Data Management Technologies and Applications: 8th International Conference, DATA 2019, Prague, Czech Republic, July 26–28, 2019, Revised Selected Papers ... Computer and Information Science Book 1255)

This book constitutes the thoroughly refereed proceedings of the 8th International Conference on Data Management Technologies and Applications, DATA 2019, held in Prague, Czech Republic, in July 2019. The 8 revised full papers were carefully reviewed and selected from 90 submissions. The papers deal with the following topics: decision support systems, data analytics, data and information quality, digital rights management, big data, knowledge management, ontology engineering, digital libraries, mobile databases, object-oriented database systems, and data integrity. Preface 6 Organization 7 Contents 11 Explainable and Transferrable Text Categorization 12 1 Introduction 12 2 State of the Art 13 2.1 Argument Mining 13 2.2 Text Categorization Approaches 15 2.3 Feature Assessment and Evaluation Metrics 18 3 Model 19 4 Implementation 21 5 Effectiveness Evaluation 22 5.1 General and Topic Specific Features for Argument Stance Recognition 22 5.2 Using C3 TFIDF-SVM for Article Triage 25 5.3 Using C3 TFIDF-SVM for German Language Offensive Language Detection 26 5.4 Using C3 TFIDF-SVM for Digital Assistant Intent Detection 26 6 Understandability Survey 28 7 Conclusions 29 7.1 About Topic Specific and General Terms as Features 29 7.2 About Flexible, Explainable and Robust Text Categorization 30 References 31 Dealing with Critical Issues in Emails: A Comparison of Approaches for Sentiment Analysis 34 1 Introduction 34 1.1 Problem Description 34 1.2 Research Questions 35 2 Methodology 36 2.1 Literature Analysis and Related Work 36 2.2 Implementation 36 2.3 Data Acquisition 36 2.4 Data Preprocessing 37 2.5 Feature Extraction and Selection 37 2.6 Sentiment Lexicon 38 3 Experiments and Results 39 3.1 Evaluation 39 3.2 Experiments and Results for the Sentiment Dictionary (A) and Feature Extraction (B) 40 3.3 Experiments and Results for the Deep Learning Approach as a Combination of Word Embeddings and CNN (C) 43 4 Summary and Future Work 45 References 45 Industry 4.0: Sensor Data Analysis Using Machine Learning 48 1 Introduction 48 2 Objectives 49 3 Initial Insights About Data 50 4 Data Preprocessing 53 4.1 Descriptive Statistics and Visualization 54 5 Predictive Analysis 58 5.1 Machine Learning Based Models 58 5.2 Data Aggregation 60 5.3 Imbalanced Data 61 5.4 Random Data Sampling 62 6 Evaluation 63 6.1 Overall Equipment Effectiveness 63 6.2 Testing of Machine Learning Models 65 7 Related Work 67 8 Conclusions and Future Work 68 References 68 Scalable Architecture, Storage and Visualization Approaches for Time Series Analysis Systems 70 1 Introduction 70 2 Approaches 72 2.1 Architecture 72 2.2 Time Series Storage 74 2.3 Annotation Storage 76 2.4 Time Series Visualization 77 2.5 Annotation Visualization 78 3 Implementation and Challenges 79 3.1 Data Model 80 3.2 Data Management 81 3.3 Architecture 82 3.4 Visualization 84 4 Evaluation 86 4.1 Performance Testing of Databases for Time Series Storage 86 4.2 Performance Testing of Monoglot vs Polyglot Architectures 88 5 Conclusion 90 References 90 Optimizing Steering of Roaming Traffic with A-number Billing Under a Rolling Horizon Policy 94 1 Introduction 94 2 Problem Description 