Advanced Data Mining and Applications 18th International Conference, ADMA 2022, Brisbane, QLD, Australia, November 28-30, 2022, Proceedings, Part I

The two-volume set LNAI 13725 and 13726 constitutes the proceedings of the 18th International Conference on Advanced Data Mining and Applications, ADMA 2022, which took place in Brisbane, Queensland, Australia, in November 2022. The 72 papers presented in the proceedings were carefully reviewed and...

Full description

Saved in:
Bibliographic Details
Main Authors Chen, Weitong, Yao, Lina, Cai, Taotao, Pan, Shirui, Shen, Tao, Li, Xue
Format eBook
LanguageEnglish
Published Cham Springer 2022
Springer Nature Switzerland
Edition1
SeriesLecture Notes in Computer Science
Subjects
Data mining
Data mining-Congresses
Online AccessGet full text
ISBN3031220633
9783031220630

Cover

Table of Contents:
  • Causality Discovery Based on Combined Causes and Multiple Causes in Drug-Drug Interaction -- 1 Introduction -- 2 Background -- 2.1 Combined Causes and Multiple Causes in DDI -- 2.2 Limitations of CBN -- 3 Proposed Method -- 4 Empirical Evaluation -- 5 Results and Discussions -- 6 Conclusion -- References -- An Integrated Medical Recommendation Mechanism Combining Promote Product Singular Value Decomposition and Knowledge Graph -- 1 Introduction -- 2 Proposed Methodology -- 2.1 Promote Product Singular Value Decomposition Algorithm -- 2.2 Knowledge Graph to Recommendation -- 3 Experiment -- 3.1 Environment and Dataset -- 3.2 Evaluation Metrics -- 3.3 Results and Analysis -- 4 Conclusion -- References -- Web and IoT Applications -- Joint Extraction of Entities and Relations in the News Domain -- 1 Introduction -- 2 Research Status -- 3 Methodology -- 3.1 Labeling Strategy for Central Entities -- 3.2 RoBERTa Presentation Layer -- 3.3 Improved BiLSTM* Layer -- 4 Experiment -- 4.1 Experimental Data and Experimental Environment -- 4.2 Evaluation Standard -- 4.3 Experimental Parameters -- 4.4 Experimental Design -- 4.5 Result Analysis -- 5 Conclusion -- References -- Event Detection from Web Data in Chinese Based on Bi-LSTM with Attention*-8pt -- 1 Introduction -- 2 Related Work -- 2.1 Pattern Matching Based Methods -- 2.2 Machine Learning Based Methods -- 3 ABiLSTM Model -- 3.1 Problem Formulation -- 3.2 Static Classification Model -- 3.3 Dynamic Model Maintenance -- 4 Experimental Evaluation -- 4.1 Dataset and Experimental Setup -- 4.2 Chinese Text Preprocessing -- 4.3 Sensitivity Analysis -- 4.4 Effectiveness Analysis -- 4.5 Dynamic Maintenance Comparison -- 5 Conclusion and Future Work -- References -- Sentiment Analysis of Tweets Using Deep Learning -- 1 Introduction -- 2 Related Work -- 2.1 Sentiment Analysis on Tweets
  • A Deep Learning Framework for Removing Bias from Single-Photon Emission Computerized Tomography
  • 2.2 Sentiment Analysis on Coronavirus Related Tweets -- 3 Data Collection and Pre-Processing -- 4 Methodology -- 4.1 Text Tokenization and Padding -- 4.2 Convolutional Neural Network Model (CNN) -- 4.3 Long Short-Term Memory (LSTM) -- 4.4 CNN-LSTM -- 4.5 Distiled Bidirectional Encoder Representation from Transformer (DistilBERT) -- 4.6 Stratified K-Fold Cross Validation -- 5 Experiments and Results -- 6 Conclusions -- References -- Cyber Attack Detection in IoT Networks with Small Samples: Implementation And Analysis -- 1 Introduction -- 2 Related Work -- 3 System Architecture -- 3.1 Network