning -- 2.4 Graph Neural Networks -- 2.5 Summary -- Chapter 3 Graph Neural Networks -- 3.1 Graph Neural Networks: An Introduction -- 3.2 Graph Neural Networks: Overview -- 3.2.1 Graph Neural Networks: Foundations -- 3.2.2 Graph Neural Networks: Frontiers -- 3.2.3 Graph Neural Networks: Applications -- 3.2.3.1 Graph Construction -- 3.2.3.2 Graph Representation Learning -- 3.2.4 Graph Neural Networks: Organization -- 3.3 Summary -- Part II Foundations of Graph Neural Networks -- Chapter 4 Graph Neural Networks for Node Classification -- 4.1 Background and Problem Definition. , 4.2 Supervised Graph Neural Networks -- 4.2.1 General Framework of Graph Neural Networks -- 4.2.2 Graph Convolutional Networks -- 4.2.3 Graph Attention Networks -- 4.2.4 Neural Message Passing Networks -- 4.2.5 Continuous Graph Neural Networks -- 4.3 Unsupervised Graph Neural Networks -- 4.3.1 Variational Graph Auto-Encoders -- 4.3.1.1 Problem Setup -- 4.3.1.2 Model -- 4.3.1.3 Discussion -- 4.3.2 Deep Graph Infomax -- 4.3.2.1 Problem Setup -- 4.3.2.2 Model -- 4.3.2.3 Discussion -- 4.4 Over-smoothing Problem -- 4.5 Summary -- Chapter 5 The Expressive Power of Graph Neural Networks -- 5.1 Introduction -- 5.2 Graph Representation Learning and Problem Formulation -- 5.3 The Power of Message Passing Graph Neural Networks -- 5.3.1 Preliminaries: Neural Networks for Sets -- 5.3.2 Message Passing Graph Neural Networks -- 5.3.3 The Expressive Power of MP-GNN -- 5.3.4 MP-GNN with the Power of the 1-WL Test -- 5.4 Graph Neural Networks Architectures that are more Powerful than 1-WL Test -- 5.4.1 Limitations of MP-GNN -- 5.4.2 Injecting Random Attributes -- 5.4.2.1 Relational Pooling GNN (RP-GNN) (Murphy et al, 2019a) -- 5.4.2.2 Random Graph Isomorphic Network (rGIN) (Sato et al, 2021) -- 5.4.2.3 Position-aware GNN (PGNN) (You et al, 2019) -- 5.4.2.4 Randomized Matrix Factorization (Srinivasan and Ribeiro, 2020a)(Dwivedi et al, 2020) -- 5.4.3 Injecting Deterministic Distance Attributes -- 5.4.3.1 Distance Encoding (Li et al, 2020e) -- 5.4.3.2 Identity-aware GNN (You et al, 2021) -- 5.4.4 Higher-order Graph Neural Networks -- 5.4.4.1 k-WL-induced GNNs (Morris et al, 2019) -- 5.4.4.2 Invariant and equivariant GNNs (Maron et al, 2018, 2019b) -- 5.4.4.3 FWL-induced GNNs (Maron et al, 2019a -- Chen et al, 2019f) -- 5.5 Summary -- Chapter 6 Graph Neural Networks: Scalability -- 6.1 Introduction -- 6.2 Preliminary -- 6.3 Sampling Paradigms -- 6.3.1 Node-wise Sampling. , 6.3.1.1 GraphSAGE -- 6.3.1.2 VR-GCN -- 6.3.2 Layer-wise Sampling -- 6.3.2.1 FastGCN -- 6.3.2.2 ASGCN -- 6.3.3 Graph-wise Sampling -- 6.3.3.1 Cluster-GCN -- 6.3.3.2 GraphSAINT -- 6.3.3.3 Overall Comparison of Different Models -- 6.4 Applications of Large-scale Graph Neural Networks on Recommendation Systems -- 6.4.1 Item-item Recommendation -- 6.4.2 User-item Recommendation -- 6.5 Future Directions -- Chapter 7 Interpretability in Graph Neural Networks -- 7.1 Background: Interpretability in Deep Models -- 7.1.1 Definition of Interpretability and Interpretation -- 7.1.2 The Value of Interpretation -- 7.1.2.1 Model-Oriented Reasons -- 7.1.2.2 User-Oriented Reasons -- 7.1.3 Traditional Interpretation Methods -- 7.1.3.1 Post-Hoc Interpretation -- 7.1.3.2 Interpretable Modeling -- 7.1.4 Opportunities and Challenges -- 7.2 Explanation Methods for Graph Neural Networks -- 7.2.1 Background -- 7.2.2 Approximation-Based Explanation -- 7.2.2.1 White-Box Approximation Method -- 7.2.2.2 Black-Box Approximation Methods -- 