Cooperation in Classification and Data Analysis (eBook)

Proceedings of Two German-Japanese Workshops

Akinori Okada, Tadashi Imaizumi, Hans-Hermann Bock, Wolfgang A. Gaul (Herausgeber)

eBook Download: PDF

2009 | 2009
XII, 208 Seiten
Springer Berlin (Verlag)
978-3-642-00668-5 (ISBN)

Infos

This volume presents theories, models, algorithms, and applications in clustering, classification, and visualization. It also includes applications of clustering, classification, and visualization in various fields such as marketing, recommendation system, biology, sociology, and social survey. The contributions give insight into new models and concepts and show the variety of research in clustering, classification, and visualization.

Inhalt

Preface 5
Contents 7
Contributors 9
Classification and Visualization 12
Analyzing Symbolic Data: Problems, Methods, and Perspectives 13
1 Introduction 13
2 Visualization Tools: Zoom Stars and Principal Component Analysis 14
3 Dissimilarity Between Data Rectangles 15
4 Average Intervals and Class Prototypes: Centrocubes 16
5 Partitioning Clustering Methods 18
6 A Parametric Probabilistic Approach for Clustering Interval Data 19
7 FinalRemarks 21
References 21
Constraining Shape and Size in Clustering 23
1 Introduction 23
2 Mixture Models and the EM Algorithm 24
3 Fuzzy Clustering 25
4 Constraining Cluster Parameters 28
5 Experiments 32
6 Conclusions 34
References 35
Dissolution and Isolation Robustness of Fixed Point Clusters 36
1 Introduction 36
2 Robustness Concepts 37
3 Fixed Point Clusters 39
4 Proofs 45
References 47
ADCLUS: A Data Model for the Comparison of Two- Mode Clustering Methods by Monte Carlo Simulation 49
1 Introduction 49
2 The ADCLUS Model as a General Model for Generating Clustered Data 50
3 An Exemplifying Simulation Study 54
4 Conclusions 57
References 58
Density-Based Multidimensional Scaling 60
1 Introduction 60
2 Sammon's Mapping 61
3 Density-Based Mappings 62
4 Results 65
5 Conclusions 67
References 67
Classification of Binary Data Using a Spherical Distribution 68
1 Introduction 68
2 Transformation Binary Data into Directional Data 69
3 Distribution on a Hypersphere 71
4 Discriminant Function 73
5 Numerical Experiments 74
6 Concluding Remarks 75
References 76
Fuzzy Clustering Based Regression with Attribute Weights 77
1 Introduction 77
2 Fuzzy Clustering Considering Attributes 78
3 Fuzzy Cluster Loading Model 79
4 A Weighted Regression Analysis Using Fuzzy Clustering 81
5 Attribute Based Fuzzy Cluster Loading Model and a Fuzzy Weighted Regression Analysis 81
6 Numerical Example 82
7 Conclusion 85
References 85
Polynomial Regression on a Dependent Variable with Immeasurable Observations 87
1 Introduction 87
2 Preliminaries 88
3 Likelihood Functions 89
4 Simulation Studies 90
5 Conclusion 93
References 94
Methods in Fields 95
Feedback Options for a Personal News Recommendation Tool 96
1 Introduction 96
2 Interest Profiles 97
3 Feedback Options 98
4 Web Page Classification 99
5 Evaluation Method 100
6 Empirical Results 101
7 Conclusions 102
References 103
Classification in Marketing Science 104
1 Introduction 104
2 Data Description and Preprocessing 105
3 Growing Bisecting k-Means: A Methodological Outline 106
4 Application to Marketing Text Corpus 108
5 Conclusions 110
References 110
Deriving a Statistical Model for the Prediction of Spiralling in BTA Deep- Hole- Drilling from a Physical Model 112
1 Introduction 112
2 Physical Model 114
3 Statistical Model 115
4 Summary and Outlook 118
References 119
Analyzing Protein-Protein Interaction with Variant Analysis 120
1 Introduction 120
2 Parameter Estimation Under Ambiguity and Contamination 121
3 Study of a Protein-Protein Interaction 124
References 127
Estimation for the Parameters in Geostatistics 128
1 Introduction 128
2 Using Geostatistics for Prediction 129
3 Non-negative Least Squares Method for Nonlinear Model ( NNLS) 132
4 Numerical Example 134
5 Conclusion and Future Research 135
Identifying Patients at Risk: Mining Dialysis Treatment Data 136
1 Introduction 136
2 Background and RelatedWork 137
3 The Data-set 138
4 Standard Model 139
5 Temporal Model 140
6 MixedModel 143
7 Summary and Outlook 144
References 144
Sequential Multiple Comparison Procedure for Finding a Changing Point in Dose Finding Test 146
1 Introduction 146
2 Sequential Multiple Comparison Procedure 147
3 Critical Value 148
4 Power of Test and Necessary Sample Size 149
5 A Simulation Study 150
6 A Case Study 151
7 Conclusions 152
References 154
Semi-supervised Clustering of Yeast Gene Expression Data 155
1 Introduction 155
2 Methods 156
3 Results 159
4 Conclusion 161
References 162
Event Detection in Environmental Scanning: News from a Hospitality Industry Newsletter 164
1 Introduction 164
2 Data Description and Preprocessing 165
3 Methodology 166
4 Discussion and Conclusions 171
References 171
Applications in Clustering and Visualization 172
External Asymmetric Multidimensional Scaling Study of Regional Closeness in Marriage Among Japanese Prefectures 173
1 Introduction 173
2 TheData 174
3 TheMethod 174
4 The Analysis 175
5 Results 175
6 Discussion 177
References 180
Socioeconomic and Age Differences in Women's Cultural Consumption: Multidimensional Preference Analysis 181
1 Social Patterning of Cultural Consumption 181
2 Data 182
3 Results 183
4 Discussion and Conclusion 188
References 188
Analysis of Purchase Intentions at a Department Store by Three- Way Distance Model 190
1 Introduction 190
2 Data 191
3 Analysis 192
4 Results 193
5 Discussion 195
References 197
Facet Analysis of the AsiaBarometer Survey: Well- being, Trust and Political Attitudes 198
1 Introduction 198
2 Results of Data Analysis 199
3 Conclusion 204
References 205
Author Index 206
Subject Index 207

Produkt-Details

• Erscheint lt. Verlag: 17.6.2009
• Reihe/Serie: Studies in Classification, Data Analysis, and Knowledge Organization
• Reihe/Serie: Studies in Classification, Data Analysis, and Knowledge Organization
• Zusatzinfo: XII, 208 p. 55 illus., 11 illus. in color.
• Verlagsort: Berlin
• Sprache: englisch
• Themenwelt: Mathematik / Informatik ► Informatik ► Datenbanken
• Themenwelt: Mathematik / Informatik ► Mathematik ► Statistik
• Themenwelt: Mathematik / Informatik ► Mathematik ► Wahrscheinlichkeit / Kombinatorik
• Themenwelt: Technik
• Themenwelt: Wirtschaft ► Betriebswirtschaft / Management ► Unternehmensführung / Management
• Schlagworte: algorithms • Biology • classification • Clustering • Data Analysis • Model • Multidimensional Scaling • multivariate analysis • Statistica • Variable • Visualization
• ISBN-10: 3-642-00668-X / 364200668X
• ISBN-13: 978-3-642-00668-5 / 9783642006685