Analysis of Large and Complex Data

Editors: Adalbert F.X. Wilhelm, Hans A. Kestler



Offers a snapshot of the state-of-the-art in classification at the interface between statistics, computer science and application fields

With contributions from a variety of interdisciplinary fields

Showcases the strong role of computational techniques in data analysis and classification

This book offers a snapshot of the state-of-the-art in classification at the interface between statistics, computer science and application fields. The contributions span a broad spectrum, from theoretical developments to practical applications; they all share a strong computational component. The topics addressed are from the following fields: Statistics and Data Analysis; Machine Learning and Knowledge Discovery; Data Analysis in Marketing; Data Analysis in Finance and Economics; Data Analysis in Medicine and the Life Sciences; Data Analysis in the Social, Behavioural, and Health Care Sciences; Data Analysis in Interdisciplinary Domains; Classification and Subject Indexing in Library and Information Science.

The book presents selected papers from the Second European Conference on Data Analysis, held at Jacobs University Bremen in July 2014. This conference unites diverse researchers in the pursuit of a common topic, creating truly unique synergies in the process.

Table of contents (55 chapters)

Front Matter

Invited Papers
• Front Matter
• Latent Variables and Marketing Theory: The Paradigm Shift
• Business Intelligence in the Context of Integrated Care Systems (ICS): Experiences from the ICS “Gesundes Kinzigtal” in Germany
• Clustering and a Dissimilarity Measure for Methadone Dosage Time Series
• Linear Storage and Potentially Constant Time Hierarchical Clustering Using the Baire Metric and Random Spanning Paths
• Standard and Novel Model Selection Criteria in the Pairwise Likelihood Estimation of a Mixture Model for Ordinal Data

Big Data
• Front Matter
• Textual Information Localization and Retrieval in Document Images Based on Quadtree Decomposition
• Selection Stability as a Means of Biomarker Discovery in Classification
• Active Multi-Instance Multi-Label Learning
• Using Annotated Suffix Tree Similarity Measure for Text Summarisation
• Big Data Classification : Aspects on Many Features and Many Observations

Clustering
• Front Matter
• Bottom-Up Variable Selection in Cluster Analysis Using Bootstrapping: A Proposal
• A Comparison Study for Spectral, Ensemble and Spectral-Mean Shift Clustering Approaches for Interval-Valued Symbolic Data
• Supervised Pre-processings Are Useful for Supervised Clustering
• Similarity Measures on Concept Lattices

Classification
• Front Matter
• Multivariate Functional Regression Analysis with Application to Classification Problems
• Incremental Generalized Canonical Correlation Analysis
• Evaluating the Necessity of a Triadic Distance Model
• Assessing the Reliability of a Multi-Class Classifier

Regression and Other Statistical Techniques
• Front Matter
• Reviewing Graphical Modelling of Multivariate Temporal Processes
• The Weight of Penalty Optimization for Ridge Regression

• Monitoring a Dynamic Weighted Majority Method Based on Datasets with Concept Drift

Applications
• Front Matter
• Specialization in Smart Growth Sectors vs. Effects of Change of Workforce Numbers in the European Union Regional Space
• Evaluation of the Individually Perceived Quality from Head-Up Display Images Relating to Distortions
• Minimizing Redundancy Among Genes Selected Based on the Overlapping Analysis
• The Identification of Relations Between Smart Specialization and Sensitivity to Crisis in the European Union Regions

Data Analysis in Marketing
• Front Matter
• Market Oriented Product Design and Pricing: Effects of Intra-Individual Varying Partworths
• The Use of Hybrid Predictive C&RT-Logit Models in Analytical CRM

Data Analysis in Finance
• Front Matter
• Excess Takeover Premiums and Bidder Contests in Merger & Acquisitions: New Methods for Determining Abnormal Offer Prices
• Firm-Specific Determinants on Dividend Changes: Insights from Data Mining
• Selection of Balanced Structure Samples in Corporate Bankruptcy Prediction
• Facilitating Household Financial Plan Optimization by Adjusting Time Range of Analysis to Life-Length Risk Aversion
• Dynamic Aspects of Bankruptcy Prediction Logit Model for Manufacturing Firms in Poland

Data Analysis in Medicine and Life Sciences
• Front Matter
• Estimating Age- and Height-Specific Percentile Curves for Children Using GAMLSS in the IDEFICS Study
• An Ensemble of Optimal Trees for Class Membership Probability Estimation
• Ensemble of Subset of k-Nearest Neighbours Models for Class Membership Probability Estimation

Data Analysis in Musicology
• Front Matter
• The Surprising Character of Music: A Search for Sparsity in Music Evoked Body Movements
• Comparing Audio Features and Playlist Statistics for Music Classification
• Duplicate Detection in Facsimile Scans of Early Printed Music
• Fast Model Based Optimization of Tone Onset Detection by Instance Sampling
• Recognition of Leitmotives in Richard Wagner’s Music: An Item Response Theory Approach


Data Analysis in Interdisciplinary Domains
• Front Matter
• Optimization of a Simulation for Inhomogeneous Mineral Subsoil Machining
• Fast and Robust Isosurface Similarity Maps Extraction Using Quasi-Monte Carlo Approach
• Analysis of ChIP-seq Data Via Bayesian Finite Mixture Models with a Non-parametric Component
• Information Theoretic Measures for Ant Colony Optimization
• A Signature Based Method for Fraud Detection on E-Commerce Scenarios
• Three-Way Clustering Problems in Regional Science

Data Analysis in Social, Behavioural and Health Care Sciences
• Front Matter
• CFA-MTMM Model in Comparative Analysis of 5-, 7-, 9-, and 11-point A/D Scales
• Biasing Effects of Non-Representative Samples of Quasi-Orders in the Assessment of Recovery Quality of IITA-Type Item Hierarchy Mining
• Correlated Component Regression: Profiling Student Performances by Means of Background Characteristics
• Analysing Psychological Data by Evolving Computational Models
• Use of Panel Data Analysis for V4 Households Poverty Risk Prediction

Data Analysis in Library Science
• Front Matter
• Collaborative LiteratureWork in the Research Publication Process: The Cogeneration of Citation Networks as Example
• Subject Indexing of Textbooks: Challenges in the Construction of a Discovery System
• The Ofness and Aboutness of Survey Data: Improved Indexing of Social Science Questionnaires
• Subject Indexing for Author Name Disambiguation: Opportunities and Challenges

Back Matter

原版 PDF + EPUB: