Computational Science – ICCS 2021: 21st International Conference, Krakow, Poland, June 16–18, 2021, Proceedings, Part I (Theoretical Computer Science and General Issues)

The six-volume set LNCS 12742, 12743, 12744, 12745, 12746, and 12747 constitutes the proceedings of the 21st International Conference on Computational Science, ICCS 2021, held in Krakow, Poland, in June 2021.* The total of 260 full papers and 57 short papers presented in this book set were carefully reviewed and selected from 635 submissions. 48 full and 14 short papers were accepted to the main track from 156 submissions; 212 full and 43 short papers were accepted to the workshops/ thematic tracks from 479 submissions. The papers were organized in topical sections named: Part I: ICCS Main Track Part II: Advances in High-Performance Computational Earth Sciences: Applications and Frameworks; Applications of Computational Methods in Artificial Intelligence and Machine Learning; Artificial Intelligence and High-Performance Computing for Advanced Simulations; Biomedical and Bioinformatics Challenges for Computer Science Part III: Classifier Learning from Difficult Data; Computational Analysis of Complex Social Systems; Computational Collective Intelligence; Computational Health Part IV: Computational Methods for Emerging Problems in (dis-)Information Analysis; Computational Methods in Smart Agriculture; Computational Optimization, Modelling and Simulation; Computational Science in IoT and Smart Systems Part V: Computer Graphics, Image Processing and Artificial Intelligence; Data-Driven Computational Sciences; Machine Learning and Data Assimilation for Dynamical Systems; MeshFree Methods and Radial Basis Functions in Computational Sciences; Multiscale Modelling and Simulation Part VI: Quantum Computing Workshop; Simulations of Flow and Transport: Modeling, Algorithms and Computation; Smart Systems: Bringing Together Computer Vision, Sensor Networks and Machine Learning; Software Engineering for Computational Science; Solving Problems with Uncertainty; Teaching Computational Science; Uncertainty Quantification for Computational Models *The conference was held virtually. Chapter “Deep Learning Driven Self-adaptive hp Finite Element Method” is available open access under a Creative Commons Attribution 4.0 International License via link.springer.com. Preface Organization Contents – Part I ICCS 2021 Main Track Smoothing Speed Variability in Age-Friendly Urban Traffic Management 1 Introduction 2 Related Work 3 System Model 4 CoMAAPRAS 4.1 Update Road Pheromone 4.2 Collaborative Decision Making 5 Experiment Design 6 Results 6.1 Speed Variability 6.2 Waiting Time 6.3 Fuel Consumption 6.4 Travel Time 7 Conclusions References An Innovative Employment of the NetLogo AIDS Model in Developing a New Chain Code for Compression 1 Introduction 2 Method 3 Results 4 Discussion and Conclusion References Simulation Modeling of Epidemic Risk in Supermarkets: Investigating the Impact of Social Distancing and Checkout Zone Design 1 Introduction 2 Modeling Infection Transmission 3 Simulation Setup 4 Results 5 Conclusions References A Multi-cell Cellular Automata Model of Traffic Flow with Emergency Vehicles: Effect of a Corridor of Life 1 Introduction 2 Proposed Model 2.1 Road Structure, Types of Vehicles and Real Data 2.2 The Corridor of Life 2.3 Safe Distance Between Cars and the Friction Conflict 2.4 The Rules of Traffic Movement 3 Results 4 Conclusions References HSLF: HTTP Header Sequence Based LSH Fingerprints for Application Traffic Classification 1 Introduction 2 Background and Related Work 2.1 