7.2.3 Relevance-Propagation Based Explanation -- 7.2.4 Perturbation-Based Approaches -- 7.2.5 Generative Explanation -- 7.3 Interpretable Modeling on Graph Neural Networks -- 7.3.1 GNN-Based Attention Models -- 7.3.1.1 Attention Models for Homogeneous Graphs -- 7.3.1.2 Attention Models for Heterogeneous Graphs -- 7.3.2 Disentangled Representation Learning on Graphs -- 7.3.2.1 Is A Single Vector Enough? -- 7.3.2.2 Prototypes-Based Soft-Cluster Assignment -- 7.3.2.3 Dynamic Routing Based Clustering -- 7.4 Evaluation of Graph Neural Networks Explanations -- 7.4.1 Benchmark Datasets -- 7.4.1.1 Synthetic Datasets -- 7.4.1.2 Real-World Datasets -- 7.4.2 Evaluation Metrics -- 7.5 Future Directions -- Chapter 8 Graph Neural Networks: Adversarial Robustness -- 8.1 Motivation -- 8.2 Limitations of Graph Neural Networks: Adversarial Examples. , 8.2.1 Categorization of Adversarial Attacks -- Aspect 1: Property under Investigation (Attacker's Goal) -- Aspect 2: The Perturbation Space (Attacker's Capabilities) -- Aspect 3: Available Information (Attacker's Knowledge) -- Aspect 4: The Algorithmic View -- 8.2.2 The Effect of Perturbations and Some Insights -- 8.2.2.1 Transferability and Patterns -- 8.2.3 Discussion and Future Directions -- 8.3 Provable Robustness: Certificates for Graph Neural Networks -- 8.3.1 Model-Specific Certificates -- Lower Bounds on the Worst-Case Margin -- 8.3.2 Model-Agnostic Certificates -- Putting Model-Agnostic Certificates into Practice -- 8.3.3 Advanced Certification and Discussion -- 8.4 Improving Robustness of Graph Neural Networks -- 8.4.1 Improving the Graph -- 8.4.2 Improving the Training Procedure -- 8.4.2.1 Robust Training -- 8.4.2.2 Further Training Principles -- 8.4.3 Improving the Graph Neural Networks' Architecture -- 8.4.3.1 Adaptively Down-Weighting Edges -- 8.4.3.2 Further Approaches -- 8.4.4 Discussion and Future Directions -- 8.5 Proper Evaluation in the View of Robustness -- Empirical Robustness Evaluation -- Provable Robustness Evaluation -- 8.6 Summary -- Acknowledgements -- Part III Frontiers of Graph Neural Networks -- Chapter 9 Graph Neural Networks: Graph Classification -- 9.1 Introduction -- 9.2 Graph neural networks for graph classification: Classic works and modern architectures -- 9.2.1 Spatial approaches -- 9.2.2 Spectral approaches -- 9.3 Pooling layers: Learning graph-level outputs from node-level outputs -- 9.3.1 Attention-based pooling layers -- 9.3.2 Cluster-based pooling layers -- 9.3.3 Other pooling layers -- 9.4 Limitations of graph neural networks and higher-order layers for graph classification -- 9.4.1 Overcoming limitations -- 9.5 Applications of graph neural networks for graph classification -- 9.6 Benchmark Datasets. , 9.7 Summary -- Chapter 10 Graph Neural Networks: Link Prediction -- 10.1 Introduction -- 10.2 Traditional Link Prediction Methods -- 10.2.1 Heuristic Methods -- 10.2.1.1 Local Heuristics -- 10.2.1.3 Summarization -- 10.2.2 Latent-Feature Methods -- 10.2.2.1 Matrix Factorization -- 10.2.2.2 Network Embedding -- 10.2.2.3 Summarization -- 10.2.3 Content-Based Methods -- 10.3 GNN Methods for Link Prediction -- 10.3.1 Node-Based Methods -- 10.3.1.1 Graph AutoEncoder -- 10.3.1.2 Variational Graph AutoEncoder -- 10.3.1.3 Variants of GAE and VGAE -- 10.3.2 Subgraph-Based Methods -- 10.3.2.1 The SEAL Framework -- 10.3.2.2 Variants of SEAL -- 10.3.3 Comparing Node-Based Methods and Subgraph-Based Methods -- 10.4 Theory for Link Prediction -- 10.4.1 γ-Decaying