Topology -- 3.2 Attack Model -- 4 Threat Detection System -- 5 Modelling the Traffic Data and Evaluation -- 5.1 Results and Discussion -- 5.2 Supervised Methods -- 5.3 Unsupervised Methods -- 5.4 Comparison with Relatively Larger Dataset -- 6 Conclusion -- References -- SATB: A Testbed of IoT-Based Smart Agriculture Network for Dataset Generation -- 1 Introduction -- 2 Background and Related Work -- 2.1 Smart Agriculture -- 2.2 LoRaWAN -- 2.3 Related Work -- 3 SATB: A LoRaWAN SA Testbed -- 3.1 Components of SATB -- 3.2 Functionalities of SATB -- 4 A Case Study: Constructing an SA Dataset with SATB -- 4.1 Test Cases and Data Collection -- 4.2 Data Preprocessing -- 4.3 A Preliminary Study of the Dataset -- 5 Usage of the SATB Testbed -- 5.1 Development of Intrusion Detection Systems for SA -- 5.2 Preservation of Data Privacy and Integrity for SA -- 5.3 Development of Data-Driven Applications for SA -- 6 Conclusion -- References -- An Overview on Reducing Social Networks' Size -- 1 Introduction -- 2 Preliminaries -- 2.1 Problem Definition -- 2.2 Network Properties -- 3 Graph Sampling -- 3.1 Node Sampling -- 3.2 Edge Sampling -- 3.3 Traversal Based Sampling -- 4 Graph Coarsening -- 5 Recent Directions -- 6 Conclusion -- References
  • 4.1 Datasets Used -- 4.2 Experimental Setup -- 4.3 Algorithms Compared -- 4.4 Goals of the Experiments -- 4.5 Observations with Explanation -- 5 Conclusion and Future Research Directions -- References -- Quantifying Association Between Street-Level Urban Features and Crime Distribution Around Manhattan Subway Entrances -- 1 Introduction -- 2 Literature Review -- 2.1 Key Dimensions in Assessing Crimes Around Subway Stations -- 2.2 SVI, CV, and ML for Street Measures -- 3 Data and Methods -- 3.1 Hotspots of Crime Around Subway Stations in Manhattan -- 3.2 Analytical Framework -- 3.3 Data for Constructing Variables -- 4 Findings and Discussion -- 4.1 Regression Results -- 4.2 Urban Design Quality Matters -- 5 Conclusion -- References -- The Coherence and Divergence Between the Objective and Subjective Measurement of Street Perceptions for Shanghai -- 1 Introduction -- 2 Literature Review -- 3 Methods and Process -- 3.1 Analytical Framework -- 3.2 Site Investigation and Data Preparation -- 3.3 Quantifying Objective and Subjective Perception Scores -- 3.4 Coherence and Divergence of the Subjective and Objective Perceptions -- 3.5 Features that Cause Differences Between Objective and Subjective Measures -- 4 Results and Discussion -- 4.1 Spatial Mismatch Between Subjective and Objective Perceptions -- 4.2 Key Urban Features for Variances Between Two Models -- 5 Conclusion -- Appendix -- References -- Other Application -- A Comparative Study of Question Answering over Knowledge Bases -- 1 Introduction -- 2 Methodology -- 2.1 Problem Setting -- 2.2 KBQA Approaches -- 2.3 Summary -- 3 Experimental Setup -- 4 Results -- 4.1 End-to-end Comparison -- 4.2 Running Time -- 4.3 Influence of Question Taxonomy -- 4.4 Effects of Quantity of Questions -- 5 Conclusion -- References