Traffic Classification Solutions 2.2 Research on HTTP Headers 3 Preprocessing 3.1 Weight Assignment 3.2 HTTP Header Sequence 4 HTTP Header Sequence Based LSH Fingerprints 4.1 LSH Fingerprint 4.2 Fingerprint Database 4.3 Application Identification 5 Experiments 5.1 Dataset 5.2 Multi-class Classification Performance 5.3 Compared with Classic Machine Learning Models 5.4 Comparison with Other Approaches 6 Conclusion References Music Genre Classification: Looking for the Perfect Network 1 Introduction 1.1 Related Work 1.2 Contribution and Paper Structure 2 Deep Learning Models 2.1 Convolutional Neural Network 2.2 1-Dimensional Convolutional Recurrent Neural Network 2.3 2-Dimensional Convolutional Recurrent Neural Network 2.4 Recurrent Neural Network with Long Short-Term Memory Cells (LSTM) 2.5 Ensembles 3 Experiments 3.1 Dataset and Hardware Setup 3.2 Additional Settings 3.3 Quantitative Results 3.4 Qualitative Results 3.5 Comparison of the Outcomes 4 Conclusions References Big Data for National Security in the Era of COVID-19 1 Introduction 2 COVID-19 and National Security 3 An Overview of the Framework 3.1 Event Polarisation and Early Warning Alert (Q1) 3.2 Radical Behaviour (Q2, Q3 and Q4) 3.3 Ideology (Q5) 3.4 Web Insights (Q6) 4 Analysing Two COVID-19 Disruptive Events 4.1 Data Collection and Cleansing 4.2 Early Warning Alert (Q1) 4.3 Radical Behaviour (Q2, Q3 and Q4) 4.4 Ideology (Q5) 4.5 Web Insights (Q6) 5 Conclusions References Efficient Prediction of Spatio-Temporal Events on the Example of the Availability of Vehicles Rented per Minute 1 Introduction 1.1 Contribution 2 Related Work 3 Model and Problem Definition 4 Dataset 4.1 Performance Measures 5 Results 6 Conclusion References Grouped Multi-Layer Echo State Networks with Self-Normalizing Activations 1 Introduction 2 ESN Architectures 2.1 Shallow Echo State Network 2.2 Self-Normalizing Activation Function on Hyper-Sphere 2.3 Grouped Deep Echo State Network 3 AutoESN Library 4 Results 5 Conclusion References SGAIN, WSGAIN-CP and WSGAIN-GP: Novel GAN Methods for Missing Data Imputation 1 Introduction 2 Imputation Methods Based on GAN 3 Novel Generative Imputation Methods 3.1 Notation and Problem Formulation 3.2 Slim GAIN 3.3 Wasserstein Slim GAIN with Clipping Penalty 3.4 Wasserstein Slim GAIN with Gradient Penalty 4 Experimental Results 4.1 Response Times 4.2 RMSE Performance 4.3 AUROC Performance 5 Conclusions References Deep Learning Driven Self-adaptive Hp Finite Element Method 1 Introduction 2 Self-adaptive hp-FEM with Neural Network 3 Conclusions References Machine-Learning Based Prediction of Multiple Types of Network Traffic 1 Introduction 2 Related Work 3 Data Analysis 4 Proposed Models and Algorithms 5 Numerical Experiments 6 Conclusions and Future Work References Scalable Handwritten Text Recognition System for Lexicographic Sources of Under-Resourced Languages and Alphabets 1 Introduction 2 Related Work 3 Data 3.1 Original Data 3.2 Synthetic Data for Training 3.3 Manually Labelled Subsets 4 Methodological Workflow 4.1 Detection of the Index Word 4.2 Recognition 4.3 Transfer Learning 4.4 Postprocessing 5 Application 6 Results 7 Discussion 8 Conclusion References Out-Plant Milk-Run-Driven Mission Planning Subject to Dynamic Changes of Date and Place Delivery 1 Introduction 2 Literature Review 3 An Ordered Fuzzy Numbers Framework 4 Problem Formulation 5 OFN-Based Constraint Satisfaction Problem 6 Dynamic Mission Planning 7 Computational Experiments 8 Conclusions References An Efficient Hybrid Planning Framework for In-Station Train Dispatching 1 Introduction 2 The In-Station Train Dispatching Problem 3 Description of the Framework 3.1 Preprocessor 3.2 Optimised Planning Engine 3.3 Visualisation Tool 4 Experimental Analysis 5 Related Work and Conclusions References Evaluating Energy-Aware Scheduling Algorithms for I/O-Intensive Scientific Workflows 1 Introduction 2 Background 2.1 Scientific Workflows 2.2 Power and Energy Consumption 3 Analysis of Energy-Aware Workflow Scheduling Algorithms 3.1 SPSS-EB 3.2 EnReal 3.3 Workflow Energy Consumption Analysis 4 Energy-Aware Scheduling of I/O-Intensive Workflows 4.1 I/O- and Energy-Aware Scheduling 4.2 Experimental Evaluation 5 Related Work 6 Conclusion and Future Work References A Job Shop Scheduling Problem with Due Dates Under Conditions of Uncertainty 1 Introduction 2 Problem Formulation 3 Uncertainty 4 Computational Experiments 5 Summary References New Variants of SDLS Algorithm for LABS Problem Dedicated to GPGPU Architectures 1 Introduction 2 New Variants of SDLS Search Algorithms for LABS 2.1 The SDLS-2 Algorithm with Extended Neighbourhood 2.2 Sequential Version of the SDLS-DT Algorithm 2.3 Parallel Version of SDLS-DT for GPGPU 3 Effectiveness of the Proposed Algorithms 4 Conclusions and Further Work References Highly Effective GPU Realization of Discrete Wavelet Transform for Big-Data Problems 1 Introduction 2 Calculation of One-Dimensional DWT 2.1 Calculations Based on the Convolution 2.2 Calculations Based on the Lattice Structure 3 The Proposed Lattice Structure 4 Experimental Analysis 5 Conclusions References A Dynamic Replication Approach for Monte Carlo Photon Transport on Heterogeneous Architectures 1 Introduction 2 Background 3 Related Works 4 Our Method 4.1 Step 1: Assignment 4.2 Step 2: Distribution 4.3 Step 3: Mapping 5 Experiment Overview 5.1 Hardware and Software 5.2 Experimental Factors 5.3 Measurements 6 Results 6.1 Algorithm Performance 6.2 Load Balance Efficiency 6.3 Surge Capability 7 Conclusion References Scientific Workflow Management on Hybrid Clouds with Cloud Bursting and Transparent Data Access 1 Introduction 2 Related Work 3 Cloud Bursting Solution for Scientific Workflows 3.1 Architecture 3.2 Workflow Partitioning 4 Evaluation 4.1 Workflow Partitioning Analysis 4.2 Experimental Runs 4.3 Discussion 5 Conclusions and Future Work References Scaling Simulation of Continuous Urban Traffic Model for High Performance Computing System 1 Introduction 2 Scalable Traffic Simulations 3 Towards HPC-Grade Traffic Simulation 3.1 Initialization of the Simulation 3.2 Data Scalability 3.3 Massive Parallelism Issues 3.4 Simulation Results Processing 4 Evaluation of Traffic Simulation Scalability 4.1 Strong Scalability 4.2 Weak Scalability 5 Conclusions and Further Work References A Semi-supervised Approach for Trajectory Segmentation to Identify Different Moisture Processes in the Atmosphere 1 Introduction 2 Background 2.1 Trajectory Clustering 2.2 Research Data 3 Experimental Evaluation 4 Discussion 5 Conclusion References mRelief: A Reward Penalty Based Feature Subset Selection Considering Data Overlapping Problem 1 Introduction 2 Preliminaries 2.1 Relief 2.2 ReliefF 2.3 SURF and SURF* 2.4 MultiSURF* and MultiSURF 3 Modified Relief (mRelief) 3.1 Candidate Feature Selection 3.2 Final Feature Subset Selection 3.3 An Illustrative Example 4 Result Analysis and Discussions 4.1 Dataset Description 4.2 Implementation Detail 4.3 Comparison of mRelief with the State-of-the-Art Methods 5 Conclusion References Reconstruction of Long-Lived Particles in LHCb CERN Project by Data Analysis and Computational Intelligence Methods 1 Introduction 2 Long-Lived Particles in LHCb 3 Proposed Approach 3.1 Initial Stage 3.2 Online Stage 3.3 Calibration Stage 4 Evaluation Criteria and Preliminary Results 5 Final Comments References Motion Trajectory Grouping for Human Head Gestures Related to Facial Expressions 1 Introduction 2 Related Works 3 Proposed Approach 3.1 Head Gestures 3.2 Rigid Head Model 4 Rotation Trajectories Analysis 4.1 Ranges of Rotation Angles 4.2 Trajectories Similarity 4.3 Trajectories Grouping 4.4 Final Rotation of the Head 5 Conclusions References DenLAC: Density Levels Aggregation Clustering – A Flexible Clustering Method – 1 Introduction 2 Related Work 3 Methodology 3.1 DENCLUE (DENsity-Based CLUstEring) Algorithm 3.2 Clusters as Connected Components at Different Density Levels 3.3 Clusters as Adjacent Density Bins 4 Algorithm Pipeline 4.1 Density Estimation. Outlier Identification and Displacement 4.2 Density Based Partitioning 4.3 Splitting the Density Bins into Distinct Connected Components 4.4 Merging the Adjacent Connected Components 5 Algorithm 5.1 Choosing the Hyperparameters 5.2 Implementation 6 Experimental Results 6.1 Clustering Evaluation Methods 6.2 Evaluation Results 7 Conclusions References Acceleration of the Robust Newton Method by the Use of the S-iteration 1 Introduction 2 The Robust Newton's Method 3 The Robust Newton's Method with the S-iteration 4 Experiments 5 Conclusions References A New Approach to Eliminate Rank Reversal in the MCDA Problems 1 Introduction 2 Methods 2.1 The PROMETHEE II Method 2.2 The TOPSIS Method 2.3 The COMET Method 2.4 Similarity Coefficients 2.5 Entropy Weighting Method 3 The Proposed Approaches 3.1 Rank Reversal - Exemplary Study Case 3.2 Effectiveness 4 Conclusions References Validating Optimal COVID-19 Vaccine Distribution Models 1 Introduction 2 Related Work 3 Methodology 3.1 Selection of Optimal Vaccine Distribution Center 3.2 System Model for Vaccine Distribution 3.3 Problem Formulation 3.4 Variations of Vaccine Distribution Models 4 Case Study - Chennai, India 4.1 Clustering Phase 4.2 Vaccine-Distribution Phase 5 Results and Discussion 5.1 Random-Simulation 5.2 Case-Study Simulation 6 Conclusion and Future Work References RNACache: Fast Mapping of RNA-Seq Reads to Transcriptomes Using MinHashing 1 Introduction 2 Method 2.1 Database Construction 2.2 Querying and Initial Read Assignment 2.3 Online Filtering 2.4 Post-processing (Coverage) Filter 2.5 Parallelization 3 Evaluation 3.1 Accuracy Evaluation Using Simulated Reads 3.2 Runtime and Parallel Scalability 3.3 Evaluation Using Experimental Data 4 Conclusion References Digital Image Reduction for Analysis of Topological Changes in Pore Space During Chemical Dissolution 1 Introduction 2 Digital Images 3 Edelsbrunner Algorithm 4 Reduction Algorithm 5 Numerical Experiments 5.1 Statistical Models 5.2 Pore-Scale Dissolution by CO2 Saturated Brine in a Multi-mineral Carbonate at Reservoir Conditions 6 Conclusion References Oil and Gas Reservoirs Parameters Analysis Using Mixed Learning of Bayesian Networks 1 Introduction 2 Related Work 3 Problem Statement 4 Algorithms and Methods 4.1 MixLearn@BN: Algorithm for Mixed Learning of Bayesian Networks 4.2 Reducing the Training Samples Using Similarity Detection 4.3 Method for Parameters Restoration with Bayesian Networks Learning on Analogues 5 Experiments and Results 5.1 Exploratory Data Analysis with Bayesian Networks 5.2 Bayesian Networks Application Experiments 6 Conclusion References Analytic and Numerical Solutions of Space-Time Fractional Diffusion Wave Equations with Different Fractional Order 1 Introduction 2 Preliminaries 3 Finite Difference