Database Systems for Advanced Applications

Name: Database Systems for Advanced Applications | 23rd International Conference, DASFAA 2018, Gold Coast, QLD, Australia, May 21-24, 2018, Proceedings, Part II
Brand: Springer
Price: 96.29 EUR
Availability: OnlineOnly

23rd International Conference, DASFAA 2018, Gold Coast, QLD, Australia, May 21-24, 2018, Proceedings, Part II

Jian Pei Yannis Manolopoulos Shazia Sadiq Jianxin Li(Herausgeber*in)

Springer (Verlag)

Erschienen am 11. Mai 2018

XXIV, 834 Seiten

E-Book

PDF mit Wasserzeichen-DRM

Systemvoraussetzungen

978-3-319-91458-9 (ISBN)

96,29 €inkl. 7% MwSt.

Systemvoraussetzungen

für PDF mit Wasserzeichen-DRM

E-Book Einzellizenz

Als Download verfügbar

Beschreibung

Weitere Details

Weitere Ausgaben

Inhalt

Intro
Preface
Organization
Contents -- Part II
Contents -- Part I
Medical Data Mining
Personalized Prescription for Comorbidity
1 Introduction
2 Related Work
3 Personalized Prescription for Comorbidity
3.1 Preliminaries
3.2 Algorithm Overview
3.3 C1: Learning to Represent the Diagnosis
3.4 C2: Learning to Represent the Patient
3.5 C3: Fusing Representations with Trilinear Method
3.6 Objective Optimization
4 Experiment
4.1 Dataset Description
4.2 Prediction Accuracy
4.3 Ablation Study
4.4 Embedding Analysis
4.5 Attention Analysis
4.6 Personalized Prescription Analysis
5 Conclusion
References
Modeling Patient Visit Using Electronic Medical Records for Cost Profile Estimation
1 Introduction
2 Problem Definition
2.1 Definition
2.2 Cost Profile Estimation Problem
3 Model
3.1 Assumptions
3.2 Patient Visit Probabilistic Generative Model
3.3 Model Learning
3.4 Cost Profile Estimation
4 Experiments
4.1 Experiment Setup
4.2 Baseline Methods
4.3 Performance Comparison
4.4 Sensitivity Analysis
5 Related Work
6 Conclusion
References
Learning the Representation of Medical Features for Clinical Pathway Analysis
1 Introduction
2 Related Work
2.1 CP Analysis
2.2 Representation Learning in Healthcare
3 Methodology
3.1 Preliminary
3.2 Brief Review of Word2vec
3.3 RoMCP
4 Experiments
4.1 Dataset
4.2 Baseline Methods
4.3 Experimental Setting
4.4 Evaluation
4.5 Results
4.6 Computational Complexity Study
4.7 Case Study
5 Conclusion
References
Domain Supervised Deep Learning Framework for Detecting Chinese Diabetes-Related Topics
1 Introduction
2 Related Work
3 The Topic Classification Framework
3.1 Data Collection
3.2 Data Preprocessing
3.3 Model Training and Topic Classification
4 The SDA-Based Models
4.1 Topic Supervised Stacked Denoising Autoencoders
4.2 Domain Supervised Stacked Denoising Autoencoders
5 Experiments
5.1 The Datasets
5.2 Evaluation Metrics and Benchmarks
5.3 Comparison Results
5.4 Extra Comparison Results Using English Datasets
5.5 The Effects of the Parameter Values
5.6 The Effects of the Feature Vectors
5.7 Causes of Misclassification Errors
6 Conclusion
References
Security and Privacy
Publishing Graph Node Strength Histogram with Edge Differential Privacy
1 Introduction
2 Preliminaries
2.1 Node Strength
2.2 Differential Privacy
3 Proposed Approaches
3.1 Sequence-Aware Clustering
3.2 Density-Based Clustering
3.3 Finding the Least Cost Partition
4 Experiment
4.1 Datasets and Settings
4.2 Evaluating t-Sequence-aware-Hist and t-Density-based-Hist
4.3 Introspective Analysis
5 Related Work
6 Conclusion
References
PrivTS: Differentially Private Frequent Time-Constrained Sequential Pattern Mining
1 Introduction
2 Preliminaries
3 Overview of PrivTS
