Data Analytics and Management in Data Intensive Domains: 23rd International Conference, DAMDID/RCDL 2021, Moscow, Russia, October 26–29, 2021, Revised ... in Computer and Information Science)

✍ Scribed by Alexei Pozanenko (editor), Sergey Stupnikov (editor), Bernhard Thalheim (editor), Eva Mendez (editor), Nadezhda Kiselyova (editor)

• Publisher: Springer
• Year: 2022
• Tongue: English
• Leaves: 272
• Category: Library

✦ Synopsis

This book constitutes the post-conference proceedings of the 23rd International Conference on Data Analytics and Management in Data Intensive Domains, DAMDID/RCDL 2021, held in Moscow, Russia, in October 2021.
The 16 revised full papers were carefully reviewed and selected from 61 submissions. The papers are organized in the following topical sections: problem solving infrastructures, experiment organization, and machine learning applications; data analysis in astronomy; data analysis in material and earth sciences; information extraction from text
The conference was held virtually due to the COVID-19 pandemic.

✦ Table of Contents

Preface
Organization
Contents
Problem Solving Infrastructures, Experiment Organization, and Machine Learning Applications
MLDev: Data Science Experiment Automation and Reproducibility Software
1 Introduction
2 Problem Statement
3 Proposed Solution
3.1 Experiment Specification
3.2 Extensibility Mechanisms
3.3 Open Source Development
4 Experimental Evaluation
4.1 Experiment Design
4.2 Application to a New Experiment
4.3 Reproducibility Study for a Published Paper
4.4 Analysis and Results
5 Related Work and Comparison
5.1 Command Line Tools
5.2 Jupyter Notebooks
5.3 NextFlow
5.4 MLflow
5.5 Analysis and Comparison
6 Conclusions
A Quality Requirements for Experiment Automation Software
References
Response to Cybersecurity Threats of Informational Infrastructure Based on Conceptual Models
1 Introduction
2 Related Works
3 Model Overview
3.1 Use Cases
3.2 Implementation
3.3 External Standards and Taxonomies
4 Use Cases of Model Application
4.1 Attack Classification
4.2 Network Nodes Reachability and Risk Estimation
4.3 Countermeasures
4.4 Incident Generation
5 Conclusions and Directions for Further Work
References
Social Network Analysis of the Professional Community Interaction—Movie Industry Case
1 Introduction
2 Related Work
3 Dataset Exploration
4 Network Model
4.1 Graph Generation
4.2 Graph Description
4.3 Random Walk Network Model
5 Experiment
5.1 Random Forest Models
5.2 Random Forest Model
5.3 Decision Tree Model
5.4 Neural Network Models
6 Conclusions
References
Data Analysis in Astronomy
Cross-Matching of Large Sky Surveys and Study of Astronomical Objects Apparent in Ultraviolet Band Only
1 Introduction
2 Sky Surveys Overview
3 Cross-Matching of Multi-Wavelength Surveys
4 Properties of UV-Only Objects
5 Objects with Extreme UV-optical Colours
6 Discussion
7 Conclusion
References
The Diversity of Light Curves of Supernovae Associated with Gamma-Ray Bursts
1 Introduction
1.1 Statistical Information
1.2 Physical Description of the Phenomenon
2 Registration of GRBs and Their Observation
3 Astronomical Images Processing
4 Sample
5 Light Curves of SNe Associated with GRBs
5.1 Well Statistically Secure SN's Light Curve
5.2 Averagely Statistically Secure SN's Light Curve
5.3 Single-Filter SN's Light Curve
5.4 Subtle SN's Light Curve
5.5 Hybrid SN's Light Curve
6 Description of Light Curves of SNe Associated with GRBs
7 Discussion
8 Interdisciplinary Application
9 Conclusion
References
Application of Machine Learning Methods for Cross-Matching Astronomical Catalogues
1 Introduction
2 Related Work
3 A Machine Learning Approach for Cross-Matching Astronomical Catalogues
3.1 The Machine Learning Approach Overview
3.2 Data Sources Selection
3.3 Data Preparation and Data Quality Issues
3.4 Train Set Creation Issues
