Decker / Lenz Advances in Data Analysis

Proceedings of the 30th Annual Conference of the Gesellschaft für Klassifikation e.V., Freie Universität Berlin, March 8-10, 2006
1. Auflage 2007
ISBN: 978-3-540-70981-7
Verlag: Springer-Verlag
Format: PDF
Kopierschutz: Adobe DRM (»Systemvoraussetzungen)

E-Book, Englisch, 689 Seiten

This book focuses on exploratory data analysis, learning of latent structures in datasets, and unscrambling of knowledge. Coverage details a broad range of methods from multivariate statistics, clustering and classification, visualization and scaling as well as from data and time series analysis. It provides new approaches for information retrieval and data mining and reports a host of challenging applications in various fields.

Autoren/Hrsg.

Decker, Reinhold

Lenz, Hans-Joachim

Inhaltsverzeichnis

1;Preface;6
2;Contents;9
3;Clustering;17
3.1;Mixture Models for Classification;18
3.2;How to Choose the Number of Clusters: The Cramer Multiplicity Solution;30
3.3;Model Selection Criteria for Model-Based Clustering of Categorical Time Series Data: A Monte Carlo Study;38
3.4;Cluster Quality Indexes for Symbolic Classification – An Examination;46
3.5;Semi-Supervised Clustering: Application to Image Segmentation;54
3.6;A Method for Analyzing the Asymptotic Behavior of the Walk Process in Restricted Random Walk Cluster Algorithm;66
3.7;Cluster and Select Approach to Classifier Fusion;74
3.8;Random Intersection Graphs and Classification;82
3.9;Optimized Alignment and Visualization of Clustering Results;90
3.10;Finding Cliques in Directed Weighted Graphs Using Complex Hermitian Adjacency Matrices;98
3.11;Text Clustering with String Kernels in R;106
3.12;Automatic Classification of Functional Data with Extremal Information;114
3.13;Typicality Degrees and Fuzzy Prototypes for Clustering;122
3.14;On Validation of Hierarchical Clustering;130
4;Classification;138
4.1;Rearranging Classified Items in Hierarchies Using Categorization Uncertainty;139
4.2;Localized Linear Discriminant Analysis;147
4.3;Calibrating Classifier Scores into Probabilities;155
4.4;Nonlinear Support Vector Machines Through Iterative Majorization and I- Splines;163
4.5;Deriving Consensus Rankings from Benchmarking Experiments;176
4.6;Classification of Contradiction Patterns;184
4.7;Selecting SVM Kernels and Input Variable Subsets in Credit Scoring Models;192
5;Data and Time Series Analysis;200
5.1;Simultaneous Selection of Variables and Smoothing Parameters in Geoadditive Regression Models;201
5.2;Modelling and Analysing Interval Data;209
5.3;Testing for Genuine Multimodality in Finite Mixture Models: Application to Linear Regression Models;221
5.4;Happy Birthday to You, Mr. Wilcoxon!;229
5.5;Equivalent Number of Degrees of Freedom for Neural Networks;241
5.6;Model Choice for Panel Spatial Models: Crime Modeling in Japan;249
5.7;A Boosting Approach to Generalized Monotonic Regression;257
5.8;From Eigenspots to Fisherspots – Latent Spaces in the Nonlinear Detection of Spot Patterns in a Highly Varying Background;267
5.9;Identifying and Exploiting Ultrametricity;275
5.10;Factor Analysis for Extraction of Structural Components and Prediction in Time Series;285
5.11;Classification of the U.S. Business Cycle by Dynamic Linear Discriminant Analysis;293
5.12;Examination of Several Results of Different Cluster Analyses with a Separate View to Balancing the Economic and Ecological Performance Potential of Towns and Cities;301
6;Visualization and Scaling Methods;309
6.1;VOS: A New Method for Visualizing Similarities Between Objects;310
