Advances in Data Mining. Applications and Theoretical Aspects
12th Industrial Conference, ICDM 2012, Berlin, Germany, July 13-20, 2012. Proceedings
Published on 9. July 2012
XI, 289 pages
978-3-642-31488-9 (ISBN)
Description
This book constitutes the refereed proceedings of the 12th Industrial Conference on Data Mining, ICDM 2012, held in Berlin, Germany in July 2012.
The 22 revised full papers presented were carefully reviewed and selected from 97 submissions. The papers are organized in topical sections on data mining in medicine and biology; data mining for energy industry; data mining in traffic and logistic; data mining in telecommunication; data mining in engineering; theory in data mining; theory in data mining: clustering; theory in data mining: association rule mining and decision rule mining.
More details
Other editions
Additional editions
Petra Perner
Advances in Data Mining. Applications and Theoretical Aspects
12th Industrial Conference, ICDM 2012, Berlin, Germany, July 13-20, 2012. Proceedings
Book
07/2012
Springer
€49.22
Shipment within 7-9 days
Content
- Title Page
- Preface
- Organization
- Table of Contents
- Data Mining in Medicine and Biology
- Application of Classification Algorithms on IDDM Rat Data
- Introduction
- Background and Research Status
- Data
- Experimental Results
- Validation
- Discussion
- References
- Research Themes in the Case-Based Reasoning in Health Sciences Core Literature
- Introduction
- Model of the Decision Support System
- Experimental Results
- Experimental Results Using No.1 Datasets
- Experimental Results Using No.2 Datasets
- Evaluation of the Best Classification Model Obtained
- Conclusions
- References
- SOHAC: Efficient Storage of Tick Data That Supports Search and Analysis
- Introduction
- Related Work
- Decomposition of Tick Data Matrix Based on Clustering
- An Illustrative Example
- Definitions and Problem Formulation
- Clustering of Columns of Tick Data Matrix
- SOHAC: Storage-Optimizing Hierarchical Agglomerative Clustering
- Experiments
- Experimental Settings
- Results
- Conclusion
- References
- Data Mining for Energy Industry
- Electricity Consumption Time Series Profiling: A Data Mining Application in Energy Industry
- Introduction
- Methodology
- The Finnish Business Case
- The Experiment
- Results and Analysis
- Cluster Profiles
- Consumption Time Series Profiling
- Conclusion
- References
- Wind Turbines Fault Diagnosis Using Ensemble Classifiers
- Introduction
- Description of the Test-Bed and Measurement Procedure
- Variables Analyzed
- Fault Analysis by Ensemble Classifiers
- Results
- Success Rate
- Confusion Matrix
- Conclusions
- References
- Data Mining in Traffic and Logistic
- Bus Bunching Detection by Mining Sequences of Headway Deviations
- Introduction
- Problem Overview
- Related Work
- Motivation and Scope
- Methodology
- Mining Time Series Sequences
- Methodology
- Dataset
- Results
- Discussion
- Conclusions and Future Work
- References
- Data Mining in Telecommunication
- Detecting Abnormal Patterns in Call Graphs Based on the Aggregation of Relevant Vertex Measures
- Introduction
- Evolving Call Graphs
- Relevance Vertex Measures
- Vertex Usage (M1)
- Degree of Centrality (M2)
- Closeness Centrality (M3)
- Vertex Interest (M4)
- Finding Abnormal Vertices
- Detecting Potential Fraud Situations in Call Graphs
- Conclusions
- References
- Data Mining in Engineering
- Real-Time Mass Flow Estimation in Circulating Fluidized Bed
- Introduction
- Control Reconfiguration
- Advantages of CBR for the Reconfiguration Task
- Adequacy of CRB for Reconfiguration
- Representation in Case-Based Reasoning
- Proposition of a Case Representation
- Problem Representation
- Solution Representation
- A Case Study
- Conclusion
- References
- Representation in Case-Based Reasoning Applied to Control Reconfiguration
- Introduction
- Control Reconfiguration
- Advantages of CBR for the Reconfiguration Task
- Adequacy of CRB for Reconfiguration
- Representation in Case-Based Reasoning
- Proposition of a Case Representation
- Problem Representation
- Solution Representation
- A Case Study
- Conclusion
- References
- The Influence of Input and Output Measurement Noise on Batch-End Quality Prediction with Partial Least Squares
- Introduction
- Multiway Partial Least Squares Modelling
- Data Matrix Unfolding
- Multiway Partial Least Squares (MPLS)
- Online Batch-End Quality Prediction
- Model Order and Input Variable Selection
- Model Order Selection
- Input Variable Selection
- Case Study
- Results and Discussion
- Input Measurement Noise
- Input Variable and Model Order Selection
- Offline Quality Prediction
- Online Quality Prediction
- Output Measurement Noise
- Input Variable and Model Order Selection
- Offline Quality Prediction
- Online Quality Prediction
- Conclusions
- References
- Theory in Data Mining
- An Evolving Associative Classifier for Incomplete Database
- Introduction
- Rules and Classification
- Class Association Rules in Incomplete Database
- Building a Multi Rules Based Classifier