4 Phase 1: Sample-Based Filtering
4.1 Sparse Vector Algorithm
4.2 Sample-Based Filtering
4.3 Candidate Generating
4.4 Parameter Settings
4.5 Privacy Analysis of Sample-Based Filtering Approach
5 Phase 2: Count Refining
5.1 Grouping-Based Counting
5.2 Greedy-Based Counting
5.3 Privacy Analysis of Count Refining Approach
6 Experiments
6.1 Experimental Setup
6.2 Experimental Results
7 Related Work
8 Conclusions
References
Secure Range Query over Encrypted Data in Outsourced Environments
1 Introduction
2 Preliminaries and Problem Definition
2.1 System Framework
2.2 Security Model
2.3 Cryptographic Building Blocks
2.4 Problem Definition
3 Basic Secure Range Queries Algorithm
3.1 Basic Secure Node Intersection Operation
3.2 Basic Secure Intermediate Value Operation
3.3 Basic Secure Range Query Algorithm
4 Fully Secure Range Query Algorithm
4.1 Fully Secure Operations
4.2 Obfuscation for Oblivious Traversal
4.3 Fully Secure Range Query Algorithm
5 Experiments
6 Related Work
7 Conclusion
References
TRQED: Secure and Fast Tree-Based Private Range Queries over Encrypted Cloud
1 Introduction
2 Related Work
3 Problem Formulation
3.1 System Model
3.2 Threat Model
4 Intersection Predicate Encryption
4.1 Inner Product Comparison
4.2 Point Intersection Predicate Encryption (PIPE)
4.3 Range Intersection Predicate Encryption (RIPE)
5 TRQED Scheme
5.1 TRQED Construction
5.2 Data Update
6 Security Analysis
7 Evaluation
7.1 Overhead and Efficiency
7.2 TRQED v.s. Prior Art
8 Conclusion
References
Search and Information Retrieval
iExplore: Accelerating Exploratory Data Analysis by Predicting User Intention
1 Introduction
2 Problem Formulation
2.1 Intention Model
2.2 Convergence
3 iExplore: Intention-Driven Exploration
3.1 iExplore Architecture
3.2 Vector Model
3.3 Intention Function
3.4 Recommendation and Prefetching
4 Experimental Evaluation
4.1 Experiments Setup
4.2 Response Time Comparison
4.3 Impact of Parameter
4.4 Prefetching Evaluation
4.5 Case Study
5 Related Work
6 Conclusion and Future Work
References
Coverage-Oriented Diversification of Keyword Search Results on Graphs
1 Introduction
2 Related Work
3 Problem Formulation
4 Diversity Measurement
5 Diversified Search
5.1 Result Generation
5.2 MIS-Based Diversification
5.3 A DP-Based Approach
5.4 Search Algorithm
6 Experiments
6.1 Setup
6.2 Effectiveness
6.3 Efficiency
7 Conclusions and Future Work
References
Novel Approaches to Accelerating the Convergence Rate of Markov Decision Process for Search Result Diversification
1 Introduction
2 Related Work
2.1 Search Result Diversification
2.2 Reinforcement Learning for Information Retrieval
3 Preliminaries
3.1 Markov Decision Process
3.2 MDP-DIV
3.3 NTN-DIV
4 Methodology
4.1 K Nearest Neighbors Strategy
4.2 Pre-trained NTN-DIV Strategy
5 Experimental Study
5.1 Datasets and Evaluation Metrics
5.2 Experimental Setup
5.3 Results and Analysis
6 Conclusion
References
Structures or Texts? A Dynamic Gating Method for Expert Finding in CQA Services
1 Introduction
2 Related Work
3 Expert Finding via Jointly Embedding Texts and Structures
3.1 Problem Description and Formulation
3.2 Gating Mechanism
3.3 Matching U-Q with Neural Tensor Network
4 Experiments
5 Conclusions
References
Query Processing and Optimizations
Collusion-Resistant Processing of SQL Range Predicates
1 Introduction
1.1 Example Security Breach Under HCC
1.2 Range Predicate Security (RPS)
2 Problem Framework
2.1 Adversary Objective
2.2 Notations
3 Database Encryption with SPLIT
