Between Data Science and Applied Data Analysis: Proceedings of the 26th Annual Conference of the Gesellschaft Für Klassifikation E.V., University of M

ISBN-13: 9783540403548 / Angielski / Miękka / 2003 / 694 str.

Gesellschaft F Ur Klassifikation; Martin Schader; Wolfgang Gaul

Opis

The volume presents new developments in data analysis and classification and gives an overview of the state of the art in these scientific fields and relevant applications. Areas that receive considerable attention in the book are clustering, discrimination, data analysis, and statistics, as well as applications in economics, biology, and medicine it provides recent technical and methodological developments and a large number of application papers demonstrating the usefulness of the newly developed techniques.

Spis treści

Robust Classification Through the Forward Search.- Fitting and Smoothing Properties of Length Constrained Smoothers Applied to Time Series.- Interaction Terms in Non-linear PLS via Additive Spline Transformation.- Discriminant Analysis With Categorical Variables: A Biplot Based Approach.- Efficient Density Clustering Using Basin Spanning Thees.- Some Issues on Clustering of Functional Data.- Scalable Clustering of High Dimensional Data.- Methods to Combine Classification Trees.- Core-Based Clustering Techniques.- Combining Regression Trees and Radial Basis Function Networks in Longitudinal Data Modelling.- Implementing a new Method for Discriminant Analysis When Group Covariance Matrices are Nearly Singular.- Two Approaches for Discriminant Partial Least Squares.- Improving the Classification Performance of a Discriminant Rule by Dealing With Data Cases Having a Substantial Influence on Variable Selection.- Classification and Clustering of Vocal Performances.- Cluster- and Discriminant Analysis With Both Metric and Categorial Data.- Multivariate Mixture Models Estimation: A Genetic Algorithm Approach.- Two-Way Clustering for Contingency Tables: Maximizing a Dependence Measure.- Localised Mixtures of Experts for Mixture of Regressions.- A Bayesian Approach for the Estimation of the Covariance Structure of Separable Spatio-Temporal Stochastic Processes.- An Algorithm for the HICLAS-R Model.- Some Applications of Time-Varying Coefficient Models to Count Data.- On Ziggurats and Dendrograms.- A Dimensionality Reduction Method Based on Simple Linear Regressions.- Evolutionary Strategies to Avoid Local Mimima in Multidimensional Scaling.- Principal Component Analysis of Boolean Symbolic Objects.- Multivariate Analysis for Variables of Arbitrary Information Level.- How Wrong Models Become Useful — and Correct Models Become Dangerous.- Visualizing Symbolic Data by Closed Shapes.- LBGU-EM Algorithm for Mixture Density Estimation.- Change-Points in Bernoulli Trials With Dependence.- Two-Mode Clustering Methods: Compare and Contrast.- Sensitivity of Graphical Modeling Against Contamination.- New Graphical Symbolic Objects Representations in Parallel Coordinates.- A Hierarchical Classes Approach to Discriminant Analysis.- Prediction Optimal Data Analysis by Means of Stochastic Search.- System Error Variance Tuning in State-Space Models.- Corrado Gini and Multivariate Statistical Analysis: The (so far) Missing Link.- On Correspondence Analysis of Incomplete Orderings.- Some Statistical Issues in Microarray Data Analysis.- Background of the Variability in Past Human Populations: Selected Methodological Issues.- Spatial Prediction With Space-Time Models.- Neural Budget Networks of Sensorial Data.- Evolutionary Model Selection in Bayesian Neural Networks.- Extreme Datamining 387.- Information Filtering Based on Modal Symbolic Objects.- Analyzing Learner Behavior and Performance.- An Integration Strategy for Distributed Recommender Services in Legacy Library Systems.- Comparing Simple Association-Rules and Repeat-Buying Based Recommender Systems in a B2B Environment.- Students’ Preferences Related to Web Based E-Learning: Results of a Survey.- MURBANDY: The (so far) Missing Link: User-Friendly Retrieval and Visualization of Geographic Information.- ASCAID: Using an Asymmetric Correlation Measure for Automatic Interaction Detection 447.- Discriminative Clustering: Vector Quantization in Learning Metrics.- Neural Network Hybrid Learning: Genetic Algorithms & Levenberg-Marquardt.- Syntagmatic and Paradigmatic Associations in Information Retrieval.- Finding the Most Useful Clusters: Clustering and the Usefulness Metric.- Internet Thesaurus — Extracting Relevant Terms from WWW Pages using Weighted Threshold Function over a Cross-Reference Matrix.- Reflections on a Supervised Approach to Independent Component Analysis.- Simulated Annealing and Tabu Search for Optimization of Neural Networks.- Decentralizing Risk Management in the Case of Quadratic Hedging.- Multimedia Stimulus Presentation Methods for Conjoint Studies in Marketing Research.- Forecasting the Customer Development of a Publishing Company with Decision Trees.- Estimation of Default Probabilities in a Single-Factor Model.- Simultaneous Confidence Intervals for Default Probabilities.- Model-Based Clustering With Hidden Markov Models and its Application to Financial Time-Series Data.- Classification of Multivariate Data With Missing Values Using Expected Discriminant Scores.- Assessment of the Polish Manufacturing Sector Attractiveness: An End-User Approach.- Developing a Layout of a Supermarket Through Asymmetric Multidimensional Scaling and Cluster Analysis of Purchase Data.- Market Segmentation Method From the Bayesian Viewpoint.- Support Vector Machines for Credit Scoring: Comparing to and Combining With Some Traditional Classification Methods.- Classification of Amino-Acid Sequences Using State-Space Models.- Quantitative Study of Images in Archaeology: I. Textual Coding.- Quantitative Study of Images in Archaeology: II. Symbolic Coding.- Power Functions in Multiple Sampling Plans Using DNA Computation.- Methodological Issues in the Baffling Relationship Between Hepatitis C Virus and Non Hodgkin’s Lymphomas.- Class Discovery in Gene Expression Data: Characterizing Splits by Support Vector Machines.- Efficient Clustering Methods for Tumor Classification With Microarrays.- A Method to Classify Microarray Data.