Approximation 4 Stability and Convergence 5 Numerical Results 6 Conclusion References Chebyshev-Type Rational Approximations of the One-Way Helmholtz Equation for Solving a Class of Wave Propagation Problems 1 Introduction 2 Problem Statement 3 Approximation of the Propagator 3.1 Padé approximation 3.2 Rational Approximation on an Interval 4 Numerical Results and Discussion 4.1 Radio-Wave Propagation 4.2 Propagation in a Shallow Water 4.3 Analysis of the Computational Grid Density 5 Conclusion References Investigating In Situ Reduction via Lagrangian Representations for Cosmology and Seismology Applications 1 Introduction 2 Background and Related Work 2.1 Frames of Reference 2.2 Lagrangian Analysis 2.3 Time-Varying Vector Field Reduction 3 In Situ Reduction via Lagrangian Representations 4 Study Overview 4.1 Runtime Environment 4.2 Simulation Codes 4.3 Experiments 4.4 Evaluation Metrics 5 Results 5.1 Nyx Cosmology Simulation 5.2 SW4 Seismology Simulation 6 Conclusion References Revolve-Based Adjoint Checkpointing for Multistage Time Integration 1 Introduction 2 Revisiting Optimality of Classic Checkpointing Strategy for Multistage Methods 3 Modified Offline Checkpointing Scheme 4 Using Revolve in the discrete adjoint calculation 5 Algorithm Performance 6 Conclusion References Comprehensive Regularization of PIES for Problems Modeled by 2D Laplace’s Equation 1 Introduction 2 The Singular Formulation of the PIES 3 Elimination of Singularities from PIES Through the Regularization 4 Numerical Implementation 5 Verification of the Approach 5.1 Example 1 5.2 Example 2 6 Conclusions References High Resolution TVD Scheme Based on Fuzzy Modifiers for Shallow-Water Equations 1 Introduction 2 Numerical Model: One-Dimensional Shallow Water Flows 3 Numerical Approach: Flux Limiting High Resolution Schemes 4 Development of the New Flux Limiter Scheme 5 Numerical Validation: Using Dam Break Problem 5.1 Dam Break 5.2 CPU Time 6 Conclusion References PIES for Viscoelastic Analysis 1 Introduction 2 PIES for Viscoelastic Problems 2.1 Basic Relations for Kelvin Model 2.2 PIES Formula 3 Shape Modeling 4 Solving Procedure 5 Examples 6 Conclusions References Fast and Accurate Determination of Graph Node Connectivity Leveraging Approximate Methods 1 Introduction 2 Related Work 3 Faster Computation of Graph Node Connectivity 4 Implementation 5 Results 5.1 Random Graphs 5.2 Social Network Example 5.3 Dependence on Choice of Starting Node 5.4 Worst-Case Performance 6 Discussion References An Exact Algorithm for Finite Metric Space Embedding into a Euclidean Space When the Dimension of the Space Is Not Known 1 Introduction 2 The Euclidean Distance Matrix Problem and Euclidean Distance Geometry Problem. 3 An Exact Incremental Algorithm for Embedding a Complete Weighted Graph in the Euclidean Space 3.1 Algorithm of the Euclidean Embedding of a 3-vertex Structure 3.2 General Location Algorithm 4 Computational Experiments 5 Concluding Remarks References Resolving Policy Conflicts for Cross-Domain Access Control: A Double Auction Approach 1 Introduction 2 Related Work 2.1 Conflict Resolution Within a Singleparty 2.2 Conflict Resolution Among Multiparty 3 Problem Statement and Basic Idea 3.1 Cross-Domain Policy Mapping in RBAC 3.2 Conflicts Induced by Policy Mapping 3.3 Basic Idea for Conflict Resolution 4 Cost and Value in Conflict Resolution 4.1 Influencing Factors 4.2 Seller's Cost 4.3 Buyer's Value 5 Double Auction Game and Its Analysis 5.1 Double Auction with Incomplete Information 5.2 Bayesian Nash Equilibrium 6 Experiment Evaluation 7 Conclusion References An Adaptive