3.1 Splitting of Data
3.2 Layered Encryption
3.3 Data Transformation
3.4 Design Rationale
4 Range Query Processing
4.1 Range Query Mapping
4.2 Range Query Execution
5 Security Analysis of SPLIT
6 Experimental Evaluation
6.1 Query Execution Time
6.2 Storage Cost
7 Related Work
8 Conclusions
References
Interactive Transaction Processing for In-Memory Database System
1 Introduction
2 Design Consideration
3 Execution Model
3.1 SQL-To-Thread
3.2 SQL-To-Coroutine
3.3 Discussion and Refinement
4 Lock Manager
4.1 Lock Acquisition
4.2 Lock Releasing
4.3 Deadlock
4.4 Correctness
5 Experiment
5.1 Varying Number of Clients
5.2 Varying Number of Warehouses
5.3 Varying Workload Characteristics
5.4 Breaking CPU Time down
6 Relate Work
7 Conclusion
References
An Adaptive Eviction Framework for Anti-caching Based In-Memory Databases
1 Introduction
2 Background and Motivation
2.1 Anti-caching Background
2.2 Motivation
3 Adaptive Eviction
3.1 Overview
3.2 Tuning Techniques
4 Experiments
4.1 Benchmarks
4.2 System Setup
4.3 Results and Analysis
5 Related Work
6 Conclusion
References
Efficient Complex Social Event-Participant Planning Based on Heuristic Dynamic Programming
1 Introduction
2 Problem Definition
2.1 Complex Event Planning: GEPC Problem
3 Related Work
4 Heuristic-DP Algorithm
4.1 iTDP Algorithm
4.2 TDP Algorithm
4.3 Complexity Analysis
5 Improving Heuristic Strategy
6 Experimental Evaluation
6.1 Experimental Environment and Datasets
6.2 Results
7 Conclusion
References
Data Quality and Crowdsourcing
Repairing Data Violations with Order Dependencies
1 Introduction
2 Preliminaries
3 Framework of Repairing Order Dependency Violations
4 Data Repairing with Order Dependencies
4.1 Order Specified by LHS Attributes
4.2 Fix Violations on RHS Attributes
4.3 Repairing Violations for Multiple ODs
5 Experimental Study
6 Conclusions
References
Multi-Worker-Aware Task Planning in Real-Time Spatial Crowdsourcing
1 Introduction
2 The MWATP Problem
2.1 Problem Definitions
2.2 Hardness of MWATP Problem
3 Solutions to MWATP Problem
3.1 The Delay-Planning Algorithm
3.2 The Fast-Planning Algorithm
4 Experimental Study
4.1 Experimental Setup
4.2 Experiment Results
5 Related Work
5.1 Spatial Crowdsourcing
5.2 Orienteering Problem
6 Conclusion
References
MT-MCD: A Multi-task Cognitive Diagnosis Framework for Student Assessment
1 Introduction
2 Related Work
2.1 Student Assessment
2.2 Multi-task Learning
3 Multi Task - Multidimensional Cognitive Diagnosis
3.1 Problem Formulation
3.2 Framework
3.3 MT-MCD Implementation
4 Experiment
4.1 Dataset and Setups
4.2 Student Score Prediction
4.3 Student Attribute Evaluation
4.4 Dimension Sensitivity of Student Attributes
4.5 Question Parameter Evaluation
5 Conclusion and Future Work
References
Towards Adaptive Sensory Data Fusion for Detecting Highway Traffic Conditions in Real Time
Abstract
1 Introduction
2 Related Work
3 Real-World Data Analyses
3.1 Spatial-Temporal Distribution Analyses
3.2 Data Inherent Structure Discovery
4 Megrez Approach
4.1 Multi-source Vehicle Speed Merging
4.2 Data Completion via Compressive Sensing
4.3 Data Filtering by Traffic Flow Features
5 Evaluation
5.1 Case Study
5.2 Speed Accuracy and Traffic Condition Accuracy Evaluation
5.3 Adaptability of Megrez
6 Conclusions
Acknowledgement
References
On the Interaction of Functional and Inclusion Dependencies with Independence Atoms
1 Introduction
1.1 Contributions
2 Preliminaries
3 IAs+FDs