4 Experiments and Results
5 Conclusions
References
Pipeline for Detection of Transient Objects in Optical Surveys
1 Introduction
2 Literature Review
2.1 ROTSE
2.2 ZTF
2.3 MASTER-Net
2.4 IKI GRB Follow-Up Network
2.5 Another Surveys
3 Image Processing Pipeline
3.1 Motivation
3.2 Requirements
3.3 Architecture
3.4 Implementation
3.5 Objects Extraction and Measurement
3.6 Astrometric Reduction
3.7 Photometric Reduction
3.8 Local Catalog of Objects
3.9 Identification of Transients
3.10 Catalog of Transients
3.11 Performance and Accuracy
4 Results and Conclusions
4.1 Status on Implementation of the Pipeline
4.2 Future Plans
References
VALD in Astrophysics
1 VALD Database
2 Using the VALD
2.1 Stellar Astrophysics
2.2 Astrophysics of Interstellar Medium (ISM)
2.3 Optical Tools
3 VALD in VAMDC
4 Conclusion
References
Data Analysis in Material and Earth Sciences
Machine Learning Application to Predict New Inorganic Compounds – Results and Perspectives
1 Introduction
2 The Basic Peculiarities of Machine Learning Applications to Prediction Problems Solution for New Inorganic Compounds
3 Some Machine Learning Application Results to Inorganic Chemistry and Materials Science
3.1 Predicting Compound Formation
3.2 Predicting the Compounds Crystal Structure Type
3.3 Quantitative Properties Prediction
3.4 Machine Learning Methods Application in Inorganic Materials Industry
4 Problems and Prospects
References
Interoperability and Architecture Requirements Analysis and Metadata Standardization for a Research Data Infrastructure in Catalysis
1 Introduction
2 Requirements Analysis Methodology
3 Research Workflows and Data Provenance
4 Semantic Interoperability
5 Research Workflow to Ontology Enhancements
6 Repository Architecture
7 Conclusion
References
Fast Predictions of Lattice Energies by Continuous Isometry Invariants of Crystal Structures
1 Motivations, Problem Statement and Overview of Results
2 Review of Related Machine Learning Approaches
3 Key Definitions and Recent Results of Periodic Geometry
4 Continuity of the Energy in Terms of AMD Invariants
5 Fast Predictions of the Energy by AMD Invariants
6 Conclusions and a Discussion of Future Developments
References
Image Recognition for Large Soil Maps Archive Overview: Metadata Extraction and Georeferencing Tool Development
1 Introduction
2 Related Work
3 Challenges
4 Obtaining Map Images
5 Results
6 Summary
References
Information Extraction from Text
Cross-Lingual Plagiarism Detection Method
1 Introduction
2 Related Work
3 Cross-Lingual Plagiarism Detection Method
3.1 Preprocessing
3.2 Source Retrieval
3.3 Sentence Similarity
3.4 Text Alignment Algorithm
4 Evaluation
4.1 Essays Dataset
4.2 Evaluation Results
4.3 Comparison with Other Methods
4.4 Fragment Size Experiments
4.5 Impact of Text Alignment Algorithm
5 Conclusion
References
Methods for Automatic Argumentation Structure Prediction
1 Introduction
2 Related Work
3 Model Architectures
4 Datasets
5 Experiments
6 Conclusion
References
A System for Information Extraction from Scientific Texts in Russian
1 Introduction
2 Related Work
3 Data Description
4 Full System Architecture
4.1 Entity Recognition
4.2 Relation Extraction
4.3 Entity Linking
5 Conclusions
References
Improving Neural Abstractive Summarization with Reliable Sentence Sampling
1 Introduction
2 Related Work
2.1 Abstractive Summarization
2.2 Hallucinations in Summarization
2.3 Methods of Improving Factual Consistency
3 Obtaining Dataset for Russian News Summarization
4 Improving Quality During Training
4.1 Control Tokens
4.2 Truncated Loss
4.3 Dataset Cleaning
5 Reliable Sentence Sampling
5.1 Summary Sampling Issues
5.2 Algorithm
5.3 Reliability Scores
6 Implementation
7 Experiments
7.1 Training-Based Methods
7.2 Reliable Sentence Sampling
7.3 Human Evaluation
8 Conclusions
References
Author Index