Network Model for Procrastination Behaviour Including Self-regulation and Emotion Regulation 1 Introduction 2 Background Knowledge 3 The Modeling Approach Used 4 The Designed Adaptive Network Model 5 Experimental Setup 6 Results of the Simulation Experiments 7 Verification by Analysis of Stationary Points 8 Conclusion and Future Research References Improved Lower Bounds for the Cyclic Bandwidth Problem 1 Introduction 2 Graph Density Lower Bounds 3 Cycle Basis Lower Bound 4 Applying Our Results on 28 Harwell-Boeing Instances 5 Conclusion and Open Questions References Co-evolution of Knowledge Diffusion and Absorption: A Simulation-Based Analysis 1 Introduction 2 Background and Motivation 2.1 Networking Structure and Interactions 2.2 Diffusion and Absorption of Knowledge 2.3 Contribution of the Paper 3 Conceptual Model 4 Agent-Based Model 5 Simulation 5.1 Simulation Setup 5.2 Simulation Results 6 Conclusion References Estimation of Road Lighting Power Efficiency Using Graph-Controlled Spatial Data Interpretation 1 Introduction 2 Determinants of Street Lighting Design and Efficiency 3 Modelling and Interpretation of Spatial Relationships 3.1 Graph Representation and Generation 3.2 Graph Generation Using a Formal Grammar 3.3 Relation to Previous Results 4 Energy Requirement Estimation of Outdoor Lighting 5 Conclusions References Embedding Alignment Methods in Dynamic Networks 1 Introduction 2 Related Works 3 Graph Embedding Alignment 3.1 Notation and Problem Statement 3.2 The Importance of Embedding Alignment 3.3 Alignment Performance Measures 3.4 Dynamic Graph Embedding Alignment Methods 4 Experiments 4.1 Datasets 4.2 Node Embeddings 4.3 Embedding Aggregation 4.4 Embedding Alignment 4.5 Link Prediction 4.6 Graph Reconstruction 4.7 Impact of the Node Fraction Taken in the Alignment Process 4.8 Embedding Alignment Performance Metrics 5 Conclusions and Future Work References The OpenPME Problem Solving Environment for Numerical Simulations 1 Introduction 2 Background and Motivation 2.1 Hybrid Particle-Mesh Simulations 2.2 The OpenFPM Library 2.3 Motivation 3 OpenPME Design and Implementation 3.1 Design Overview 3.2 Metamodel for Particle-Mesh Simulations 3.3 OpenPME DSL Syntax 3.4 Metamodel for OpenFPM C++ 3.5 Model-to-model Transformation and Code Generation 4 Evaluation 4.1 Lennard-Jones: Particles-Only Simulation of a Discrete Model 4.2 Gray-Scott: Mesh-Only Simulation of a Continuous Model 4.3 Vortex-in-Cell: Hybrid Particle-Mesh Simulation of a Continuous Model 5 Related Work 6 Conclusions and Future Work References Building a Prototype for Easy to Use Collaborative Immersive Analytics 1 Introduction 2 Literature Review 2.1 Collaboration in Immersive Environments 2.2 Immersive Analytics Frameworks 2.3 Related Work 3 Proposed Solution 3.1 Technology Choices 3.2 System Architecture 4 Implementation 5 Prototype Testing 6 Conclusion and Future Work References Implementation of Auditable Blockchain Voting System with Hyperledger Fabric 1 Introduction 2 Electronic Voting and Blockchain in Hyperledger Fabric 3 Related Works 4 Auditable Blockchain Voting System with Hyperledger Fabric 4.1 Auditable Blockchain Voting System Overview 4.2 Auditable Blockchain Voting System Network 4.3 Auditable Blockchain Voting System Smart Contracts 4.4 Auditable Blockchain Voting System Security Components 5 Property Analysis 6 Conclusions References Quantum Data Hub: A Collaborative Data and Analysis Platform for Quantum Material Science 1 Introduction 2 Quantum Material Research Process and Data Model 2.1 Quantum Material Research Process 2.2 Example: Powder Synthesis