3.1 Implication Problem for FDs and IAs
3.2 Implication for UFDs and IAs
4 IAs+UFDs+UINDs
5 Polynomial-Time Conditions for Non-interaction
6 Complexity Results
7 Conclusion and Outlook
References
Source Selection for Inconsistency Detection
1 Introduction
2 Problem Definition
3 Algorithm for SSID
4 Coverage Estimation
4.1 Sketch
4.2 Estimation of Set Size
4.3 Estimation of Intersection Set Size
4.4 Properties of MH-Greedy Algorithm
5 Experimental Results
5.1 Experiment Setup
5.2 Comparison
5.3 Impact of Parameters
5.4 Results for Efficiency
6 Related Work
7 Conclusion
References
Effective Solution for Labeling Candidates with a Proper Ration for Efficient Crowdsourcing
1 Introduction
2 Preliminary
3 An End-Squeezing Approach
4 Experimental Study
4.1 Experimental Methodology
4.2 Experiments on Synthetic Data
4.3 Experiments on Real Data
5 Related Works
6 Conclusion
References
Handling Unreasonable Data in Negative Surveys
Abstract
1 Introduction
2 Reconstruction Algorithm
3 Experiments
4 Extension to General Negative Surveys
5 Conclusions and Future Work
Acknowledgment
References
Learning Models
Multi-view Proximity Learning for Clustering
1 Introduction
2 The Proposed Model
2.1 The Objective Function
2.2 Determination of Parameter
2.3 Optimization
3 Experiment
3.1 Synthetic Experiment
3.2 Real-World Datasets and Evaluation Measures
3.3 Parameter Analysis
3.4 Convergence Analysis
3.5 Comparison Experiment
4 Conclusion
References
Extracting Label Importance Information for Multi-label Classification
1 Introduction
2 Multi-label Learning
3 Multi-label Importance
4 Exploiting Multi-label Importance Information
4.1 Optimizing the Label Ordering in Classifier Chains
4.2 Considering Label Distance in ML-kNN
5 Experimental Results
5.1 Evaluation Metrics
5.2 Experiments
6 Conclusion
References
Exploiting Instance Relationship for Effective Extreme Multi-label Learning
1 Introduction
2 Related Work
2.1 Extreme Multi-label Learning
2.2 Relational Learning
3 Preliminary
3.1 FastXML
3.2 PfastreXML
3.3 Partial Label Trees
4 The RTC Approach
4.1 RTC-FastXML
4.2 RTC-PfastreXML
4.3 RTC-PLTs
4.4 Feature Engineering
5 Experiments
5.1 Datasets
5.2 Hyper-parameters
5.3 Experimental Results
5.4 Case Study
6 Conclusions
References
Exploiting Ranking Consistency Principle in Representation Learning for Location Promotion
1 Introduction
2 Preliminaries
2.1 Problem Description
2.2 Data Analysis
3 Hybrid Ranking and Embedding Method
3.1 Learning Geographical and Preference Embedding with Ranking Consistency
3.2 Learning POI Semantic with Graph Based Embedding
3.3 The Unified Model
4 Experimental Results
4.1 Settings
4.2 Overall Ranking Performance
4.3 Performance on New POIs
4.4 Parameter Sensitivity Test
4.5 A Case Study
5 Related Works
6 Conclusion
References
Patent Quality Valuation with Deep Learning Models
1 Introduction
2 Related Work
2.1 Patent Citation Network in Patent Quality Valuation
2.2 Text Mining Techniques for Patent Analysis
3 Deep Learning Based Patent Quality Valuation (DLPQV) Framework
3.1 Problem and Study Overview
3.2 Attribute Network Embedding for Citation Network
3.3 Attention-Based Convolutional Neural Network
4 Experiments
4.1 Dataset Description
4.2 Experimental Setup
4.3 Baseline Approaches
4.4 Experimental Results
5 Conclusions
References
Learning Distribution-Matched Landmarks for Unsupervised Domain Adaptation
1 Introduction
2 Related Work
3 Learning Distribution-Matched Landmarks
3.1 Problem Definition
