Databases Theory and Applications: 33rd Australasian Database Conference, ADC 2022, Sydney, NSW, Australia, September 2–4, 2022, Proceedings (Lecture Notes in Computer Science, 13459)

This book constitutes the refereed proceedings of the 33rd International Conference on Databases Theory and Applications, ADC 2022, held in Sydney, Australia, in September 2022. The conference is co-located with the 48th International Conference on Very Large Data Bases, VLDB 2022. The 9 full papers presented together with 8 short papers were carefully reviewed and selected from 36 submissions. ADC focuses on database systems, data-driven applications, and data analytics. Preface General Chair’s Welcome Message Organization Contents Invited Papers On International Chinese Education Index Ranking in a Global Perspective 1 Introduction 2 Related Work 2.1 Assessment of ICE 2.2 Assessment Methods 3 Dataset and Preprocessing 3.1 Data Sources and Choice of Indicators 3.2 Data Preprocessing 4 Results 5 Impact of the Number of Tourists and Foreign Direct Investments on ICE Ranking 6 Conclusions and Further Discussions References Multi-objective Social Network Detection - A Graph Database Supported NSGA-II Based Approach 1 Introduction 2 Related Work 3 Preliminaries 4 Graph Database-Supported NSGA-II Approach 5 Experimental Evaluation 6 Conclusions References Full Research Papers A Top-Down Scheme for Coverage Centrality Queries on Road Networks 1 Introduction 2 Related Work 2.1 Coverage Centrality 2.2 Betweenness Centrality 2.3 Shortest Path Algorithms 3 Algorithm 3.1 Framework 3.2 Intra-region Pruning 3.3 Inter-region Pruning 4 Experiments 4.1 Experiment Setting 4.2 Experimental Results 5 Conclusion References Personalized Arrhythmia Detection Based on Lightweight Autoencoder and Variational Autoencoder 1 Introduction 2 Relate Work 2.1 Arrhythmia Detection 2.2 Anomaly Detection 3 Our Proposed Methodology 3.1 Problem Definition 3.2 Encoder and Decoder 3.3 PerAD 4 Experiment and Discussion 4.1 Experimental Environment and Dataset 4.2 Experiment 1: Test the Influence of the Number of Simulation Data on Training ShaAE 4.3 Experiment 2: Evaluate PerAD with Other Methods 5 Conclusion References Efficient kNN Join over Dynamic High-Dimensional Data 1 Introduction 2 Background 2.1 Problem Definition 2.2 Dynamic kNN Join 3 Related Work 4 HDR Tree 4.1 Principal Component Analysis 4.2 Structure of Tree 4.3 Construction 4.4 Search 5 Lazy Updates 6 Batch Updates 7 Deletion Optimization 8 Performance Evaluation 9 Conclusion References Diverse Shortest Paths in Game Maps: A Comparative User Study and Experiments 1 Introduction 2 Preliminaries 2.1 Problem Formulation 2.2 Related Work 3 Adapting Existing Techniques for Game Maps 4 User Study 5 Experiments 5.1 Settings 5.2 Evaluation Measures 5.3 Results 6 Conclusions and Future Work References Predicting Taxi Hotspots in Dynamic Conditions Using Graph Neural Network 1 Introduction 1.1 Motivation 2 Literature Review 3 Preliminaries 3.1 Road Network Graph 3.2 GNN and Message Passing 4 Problem Definition 5 Methodology: RL Based Hotspots (Sub-graphs) Selection Using GNN 5.1 Initial Influential Node Selection 5.2 Sub-graph Generation 5.3 Sub-graph Completion Criteria 6 Performance Analysis 6.1 Qualitative Evaluation 6.2 Quantitative Evaluation 6.3 Comparison with Other State of Art Methods 7 Conclusion References Analysing Big Brain Signal Data for Advanced Brain Computer Interface System 1 Introduction 2 Proposed Framework 3 Experimental Data 4 Results and Discussions 