and Measurement Process 2.3 The Quantum Foundry Data Model 3 Quantum Data Hub Architecture 4 Related Work 5 Conclusions Ad Future Work References Hierarchical Analysis of Halo Center in Cosmology 1 Introduction 2 Method 3 Error Bounds and Complexity Analysis 4 Numerical Results 4.1 2D Result 4.2 3D Result 5 Conclusion and Future Work References Fast Click-Through Rate Estimation Using Data Aggregates 1 Introduction 2 State of the Art 3 Research Goals and Approach 4 Modelling Overview 4.1 Feature Encoding 4.2 Aggregate Encoding 5 Experiments and Results 5.1 Experiment Setup 5.2 Results 6 Conclusions and Future Work References A Model for Predicting n-gram Frequency Distribution in Large Corpora 1 Introduction 2 Background 3 The Model 3.1 Wz(k): The Size of the Frequency Levels from Zipf's Law 3.2 An Analytical Model for the Dependence of on Corpus Size 3.3 W*(k,C): The Dependence of Level Size on Corpus Size 4 Results and Discussion 4.1 The Poisson-Zipf Model 4.2 Comparison of Results 5 Conclusions References Exploiting Extensive External Information for Event Detection Through Semantic Networks Word Representation and Attention Map 1 Introduction 2 Related Works 3 Method 4 Experiment 5 Conclusion References A New Consistency Coefficient in the Multi-criteria Decision Analysis Domain 1 Introduction 2 Matrix of Expert Judgment (MEJ) 3 Consistency Coefficient 3.1 Triads Analysis 3.2 Consistency Coefficient 4 Consistency Coefficient - Study Cases 5 Conclusions References Predicting the Age of Scientific Papers 1 Introduction 2 Datasets 3 Method 3.1 Predicting Sentence Age 3.2 Predicting Document Age 4 Results 5 Conclusions and Future Work References Data Augmentation for Copy-Mechanism in Dialogue State Tracking 1 Introduction 2 Related Works 2.1 Dialogue State Tracking 2.2 Copy-Mechanism 3 Datasets, Baseline Model and Evaluation 3.1 Datasets 3.2 Baseline Model 3.3 Evaluation Metric 4 Data Analysis and Observations 4.1 Original Datasets May Mislead the Model 4.2 Greater Diversity of Values Brings Better Generalization 4.3 Random Strings Also Work Well 5 Interactive Data Augmentation for DST 5.1 Approach 5.2 Performance 5.3 Hyperparametric Analysis 6 Conclusion and Future Work References Ensemble Labeling Towards Scientific Information Extraction (ELSIE) 1 Introduction 2 Motivation 3 Related Work 4 Architecture 4.1 Input Dataset 4.2 The Snorkel System and Its Built-In Functionalities 4.3 Majority Ensemble Labeler and ELSIE 5 Results and Analysis 5.1 Training Dataset and Its Labels 5.2 Updated Gold Standard Labels 5.3 Results 5.4 Analysis 6 Conclusion References Error Estimation and Correction Using the Forward CENA Method 1 Introduction 2 Related Work 3 Brief Introduction to AD 4 Forward CENA Method 5 Implementation 6 Test Cases and Experimental Results 6.1 Sum Reduction 6.2 HACCmk 6.3 Classic and Strassen Matrix Multiplication 6.4 Muller Recurrence 7 Conclusions References Monte Carlo Approach to the Computational Capacities Analysis of the Computing Continuum 1 Introduction 2 Related Work and Definitions 2.1 Computing Continuum 2.2 Computational Network with Scale-Free Topology 2.3 Modelling Congested States of the Computing Continuum Through Phase Transitions 3 Mathematical Model 3.1 Workload Model 3.2 Agent Model 3.3 Network Model 3.4 Order Parameter of the Computational Network 3.5 Network Bandwidth Model 3.6 Communication and Computation in the Network 4 Experimental Study 4.1 Monte Carlo Simulation of the Computational Network 4.2 Implementation Details 4.3 Numerical Results and Discussion 5 Discussion and Future Work References Author Index