3.2 Problem Formulation
3.3 Problem Optimization
3.4 Computational Complexity
4 Experiments
4.1 Datasets
4.2 Compared Baselines
4.3 Experimental Settings
4.4 Experimental Results
4.5 Parameter Sensitivity and Convergence
4.6 Effectiveness Analysis
5 Conclusion
References
Factorization Meets Memory Network: Learning to Predict Activity Popularity
1 Introduction
2 Related Work
2.1 Popularity Prediction
2.2 Deep Learning for Personalization and Memory Network
3 Problem Definition
4 Computational Model
4.1 Model Overview
4.2 Memory Network Module
4.3 Tensor Factorization Module
4.4 Training
5 Experimental Setup
5.1 Datasets
5.2 Baselines
5.3 Variants of MOOD
5.4 Implementation Details and Evaluation Metrics
6 Experimental Results
6.1 Model Performance Comparison (Q1)
6.2 Factor Contribution (Q2)
6.3 Impact of Number of Layers
6.4 Impact of Activity Time
6.5 Case Study for Attention Visualization
7 Conclusion
References
Representation Learning for Large-Scale Dynamic Networks
1 Introduction
2 Related Work
3 Problem Definition
4 DLNE: Dynamic Large-Scale Network Embedding
4.1 Overall Framework
4.2 Algorithm and Optimization
5 Experiments
5.1 Data Description
5.2 Baselines and Evaluation Metrics
5.3 Performance Comparison
5.4 Parallel Computing
6 Conclusion
References
Multi-view Discriminative Learning via Joint Non-negative Matrix Factorization
1 Introduction
2 Related Work
3 The Proposed Method
3.1 Preliminaries
3.2 Discriminant Learning on Multi-view Data
3.3 Regularization Terms
3.4 Optimization
4 Experiment
4.1 Data Sets
4.2 Selection of Comparison Algorithms
4.3 Classification on Real-World Data Sets
4.4 Empirical Study of DICS Algorithm
4.5 Parameter Study
4.6 Convergence Analysis
5 Conclusion
References
Efficient Discovery of Embedded Patterns from Large Attributed Trees
1 Introduction
2 Definitions and Problem Statement
3 Mining Embedded Tree Patterns from Non-attributed Trees
3.1 Candidate Pattern Generation
3.2 Support Computation
3.3 Algorithm embTM
4 Mining Embedded Attributed Patterns: An Interleaved Approach
5 Mining Embedded Attributed Patterns: A Layered Approach
6 Experimental Evaluation
7 Related Work
8 Conclusion
References
Classification Learning from Private Data in Heterogeneous Settings
1 Introduction
2 System Model
2.1 Problem Definition
2.2 Privacy Model
2.3 Utility Metrics
3 Private Naïve Bayes Classifier in the Local Setting
3.1 Utility-First Strategy (UFS)
3.2 Theoretical Analysis
4 Private Naïve Bayes Classifier in the Mixture Setting
4.1 Mechanism Description
4.2 Theoretical Analysis
5 Experiment
6 Related Work
7 Conclusion and Future Work
References
Multimedia Data Processing
Fusing Satellite Data and Urban Data for Business Location Selection: A Neural Approach
1 Introduction
2 Problem and Framework
3 Empirical Data Analysis
4 Location Popularity Appraisal Using Neural Networks
4.1 Urban Context and Satellite Feature Extraction
4.2 R2Net: Proposed Model
4.3 Model Training and Optimization
5 Experiments
5.1 Datasets
5.2 Performance Metrics
5.3 Baseline Methods
5.4 Performance Comparison of Different Approaches
5.5 Impact of Combination of Ranking and Regression
5.6 Feature Evaluation
6 Related Work
7 Conclusion
References
Index and Retrieve Multimedia Data: Cross-Modal Hashing by Learning Subspace Relation
1 Introduction
2 Related Work
3 Proposed Method
3.1 Notations
3.2 Hash Functions
3.3 Subspace Relation Learning for Cross-Modal Hashing
3.4 Optimization Algorithm