5 Conclusion References Hop-Constrained s-t Simple Path Enumeration in Large Uncertain Graphs 1 Introduction 2 Preliminary 3 Related Work 4 The Baseline Solution 5 Our Approach 5.1 Overview 5.2 Light-Weight Index for Pruning 5.3 UHC-s-t path Enumeration 6 Experimental Evaluation 7 Conclusion References Improving Eco-Friendly Routing Considering Detailed Mobility Profiles, Driving Behavior and Vehicle Type 1 Introduction 2 Preliminaries 2.1 Problem Formulation 2.2 Related Work 3 Methodology 3.1 Overview 3.2 VT-CPFM Fuel Consumption Model 3.3 Generating Detailed Mobility Profile 4 Experiments 4.1 Experimental Setup 4.2 Competitors 4.3 Results 5 Conclusions and Future Work References Real-Time Detection and Visualization of Traffic Conditions by Mining Twitter Data 1 Introduction 1.1 Motivation 1.2 Contributions 2 Literature Review 3 Proposed Approach 3.1 The Proposed Architecture 3.2 Data Collection 3.3 Data Preprocessing 3.4 Classification of Tweets 3.5 Named Entity Recognition 3.6 GeoCoding 3.7 Data Storage and Traffic Events Visualization 4 Results 4.1 Comparison with Related Studies 5 Future Work 6 Discussion and Conclusion References FluMA: An Intelligent Platform for Influenza Monitoring and Analysis 1 Introduction 2 System Overview 2.1 Data Preparation 2.2 Time Series Prediction 2.3 Data Visualisation 3 Conclusion References Short Research Papers Brain Data Mining Framework Involving Entropy Topography and Deep Learning 1 Introduction 2 Methodology of the Proposed Mining Framework 2.1 Pre-processing of the Raw Data 2.2 Topographic Image Generation of the Signal Segments 2.3 Deep Learning Based Model Training and Classification 3 Materials and Parameters for Performance Evaluation 4 Results of the Proposed Framework 4.1 Setup for Experimentation 4.2 Experimental Results of the Proposed Framework 5 Conclusion References Enhancing System Security by Intrusion Detection Using Deep Learning 1 Introduction 2 Related Work 3 Proposed Scheme 4 Results and Discussion 5 Conclusion References Challenges in Electroencephalography Data Processing Using Machine Learning Approaches 1 Introduction 2 Challenges in Identifying Brain Disorders 2.1 Challenges in EEG Data Recording 2.2 Challenges in EEG Signal Pre-processing 2.3 Challenges in EEG Classification 3 Discussion 4 Conclusion References Database States Exhibiting Tree Projection Necessity 1 Introduction 2 Terminology 2.1 Relational Databases and Operators 2.2 Tree and Cyclic Schemas 3 Constructing (k-1)-Complete k-Partite Graphs 4 The General Construction Theorem 5 Aring Database Schemas 6 Conclusions References Comparative Study of Transformer Models 1 Introduction 2 Models 2.1 BERT 2.2 XLNet 2.3 RoBERTa 2.4 ALBERT 2.5 DistilBERT 2.6 BART 2.7 ConvBERT 2.8 ELECTRA 2.9 Retrospective Reader 3 Methodology 3.1 Retro-Reader Based Question Answering System 3.2 Metrics 4 Results and Discussions 5 Conclusion 6 Future Work References Removing Performance Bottleneck of Timestamp Allocation in Two-Phase Locking Based Protocol 1 Introduction 1.1 Motivation 1.2 Problem 1.3 Contribution 2 Proposal 2.1 Thread-ID-Based Decentralization 2.2 Random-Number-Based Decentralization 2.3 Optimization: Increment ID in Commit Phase 3 Evaluation 3.1 Low-Contention Setting 3.2 High-Contention Setting 4 Related Work 5 Conclusion References Performance Prediction of Songs on Online Music Platforms 1 Introduction 2 Related Work 3 Proposed Approach 3.1 Data 3.2 Modelling 3.3 Predicting the Spotify Popularity Metric 4 Results 5 Conclusion References Author Index