Heuristic Theory -- 10.4.1.1 Definition of γ-Decaying Heuristic -- 10.4.1.2 Katz index -- 10.4.1.3 PageRank -- 10.4.1.4 SimRank -- 10.4.1.5 Discussion -- 10.4.2 Labeling Trick -- 10.4.2.1 Structural Representation -- 10.4.2.2 Labeling Trick Enables Learning Structural Representations -- 10.5 Future Directions -- 10.5.1 Accelerating Subgraph-Based Methods -- 10.5.2 Designing More Powerful Labeling Tricks -- 10.5.3 Understanding When to Use One-Hot Features -- Chapter 11 Graph Neural Networks: Graph Generation -- 11.1 Introduction -- 11.2 Classic Graph Generative Models -- 11.2.1 Erdős-Rényi Model -- 11.2.1.1 Model -- 11.2.1.2 Discussion -- 11.2.2 Stochastic Block Model -- 11.2.2.1 Model -- 11.2.2.2 Discussion -- 11.3 Deep Graph Generative Models -- 11.3.1 Representing Graphs -- 11.3.2 Variational Auto-Encoder Methods -- 11.3.2.1 The GraphVAE Family -- 11.3.2.2 Hierarchical and Constrained GraphVAEs -- 11.3.3 Deep Autoregressive Methods -- 11.3.3.1 GNN-based Autoregressive Model -- 11.3.3.2 Graph Recurrent Neural Networks (GraphRNN) -- 11.3.3.3 Graph Recurrent Attention Networks (GRAN). , 11.3.4 Generative Adversarial Methods.

Note: Intro -- Preface -- Acknowledgments -- Contents -- Biography -- List of Symbols -- 1 Introduction -- 1.1 General Background -- 1.2 Focus of This Book -- 1.3 Organization of the Remainder of the Book -- References -- 2 Complex Networks -- 2.1 Basic Concepts of Graphs -- 2.1.1 Graph Definitions -- 2.1.2 Connectivity -- 2.1.3 Paths and Cycles -- 2.1.4 Subgraphs -- 2.1.5 Trees and Forest -- 2.1.6 Graph Representation -- 2.2 Complex Network Models -- 2.2.1 Random Networks -- 2.2.2 Small-World Networks -- 2.2.3 Scale-Free Networks -- 2.2.4 Random Clustered Networks -- 2.2.5 Core-Periphery Networks -- 2.3 Complex Network Measures -- 2.3.1 Degree and Degree-Correlation Measures -- 2.3.2 Distance and Path Measures -- 2.3.3 Structural Measures -- 2.3.4 Centrality Measures -- 2.3.4.1 Distance-Based Centrality Measures -- 2.3.4.2 Path- and Walk-Based Centrality Measures -- 2.3.4.3 Vitality -- 2.3.4.4 General Feedback Centrality -- 2.3.5 Classification of the Network Measurements -- 2.4 Dynamical Processes in Complex Networks -- 2.4.1 Random Walks -- 2.4.2 Lazy Random Walks -- 2.4.3 Self-Avoiding Walks -- 2.4.4 Tourist Walks -- 2.4.5 Epidemic Spreading -- 2.4.5.1 Susceptible-Infected-Recovered (SIR) Model -- 2.4.5.2 Susceptible-Infected-Susceptible (SIS) Model -- 2.4.5.3 Epidemic Spreading in Complex Networks -- 2.5 Chapter Remarks -- References -- 3 Machine Learning -- 3.1 Overview of Machine Learning -- 3.2 Supervised Learning -- 3.2.1 Mathematical Formalization and Fundamental Assumptions -- 3.2.2 Overview of the Techniques -- 3.3 Unsupervised Learning -- 3.3.1 Mathematical Formalization and Fundamental Assumptions -- 3.3.2 Overview of the Techniques -- 3.4 Semi-Supervised Learning -- 3.4.1 Motivations -- 3.4.2 Mathematical Formalization and Fundamental Assumptions -- 3.4.3 Overview of the Techniques -- 3.5 Overview of Network-Based Machine Learning. , 3.6 Chapter Remarks -- References -- 4 Network Construction Techniques -- 4.1 Introduction -- 4.2 Similarity and Dissimilarity Functions -- 4.2.1 Formal Definitions -- 4.2.2 Examples of Vector-Based Similarity Functions -- 4.2.2.1 Numerical Data -- 4.2.2.2 Categorical Data -- 4.3 Transforming Vector-Based Data into Networks -- 4.3.1 Analysis of k-Nearest Neighbors and ε-Radius Networks -- 4.3.2 Combination of k-Nearest Neighbors and ε-Radius Network Formation