3.5 Indexing and Cross-Modal Retrieval
4 Experiments
4.1 Datasets
4.2 Compared Methods and Evaluation Metrics
4.3 Implementation
4.4 Experimental Results
5 Conclusions
References
Deep Sparse Informative Transfer SoftMax for Cross-Domain Image Classification
1 Introduction
2 Related Work
3 Sparse Informative Transfer SoftMax Model
3.1 Problem Formulation
3.2 Multiple Informative Transfer Factor
3.3 Sparse SoftMax Model
3.4 Parameter Estimation
3.5 Deep SITS Network
4 Experiments
4.1 DataSet
4.2 Experimental Settings
4.3 Experimental Results
4.4 Discussion
5 Conclusions
References
Sitcom-Stars Oriented Video Advertising via Clothing Retrieval
1 Introduction
2 Models and Implementation Details
3 DeepLink in the Wild
4 Conclusion
References
Distributed Computing
Efficient Snapshot Isolation in Paxos-Replicated Database Systems
1 Introduction
2 Background
3 SI in Paxos-Replicated Database Systems
3.1 System Architecture
3.2 Transaction Execution
3.3 Problem Analysis
4 Efficient Snapshot Isolation
4.1 Overview
4.2 Early Log Replay
4.3 Transaction Read Execution
4.4 Recovery
5 Adaptive Timestamp Allocation
6 Experiments
6.1 Scalability
6.2 Effectiveness
7 Related Work
8 Conclusion
References
Proof of Reputation: A Reputation-Based Consensus Protocol for Peer-to-Peer Network
1 Introduction
2 Related Works
3 Problem and Threat Model
3.1 Problem Definition
3.2 Threat Model
4 The Proof of Reputation Protocol
4.1 Design Overview
4.2 Broadcasting Transactions
4.3 Transactions Filter
4.4 Block Publication
4.5 Block Verification
4.6 Cost Analysis and Quick Bootstrap
4.7 Security Analysis
5 Experiments and Evaluation
5.1 Experiment Setting
5.2 Performance Evaluation
6 Conclusion and Future Work
References
Incremental Materialized View Maintenance on Distributed Log-Structured Merge-Tree
1 Introduction
2 Background
2.1 LSM-Tree Model
2.2 View Table
2.3 A Straightforward View Maintenance Design
2.4 Design Features
3 System Architecture
3.1 View Storage
3.2 Update on Base Table and View Table
3.3 Query on View Tables
3.4 Extension to Join View
4 Incremental View Maintenance
4.1 Version Control
4.2 Update of V-Memtable
4.3 Two Optimizations
5 Experiment
5.1 Experiment Setup
5.2 Effect of View Query on Transaction Processing
5.3 Effect of Transaction Processing on View Query
6 Related Work
7 Conclusion
References
CDSFM: A Circular Distributed SGLD-Based Factorization Machines
1 Introduction
2 Circular Distributed SGLD-Based FM
3 Experiments Setting
4 Related Work
5 Conclusions
References
Industrial Track
An Industrial-Scale System for Heterogeneous Information Card Ranking in Alipay
1 Introduction
2 System Architecture
3 Feature Generator
3.1 Feature Generator Overview
3.2 Factor Embedding
4 Model Training
5 Experiments
5.1 Effectiveness of Factor Embedding
5.2 Effectiveness of Online/Chunk-Based Learning Ensemble Model
6 Conclusions
References
A Twin-Buffer Scheme for High-Throughput Logging
1 Introduction
2 Related Work
3 Background
3.1 Logging Subsystem of PostgreSQL
3.2 Non-Volatile Memories
4 Design of TwinBuf
4.1 Overview
4.2 Group Commit
4.3 Switch of Log Buffers' Roles
4.4 Checkpointing
4.5 Recovery
5 Detailed Implementation
6 Evaluation
7 Conclusion
References
Qualitative Instead of Quantitative: Towards Practical Data Analysis Under Differential Privacy
1 Introduction
2 Background and Motivation
2.1 Differential Privacy
2.2 Qualitative or Quantitative Mining Under DP
3 Qualitative Analysis of Attribute Relationship