6.2;Multidimensional Scaling of Asymmetric Proximities with a Dominance Point;318
6.3;Single Cluster Visualization to Optimize Air Traffic Management;330
6.4;Rescaling Proximity Matrix Using Entropy Analyzed by INDSCAL;337
7;Information Retrieval, Data and Web Mining;345
7.1;Canonical Forms for Frequent Graph Mining;346
7.2;Applying Clickstream Data Mining to Real- Time Web Crawler Detection and Containment Using ClickTips Platform;359
7.3;Plagiarism Detection Without Reference Collections;367
7.4;Putting Successor Variety Stemming to Work;375
7.5;Collaborative Filtering Based on User Trends;383
7.6;Investigating Unstructured Texts with Latent Semantic Analysis;391
8;Marketing, Management Science and Economics;399
8.1;Heterogeneity in Preferences for Odd Prices;400
8.2;Classification of Reference Models;408
8.3;Adaptive Conjoint Analysis for Pricing Music Downloads;416
8.4;Improving the Probabilistic Modeling of Market Basket Data;424
8.5;Classification in Marketing Research by Means of LEM2- generated Rules;432
8.6;Pricing Energy in a Multi-Utility Market;440
8.7;Disproportionate Samples in Hierarchical Bayes CBC Analysis;448
8.8;Building on the Arules Infrastructure for Analyzing Transaction Data with R;456
8.9;Balanced Scorecard Simulator – A Tool for Stochastic Business Figures;464
8.10;Integration of Customer Value into Revenue Management;472
8.11;Women’s Occupational Mobility and Segregation in the Labour Market: Asymmetric Multidimensional Scaling;480
8.12;Multilevel Dimensions of Consumer Relationships in the Healthcare Service Market M- L IRT vs. M- L SEM Approach;488
8.13;Data Mining in Higher Education;496
8.14;Attribute Aware Anonymous Recommender Systems;504
9;Banking and Finance;512
9.1;On the Notions and Properties of Risk and Risk Aversion in the Time Optimal Approach to Decision Making;513
9.2;A Model of Rational Choice Among Distributions of Goal Reaching Times;521
9.3;On Goal Reaching Time Distributions Estimated from DAX Stock Index Investments;529
9.4;Credit Risk of Collaterals: Examining the Systematic Linkage between Insolvencies and Physical Assets in Germany;537
9.5;Foreign Exchange Trading with Support Vector Machines;545
9.6;The Influence of Specific Information on the Credit Risk Level;553
10;Bio- and Health Sciences;561
10.1;Enhancing Bluejay with Scalability, Genome Comparison and Microarray Visualization;562
10.2;Discovering Biomarkers for Myocardial Infarction from SELDI- TOF Spectra;574
10.3;Joint Analysis of In-situ Hybridization and Gene Expression Data;582
10.4;Unsupervised Decision Trees Structured by Gene Ontology ( GO- UDTs) for the Interpretation of Microarray Data;590
11;Linguistics and Text Analysis;598
11.1;Clustering of Polysemic Words;599
11.2;Classifying German Questions According to Ontology- Based Answer Types;607
11.3;The Relationship of Word Length and Sentence Length: The Inter- Textual Perspective;615
11.4;Comparing the Stability of Different Clustering Results of Dialect Data;623
11.5;Part-of-Speech Discovery by Clustering Contextual Features;631
12;Statistical Musicology and Sound Classification;639
12.1;A Probabilistic Framework for Audio-Based Tonal Key and Chord Recognition;640
12.2;Using MCMC as a Stochastic Optimization Procedure for Monophonic and Polyphonic Sound;648
12.3;Vowel Classification by a Neurophysiologically Parameterized Auditory Model;656
13;Archaeology;664
13.1;Uncovering the Internal Structure of the Roman Brick and Tile Making in Frankfurt- Nied by Cluster Validation;665
13.2;Where Did I See You Before... A Holistic Method to Compare and Find Archaeological Artifacts;673
14;Keywords;683
15;Author Index;687