Techniques -- 4.3.3 b-Matching Networks -- 4.3.4 Linear Neighborhood Networks -- 4.3.5 Relaxed Linear Neighborhood Networks -- 4.3.6 Network Formation Using Clustering Heuristics -- 4.3.7 Network Formation Using Overlapping Histogram Segments -- 4.3.8 More Advanced Network Formation Techniques -- 4.4 Transforming Time Series Data into Networks -- 4.4.1 Cycle Networks -- 4.4.2 Correlation Networks -- 4.4.3 Recurrence Networks -- 4.4.4 Transition Networks -- 4.5 Classification of Network Formation Techniques -- 4.6 Challenges in Transforming Unstructured Data to Networked Data -- 4.7 Chapter Remarks -- References -- 5 Network-Based Supervised Learning -- 5.1 Introduction -- 5.2 Representative Network-Based Supervised Learning Techniques -- 5.2.1 Classification Using k-Associated Graphs -- 5.2.2 Network Learning Toolkit (NetKit) -- 5.2.3 Classification Using Ease of Access Heuristic -- 5.2.3.1 Training Phase -- 5.2.3.2 Classification Phase -- 5.3 Chapter Remarks -- References -- 6 Network-Based Unsupervised Learning -- 6.1 Introduction -- 6.2 Community Detection -- 6.2.1 Relevant Concepts and Motivations -- 6.2.2 Mathematical Formalization and Fundamental Assumptions -- 6.2.3 Overview of the State-of-the-Art Techniques -- 6.2.4 Community Detection Benchmarks -- 6.3 Representative Network-Based Unsupervised Learning Techniques -- 6.3.1 Betweenness -- 6.3.2 Modularity Maximization. , 6.3.2.1 Clauset et al. Algorithm -- 6.3.2.2 Louvain Algorithm -- 6.3.3 Spectral Bisection Method -- 6.3.4 Community Detection Using Particle Competition -- 6.3.5 Chameleon -- 6.3.6 Community Detection by Space Transformation and Swarm Dynamics -- 6.3.7 Synchronization Methods -- 6.3.8 Finding Overlapping Communities -- 6.3.8.1 Clique Percolation -- 6.3.8.2 Bayesian Nonnegative Matrix Factorization Algorithm -- 6.3.8.3 Fuzzy Partition Algorithm -- 6.3.9 Network Embedding and Dimension Reduction -- 6.4 Chapter Remarks -- References -- 7 Network-Based Semi-Supervised Learning -- 7.1 Introduction -- 7.2 Network-Based Semi-Supervised Learning Assumptions -- 7.3 Representative Network-Based Semi-Supervised Learning Techniques -- 7.3.1 Maximum Flow and Minimum Cut -- 7.3.2 Gaussian Field and Harmonic Function -- 7.3.3 Tikhonov Regularization Framework -- 7.3.4 Local and Global Consistency -- 7.3.5 Adsorption -- 7.3.6 Semi-Supervised Modularity Method -- 7.3.7 Interaction Forces -- 7.3.8 Discriminative Walks (D-Walks) -- 7.4 Chapter Remarks -- References -- 8 Case Study of Network-Based Supervised Learning: High-Level Data Classification -- 8.1 A Quick Overview of the Chapter -- 8.2 Motivation -- 8.3 Model Description -- 8.3.1 Fundamental Ideas Behind the Model -- 8.3.1.1 Training Phase -- 8.3.1.2 Classification Phase -- 8.3.2 Derivation of the Hybrid Classification Framework -- 8.4 Possible Ways of Composing High-Level Classifiers -- 8.4.1 High-Level Classification Using a Mixture of Complex Network Measures -- 8.4.1.1 First Network Measure: Assortativity -- 8.4.1.2 Second Network Measure: Clustering Coefficient -- 8.4.1.3 Third Network Measure: Average Degree or Connectivity -- 8.4.2 High-Level Classification Using Tourist Walks -- 8.4.2.1 Calculating the Variational Descriptors Ti(y)(μ) and Ci(y)(μ). , 8.4.2.2 Determining the Intra-Modulation Parameters wintra(y)(μ) -- 8.4.2.3 Determining the Inter-Modulation Parameters winter(y)(μ) -- 8.5 Numerical Analysis of the High-Level Classification -- 8.5.1 An Illustrative Example -- 8.5.2 Parameter Sensitivity