  • Intro -- Preface -- Organization -- Contents - Part I -- Contents - Part II -- Finance and Healthcare -- Application of Supplemental Sampling and Interpretable AI in Credit Scoring for Canadian Fintechs: Methods and Case Studies -- 1 Introduction -- 2 Supplementary Sampling -- 2.1 Notations -- 2.2 Theories -- 2.3 Sampling Strategies -- 3 Techniques of Credit Scoring -- 4 Empirical Studies -- 4.1 Data Source and Sample Facts -- 4.2 Model Development and Comparisons -- 4.3 Model Evaluation -- 5 Conclusion -- References -- A Deep Convolutional Autoencoder-Based Approach for Parkinson's Disease Diagnosis Through Speech Signals -- 1 Introduction -- 2 Related Works -- 3 Proposed Approach -- 3.1 Dataset -- 3.2 Deep Convolutional AutoEncoder (DCAE) -- 3.3 MultiLayer Perceptron (MLP) -- 4 Experimental Results -- 5 Conclusion -- References -- Mining the Potential Relationships Between Cancer Cases and Industrial Pollution Based on High-Influence Ordered-Pair Patterns -- 1 Introduction -- 2 High-Influence Ordered-Pair Pattern -- 3 Basic Algorithm for Mining HIOPPs -- 3.1 Property Analysis of HIOPP -- 3.2 Description of Basic Algorithm -- 4 Optimizing Algorithm for Mining HIOPPs -- 4.1 Feasibility of Participation Instances -- 4.2 Obtaining Participating Instances -- 5 Experiments -- 5.1 Effectiveness of Mining Results -- 5.2 Performance Evaluation -- 6 Conclusion -- References -- Finding Hidden Relationships Between Medical Concepts by Leveraging Metamap and Text Mining Techniques -- 1 Introduction -- 2 Literature Review -- 3 Methodology -- 4 Data Collection and Analysis -- 4.1 Data Extraction from the Source -- 4.2 MetaMap Module - Processing Phase -- 4.3 MetaMap Module - Preparation Phase -- 4.4 Title and Abstract Fetching Module -- 4.5 Closed Discovery Module -- 5 System Evaluation -- 6 Result Evaluation -- 7 Conclusion and Future Work -- References
  • AuCM: Course Map Data Analytics for Australian IT Programs in Higher Education -- 1 Introduction -- 2 Related Work -- 3 The AuCM Dataset -- 3.1 Data Scraping -- 3.2 Data Processing -- 4 Statistical Analysis of AuCM -- 4.1 Analysis of the Number of Courses -- 4.2 Analysis of Curriculum Design -- 4.3 Analysis of Core Curriculum -- 4.4 Analysis of Prerequisites -- 5 Concept Semantics in AuCM -- 5.1 Semantic Feature Extraction and Analysis -- 5.2 Concept Map Learning -- 6 Conclusion -- References -- Profit Maximization Using Social Networks in Two-Phase Setting -- 1 Introduction -- 2 Background and Problem Definition -- 3 Mathematical Model and Solution Methodologies -- 4 Experimental Evaluation -- 5 Conclusion and Future Direction -- References -- On-Device Application -- SESA: Fast Trajectory Compression Method Using Sub-trajectories Segmented by Stay Areas -- 1 Introduction -- 2 Related Work -- 3 Proposed Method -- 3.1 Extraction of Stay Area -- 3.2 Segmentation -- 3.3 SQUISH-E() -- 3.4 Integration -- 4 Experiment -- 4.1 Experimental Conditions -- 4.2 Experiment Results -- 4.3 Discussion -- 5 Conclusion and Future Work -- References -- Android Malware Detection Based on Stacking and Multi-feature Fusion -- 1 Introduction -- 2 Related Work -- 2.1 Features of Android Malware Detection -- 2.2 Feature Selection -- 2.3 Stacking Technique -- 3 Framework and Implementation of Android Malware -- 3.1 Feature Extraction and Preprocessing -- 3.2 Two-Level Feature Selection -- 3.3 Malware Detection Based on Stacking Structure -- 4 Experiments and Evaluations -- 4.1 Data Set and Experimental Environment -- 4.2 Experimental Process and Results -- 5 Conclusion -- References -- Influential Billboard Slot Selection Using Pruned Submodularity Graph -- 1 Introduction -- 2 Preliminaries and Problem Definition -- 3 Proposed Solution Approach -- 4 Experimental Evaluation