3.1 Data Publication with DP
3.2 Metrics of Attribute Relationship
4 Proposed Approaches of Qualitative Analysis
4.1 Skeleton Design
4.2 Belong to Top-K Classifier (BTK)
4.3 Be Larger Classifier (BL)
5 Experiments
5.1 Experimental Settings
5.2 Metrics of Attribute Relationship
5.3 Belong to Top K Classifier (BTK)
5.4 Be Larger Classifier (BL)
6 Related Work
7 Conclusion
References
Client Churn Prediction with Call Log Analysis
1 Introduction
2 Preliminary
3 Methodology
3.1 Semantic Information
3.2 Word Importance
3.3 Word Embedding
3.4 Combined Prediction Model
4 Experiment
4.1 Datasets
4.2 Evaluation
4.3 Results
5 Conclusions
References
Unpack Local Model Interpretation for GBDT
1 Introduction
2 Related Work
3 Preliminary
3.1 Interpretation for Random Forest
3.2 Gradient Boosting Decision Tree
3.3 Problem Statement
4 Mechanism
5 Experiment
5.1 Experiment Setup
5.2 Consistency Check
5.3 Comparison to Random Forest
5.4 Case Study
6 Conclusion
References
Cost-Sensitive Churn Prediction in Fund Management Services
1 Introduction
2 Related Work
2.1 Churn Prediction
2.2 Imbalanced Data and Cost-Sensitive Learning
3 Problem Formulation
4 Model Design and Implementation
4.1 Our Learning Approach
4.2 Model Implementation
5 Experiments
5.1 Datasets
5.2 Evaluation Metrics
5.3 Baselines and Settings
5.4 Results and Analysis
6 Conclusions
References
Demonstration Track
A Movie Search System with Natural Language Queries
1 Introduction
2 Preliminary
3 The System Overview
4 Demonstration Overview
5 Summary
References
EventSys: Tracking Event Evolution on Microblogging Platforms
Abstract
1 Introduction
2 Architecture and Key Technologies of EventSys
2.1 Emotional Evolution Analysis
3 Demonstration
Acknowledgements
References
AdaptMX: Flexible Join-Matrix Streaming System for Distributed Theta-Joins
1 Introduction
2 System Overview and Key Techniques
3 Demonstration
References
A System for Spatial-Temporal Trajectory Data Integration and Representation
1 Introduction
2 System Design
2.1 Trajectory Data Description Format: TDDF
3 Case Study and Demonstration Outline
4 Conclusions
References
SLIND: Identifying Stable Links in Online Social Networks
1 Introduction
2 Method and Architecture of SLIND
3 Human Computer Interaction
4 Demonstration Plan
References
MusicRoBot: Towards Conversational Context-Aware Music Recommender System
1 Introduction
2 System Design
2.1 Music Knowledge Graph (MKG)
2.2 Scenario Design
2.3 Intent Recognition and Dialogue Management
3 Demonstration
References
HDUMP: A Data Recovery Tool for Hadoop
1 Introduction
2 HDUMP
2.1 HDUMP Overview
2.2 HDUMP Architecture
2.3 Fsimage Analyzer
2.4 Data Recovery Utilizing HDUMP
3 Demonstration and Evaluation
4 Conclusions
References
Modeling and Evaluating MID1 ICAL Pipeline on Spark
1 Introduction
2 Modeling MID1 ICAL Pipeline on Spark
2.1 MID1 ICAL Pipeline Overview
2.2 Cost Model
3 Comparisons of Different MID1 ICAL Pipeline on Spark
4 Evaluation
4.1 Evaluation Environments and Baselines
4.2 Comparisons of Different Spark Implementations of MID1 ICAL Pipeline
5 Conclusions
References
Correction to: Coverage-Oriented Diversification of Keyword Search Results on Graphs
Correction to: Chapter "Coverage-Oriented Diversification of Keyword Search Results on Graphs" in: J. Pei et al. (Eds.): Database Systems for Advanced Applications, LNCS 10828, https://doi.org/10.1007/978-3-319-91458-9_10
Author Index

Systemvoraussetzungen

Als PDF speichern Als Link merken