96 2.1 Dataset 97 2.2 Demand Forecasting 98 2.3 Agreements 99 2.4 Analysis of Quality Metrics 100 3 A-number Steering Model with Call Quality 101 4 Results 102 5 Conclusion 104 References 105 A Web-Based Decision Support System for Quality Prediction in Manufacturing Using Ensemble of Regressor Chains 107 1 Introduction 107 2 Background and Methodology 108 2.1 Textile Manufacturing Processes 109 2.2 Rear Cover Manufacturing Processes 109 2.3 Ensemble of Regressor Chains 110 2.4 Decision Support System 111 3 Experimental Setup 112 3.1 Datasets 112 3.2 Outlier Detection 113 3.3 Feature Selection 115 3.4 Implementation and Analysis Methods 117 3.5 A Model-Driven DSS for Quality Prediction 117 4 Results 119 5 Conclusion 123 References 124 Farm Area Segmentation in Satellite Images Using DeepLabv3+ Neural Networks 126 1 Introduction 126 2 Dara Description 128 3 Methodology 129 3.1 Classification of Patches (ROIs) 129 3.2 Semantic Segmentation of Farm Area Using DeepLabv3+ 134 4 Experimental Results 136 4.1 Hand-Crafted Features and Classification Modelling Results 136 4.2 Transfer Learning Strategy Results 138 4.3 Semantic Segmentation of Farm Regions Results 139 5 Conclusions 142 References 143 About the Fairness of Database Performance Comparisons 147 1 Introduction 147 2 Principles of Neo4j 149 3 Related Work 149 4 Unfairness of Performance Comparisons 151 4.1 Scope of Comparison 151 4.2 Small Test Data Sets 152 4.3 Warm Start 152 4.4 Using Standard Configurations 152 4.5 Over-Tuning 153 4.6 Artificial Test Scenarios 153 4.7 Implementation Issues 154 4.8 Data Distribution 154 4.9 Evaluation 154 5 Performance Evaluation 154 5.1 Scenarios 155 5.2 Test Conditions 155 5.3 Impact of Indexes for the PATHS Scenario 155 5.4 Cold/Warm Start 157 5.5 Implementation Variants 157 5.6 Larger Cache Size 158 5.7 Different Implementations and Structures 159 5.8 Data Distribution 161 5.9 Differences in Traversal Scenarios 162 5.10 JDBC Configuration 162 6 Further Considerations About Data Structures 163 7 Some Thoughts About Improving Fairness 165 8 Conclusions 166 References 167 Author Index 168 Front Matter ....Pages i-xi Explainable and Transferrable Text Categorization (Tobias Eljasik-Swoboda, Felix Engel, Matthias Hemmje)....Pages 1-22 Dealing with Critical Issues in Emails: A Comparison of Approaches for Sentiment Analysis (Bernd Markscheffel, Markus Haberzettl)....Pages 23-36 Industry 4.0: Sensor Data Analysis Using Machine Learning (Nadeem Iftikhar, Finn Ebertsen Nordbjerg, Thorkil Baattrup-Andersen, Karsten Jeppesen)....Pages 37-58 Scalable Architecture, Storage and Visualization Approaches for Time Series Analysis Systems (Eduardo Duarte, Diogo Gomes, David Campos, Rui L. Aguiar)....Pages 59-82 Optimizing Steering of Roaming Traffic with A-number Billing Under a Rolling Horizon Policy (Ahmet Şahin, Kenan Cem Demirel, Ege Ceyhan, Erinc Albey)....Pages 83-95 A Web-Based Decision Support System for Quality Prediction in Manufacturing Using Ensemble of Regressor Chains (Kenan Cem Demirel, Ahmet Şahin, Erinc Albey)....Pages 96-114 Farm Area Segmentation in Satellite Images Using DeepLabv3+ Neural Networks (Sara Sharifzadeh, Jagati Tata, Hilda Sharifzadeh, Bo Tan)....Pages 115-135 About the Fairness of Database Performance Comparisons (Uwe Hohenstein, Martin Jergler)....Pages 136-156 Back Matter ....Pages 157-157