- Rule Mining Method
- Genetic Network Programming
- Basic Ideas of Rule Representation
- Calculation of Rule Measurements
- Genetic Operations and Fitness Function
- Evolving Classifier Using Labeled Instances
- Experimental Results
- Classification for Incomplete Database
- Evaluation of Evolving Classifier
- Conclusions
- References
- Improving Classifier Performance by Knowledge-Driven Data Preparation
- Introduction
- Introducing an Advanced Framework Focused on Data Preparation
- Advanced Framework for Data Preparation
- Variable Derivation
- Case Study on Variable Derivation
- Experimental Setup
- Results
- Conclusion, Limitations and Future Directions
- References
- CWFM: Closed Contingency Weighted Frequent Itemsets Mining
- Introduction
- Related Work and Problem Definition
- Related Work
- Problem Definition
- CWFM
- Preprocessing
- Contingency Weight
- Contingency Weight Pattern
- FP (Frequent Pattern) Tree Structure
- CWFM Algorithm
- Experimental Results
- Performance Comparison
- Conclusion
- References
- Prognostic Modeling with High Dimensional and Censored Data
- Introduction
- Regression Learning Sets with Different Structure
- Linear Separability of Survival Learning Sets
- Convex and Piecewise Linear (CPL) Criterion Function for Survival Data Sets
- Selection of Prognostic Feature Subset with the Use of the RLS Method
- Example 1: Prognostic Model Selection on High Dimensional Synthetic Data Set
- Example 2: Prognostic Model Selection on the Breast Cancer Survival Data Set
- Concluding Remarks
- References
- Theory in Data Mining: Clustering
- SHACUN: Semi-supervised Hierarchical Active Clustering Based on Ranking Constraints
- Introduction
- Motivating Example
- Related Work
- Constraints Ranking Model
- Constraints
- Formal Semantic Of Strict Partial Order Of Constraints
- Constraints Ranking Engineering
- A. Non-numerical Base Constraints
- B. Complex Ranking Constraints
- SHACUN Semi-supervised Hierarchical Active ClUstering Based on raNking constraints algorithm
- Similarity Metric
- SHACUN Process
- Experimental Results
- SHACUN Performance Assessment
- Analysis Of The Function Criterion
- Analysis of the Granted Responsibility Criterion
- Analysis of the Source Of Group Identification Criterion
- Analysis of the Dynamicity Criterion
- Overall Performance Of SHACUN Approach vs. Related Approaches In The Literature
- Conclusion
- References
- A Minimum Spanning Tree-Inspired Clustering-Based Outlier Detection Technique
- Introduction
- Related Work
- Distance-Based Outlier Detection
- Density-Based Outlier Detection
- Clustering-Based Outlier Detection
- An Improved MST-Based Outlier Detection Algorithm
- A Simple Idea
- Detecting Local Outliers
- Our MST-Clustering Based Outlier Detection Algorithm
- A Performance Study
- Performance of Our Algorithm on Synthetic Data
- Performance of Our Algorithm on Real Data
- Conclusion
- References
- Theory in Data Mining: Association Rule Mining and Decision Rule Mining
- ML-DS: A Novel Deterministic Sampling Algorithm for Association Rules Mining
- Introduction
- Related Work
- Mining Algorithms
- Sampling Algorithms
- The Sampling Process
- The DSelect Algorithm
- The ML-DS Algorithm
- Experimental Results
- Setup
- Discussion
- Conclusions and Future Work
- References
- Decision Rules Development Using Set of Generic Operations Approach
- Introduction
- Theoretical Background
- Methods Used during Research
- Generic Operations Algorithm
- Other Rule Induction Algorithms
- Classification Process
- Investigated Datasets
- Obtained Results
- Conclusions
- References
- Text Mining
- Redundant Dictionary Spaces as a General Concept for the Analysis of Non-vectorial Data
- Handling Non-vectorial Data the Usual Way
- The Redundant Dictionary Space
- The Redundant Dictionary Mapping Process
- Mapping
- Tightening
- Inner Product Kernel
- Numerical Experiments
- Reuters Newswire Articles
- Stock Market Data
- Image Data
- Conclusion
- References
- Human-Centered Text Mining: A New Software System
- Introduction
- CORDIET Project Setup
- Student Groups
- Software Architecture
- Data Sources
- Data Source BVH
- Data Source Scientific Articles
- Data Source Clinical Pathways
- Data Source Pedophiles
- Functionality of the CORDIET Software
- Case Studies
- Care Process Analysis
- Domestic Violence under Scrutiny
- Identifying Human Trafficking Suspects
- Profiling Human Trafficking Suspects
- Analyzing Chat Conversations of Pedophiles
- FCA Literature Study
- Discussion, Conclusions and Future Work
- References
- Text Mining Scientific Papers: A Survey on FCA-Based Information Retrieval Research
- Introduction
- Formal Concept Analysis
- Dataset
- FCA-Based Information Retrieval Research
- Knowledge Representation and Browsing with FCA
- Query Result Improvement with FCA
- Web and Email Retrieval
- Image, Software and Knowledge Base Retrieval
- Defining and Processing Complex Queries with FCA
- Domain Knowledge in Search Results: Contextual Answers and Ranking
- Conclusions
- References
- Author Index
