Towards Digital Intelligence Society: A Knowledge-based Approach

✍ Scribed by Jan Paralic, Peter Sinčák, Pitoyo Hartono, Vladimir Mařík

• Publisher: Springer
• Year: 2021
• Tongue: English
• Leaves: 212
• Series: Advances In Intelligent Systems And Computing
• Edition: 1st Edition
• Category: Library

✦ Synopsis

This book aims to provide readers with up-to-date knowledge on how to make these technologies smarter. Humanity is now going through difficult times to fight the Covid-19 pandemic. Simultaneously, in these difficult times of physical separation, we can also realize how much digital society technology helps us cope with many difficulties that bring us this time. The authors focus on selected research challenges for intelligent digital society and state-of-the-art methods of how to face them. The book’s subtitle suggests that a core concept that the reader can study from various points of view in particular book chapters is the knowledge. The knowledge that can help us intelligently face different digital society challenges (Part I of this book); the knowledge extracted from available big data employing intelligent analysis techniques (Part II). For efficient processing and analysis of data, there is a strong need for smart data and information modeling techniques (Part III).

✦ Table of Contents

Preface......Page 6
Program Committee......Page 9
Contents......Page 11
Digital Intelligence: Selected Research Challenges......Page 13
Addressing False Information and Abusive Language in Digital Space Using Intelligent Approaches......Page 14
2.1 Definitions and Categorisation......Page 15
2.2 State-of-the-Art Solutions, Challenges, and Open Problems......Page 17
2.3 Characterisation of Fake News by Their Hyperlink Network......Page 20
2.4 Detection of Fake News with Deep Learning......Page 21
2.5 Detection of Users Susceptible to Spread Fake News......Page 24
2.6 Detection of Fake Reviews......Page 26
3.1 Definitions and Categorisation......Page 27
3.2 State-of-the-Art Solutions, Challenges, and Open Problems......Page 29
3.3 Detection of Abusive Language with Deep Learning......Page 30
4.1 Related Work......Page 31
4.2 Methodology and Features Extraction......Page 32
4.3 Preliminary Results......Page 34
5 Discussion and Conclusions......Page 37
References......Page 38
1 Introduction......Page 44
2 Convolutional Neural Networks......Page 45
3.1 2D Classification......Page 46
3.2 3D Classification......Page 47
4.1 Semantic Segmentation......Page 49
4.2 Instance Segmentation......Page 50
4.3 Advanced Modifications for Feature Extraction......Page 51
5.1 Reinforcement Learning in Computer Games......Page 52
5.2 Reinforcement Learning for Object Detection......Page 53
5.3 Reinforcement Learning in Robotics......Page 54
6.1 Hallucination-Based Methods......Page 55
6.2 Meta-Learning......Page 56
7 Explainability......Page 59
7.1 Backpropagation-Based Methods......Page 60
7.2 Perturbation-Based Methods......Page 61
References......Page 62
1 Introduction......Page 70
2 Exoskeletons......Page 71
3 Obstacle Detection......Page 73
3.2 Implementation......Page 74
4.1 Testing the Depth Camera......Page 77
4.2 Testing the LIDAR Module......Page 78
4.3 Testing the Up2......Page 79
5 Conclusion......Page 80
References......Page 81
Intelligent Analysis of Big Data......Page 83
1 Introduction......Page 84
2.1 The Data Analytics Processes......Page 85
2.2 Semantic Modelling of Data Analytical Processes......Page 87
2.3 Technologies for the Semantic Description of Data-Analytical Processes......Page 88
3.1 Doman Concepts......Page 90
3.2 Key Performance Indicators and Data Elements......Page 91
3.3 Algorithms and Data-Analytical Models......Page 92
3.4 The Process Model for Data Analytical Workflows......Page 93
4.1 Process Industries Use Case......Page 94
4.2 Network Intrusion Detection Use Case......Page 97
5.1 Knowledge Extraction and Use in Medical Analysis......Page 100
5.2 Metabolic Syndrome Diagnostics......Page 102
5.3 Cardiovascular Risk Assessment......Page 103
References......Page 104
1 Introduction......Page 107
2 Stream Mining......Page 109
3 Stream Forecasting......Page 110
3.1 Power Demand Forecasting......Page 111
3.2 Power Production Forecasting......Page 114
4.1 Optimization Process and Open Issues......Page 115
4.2 Optimization Methods......Page 116
4.4 Microgrid Optimization Problems......Page 117
5 Conclusion......Page 120
References......Page 121
Large Astronomical Time Series Pre-processing for Classification Using Artificial Neural Networks......Page 126
1.1 Types of Stars Variability......Page 127
2 State of the Art......Page 128
2.1 Time Series Classification Methods......Page 129
3 Data Sets......Page 135
3.2 Kepler K2......Page 136
4.1 Data Pre-processing......Page 138
5.1 BRITE Data Set......Page 139
5.2 Kepler K2 Data Set......Page 140
6 Conclusions......Page 150
References......Page 151
Data and Information Modelling......Page 154
1 Introduction......Page 155
2 Requirements on Information Modelling and Information Exchange......Page 156
3 Information Models and Formats for Information Exchange......Page 158
3.1 Information Modeling......Page 159
3.2 Formats for Information Exchange......Page 160
3.3 Formats for Information Modelling......Page 161
4 Demonstration......Page 163
5 Discussion and Conclusions......Page 165
References......Page 166
1 Introduction......Page 168
2 Attribute Exploration and Partial Attribute Implications......Page 170
3 Example of Attribute Exploration......Page 178
4 Measuring of Pupils' Computational Thinking......Page 182
5 Conclusion......Page 186
References......Page 187
1 Introduction......Page 189
2 Database System Architecture, Instance......Page 191
2.1 Background Processes......Page 193
3 Indexes......Page 194
4.1 State of the Art......Page 196
4.2 Own Proposed Solution – Flower Index on Block Granularity......Page 197
4.3 Physical Implementation of the Sharedtableblockstorage Structure......Page 199
4.4 Rebalancer......Page 200
5 JOIN – Linking Data Across the Tables......Page 201
6 Table Joining – Mapping Index......Page 202
7 Performance Evaluations......Page 203
7.1 Select Statement Performance......Page 204
7.2 Destructive DML Statement Performance......Page 205
7.3 Size Demands......Page 206
7.4 Table Joining Performance......Page 207
8 Conclusions......Page 208
References......Page 209
Author Index......Page 211

✦ Subjects

Computational Intelligence