Analysis -- 8.5.2.1 Influence of the Parameters Related to the Network Formation -- 8.5.2.2 Influence of the Critical Memory Length -- 8.6 Application: Handwritten Digits Recognition -- 8.6.1 Motivation -- 8.6.2 Description of the MNIST Data Set -- 8.6.3 A Suitable Similarity Measure for Images -- 8.6.4 Configurations of the Low-Level Classification Techniques -- 8.6.5 Experimental Results -- 8.6.6 Illustrative Examples: High-Level Classification vs. Low-Level Classification -- 8.7 Chapter Remarks -- References -- 9 Case Study of Network-Based Unsupervised Learning: Stochastic Competitive Learning in Networks -- 9.1 A Quick Overview of the Chapter -- 9.2 Description of the Stochastic Competitive Model -- 9.2.1 Intuition of the Model -- 9.2.2 Derivation of the Transition Matrix -- 9.2.3 Definition of the Stochastic Nonlinear Dynamical System -- 9.2.4 Method for Estimating the Number of Communities -- 9.2.5 Method for Detecting Overlapping Structures -- 9.2.6 Parameter Sensitivity Analysis -- 9.2.6.1 Impact of the Parameter λ -- 9.2.6.2 Impact of the Parameter Δ -- 9.2.6.3 Impact of the Parameter K -- 9.2.7 Convergence Analysis -- 9.3 Theoretical Analysis of the Model -- 9.3.1 Mathematical Analysis -- 9.3.1.1 Discovering the Factor Pp(t+1) -- 9.3.1.2 Discovering the Factor PN(t+1) -- 9.3.1.3 Discovering the Factor PE(t+1) -- 9.3.1.4 Discovering the Factor PS(t+1) -- 9.3.1.5 The Transition Probability Function -- 9.3.1.6 Discovering the Distribution P(N(t)) -- 9.3.1.7 Discovering the Distribution of the Domination Level Matrix P(N(t)). , 9.3.2 Linking the Particle Competition Model and the Classical Multiple Independent Random Walks System -- 9.3.3 A Numerical Example -- 9.4 Numerical Analysis of the Detection of Overlapping Vertices and Communities -- 9.4.1 Zachary's Karate Club Network -- 9.4.2 Dolphin Social Network -- 9.4.3 Les misérables Novel Network -- 9.5 Application: Handwritten Digits and Letters Clustering -- 9.5.1 Brief Information of the Handwritten Digits and Letters Data Sets -- 9.5.2 Determining the Optimal Number of Particles and Clusters -- 9.5.3 Handwritten Data Clustering -- 9.6 Chapter Remarks -- References -- 10 Case Study of Network-Based Semi-Supervised Learning: Stochastic Competitive-Cooperative Learning in Networks -- 10.1 A Quick Overview of the Chapter -- 10.2 Description of the Stochastic Competitive-Cooperative Model -- 10.2.1 Differences of the Semi-Supervised and the Unsupervised Versions -- 10.2.2 Familiarizing with the Semi-Supervised Environment -- 10.2.3 Deriving the Modified Competitive Transition Matrix -- 10.2.4 Modified Initial Conditions of the System -- 10.3 Theoretical Analysis of the Model -- 10.3.1 Mathematical Analysis -- 10.3.2 A Numerical Example -- 10.4 Numerical Analysis of the Model -- 10.4.1 Simulation on a Synthetic Data Set -- 10.4.2 Simulations on Real-World Data Sets -- 10.5 Application: Detection and Prevention of Error Propagation in Imperfect Learning -- 10.5.1 Motivation -- 10.5.2 Detecting Imperfect Training Data -- 10.5.3 Preventing Label Propagation from Imperfect Training Data -- 10.5.4 Definition of the Modified Learning System to Withstand Imperfect Data -- 10.5.5 Parameter Sensitivity Analysis -- 10.5.5.1 Impact of α -- 10.5.5.2 Impact of τ -- 10.5.6 Computer Simulations -- 10.5.6.1 Synthetic Data Sets -- 10.5.6.2 Real-World Data Sets -- 10.6 Chapter Remarks -- References -- Index.

Note: Literaturverzeichnis: Seite 17-19

Note: Literaturverzeichnis: Seite 12-14