Multiple Classifier Systems

Nikunj C. Oza

ISBN 10: 3540263063 / ISBN 13: 9783540263067

Editore: Springer Berlin Heidelberg, Springer Berlin Heidelberg Jun 2005, 2005

Riguardo questo articolo

Neuware -The belief that a committee of people make better decisions than any individual is widely held and appreciated. We also understand that, for this to be true, the members of the committee have to be simultaneously competent and comp- mentary. This intuitive notion holds true for committees of data sources (such as sensors) and models (such as classi ers). The substantial current research in the areas of data fusion and model fusion focuses on ensuring that the di - ent sources provide useful information but nevertheless complement one another to yield better results than any source would on its own. During the 1990s, a variety of schemes in classi er fusion, which is the focus of this workshop, were developed under many names in di erent scienti c communities such as machine learning, pattern recognition, neural networks, and statistics. The previous ve workshops on Multiple Classi er Systems (MCS) were themselves exercises in information fusion, with the goal of bringing the di erent scienti c commu- ties together, providing each other with di erent perspectives on this fascinating topic, and aiding cross-fertilization of ideas. These ve workshops achieved this goal, demonstrating signi cant advances in the theory, algorithms, and appli- tions of multiple classi er systems. Followingits vepredecessorspublishedbySpringer,thisvolumecontainsthe proceedings of the 6th International Workshop on Multiple Classi er Systems (MCS2005)heldattheEmbassySuitesinSeaside,California,USA,June13¿15, 2005. Forty-two papers were selected by the Scienti c Committee, and they were organized into the following sessions: Boosting, Combination Methods, Design of Ensembles, Performance Analysis, and Applications.Springer Verlag GmbH, Tiergartenstr. 17, 69121 Heidelberg 444 pp. Englisch.

Codice articolo 9783540263067

Dati bibliografici

• Titolo: Multiple Classifier Systems
• Editore: Springer Berlin Heidelberg, Springer Berlin Heidelberg Jun 2005
• Data di pubblicazione: 2005
• Lingua: Inglese
• ISBN 10: 3540263063
• ISBN 13: 9783540263067
• Rilegatura: Taschenbuch
• Condizione: Neu
• Dimensioni: 235 L x 155 A x 24 P (millimetri) 235 millimetri di larghezza per 155 millimetri di altezza per 24 millimetri di profondità
• Peso: 668 grammi

Descrizione articolo

Riassunto

The belief that a committee of people make better decisions than any individual is widely held and appreciated. We also understand that, for this to be true, the members of the committee have to be simultaneously competent and comp- mentary. This intuitive notion holds true for committees of data sources (such as sensors) and models (such as classi?ers). The substantial current research in the areas of data fusion and model fusion focuses on ensuring that the di?- ent sources provide useful information but nevertheless complement one another to yield better results than any source would on its own. During the 1990s, a variety of schemes in classi?er fusion, which is the focus of this workshop, were developed under many names in di?erent scienti?c communities such as machine learning, pattern recognition, neural networks, and statistics. The previous ?ve workshops on Multiple Classi?er Systems (MCS) were themselves exercises in information fusion, with the goal of bringing the di?erent scienti?c commu- ties together, providing each other with di?erent perspectives on this fascinating topic, and aiding cross-fertilization of ideas. These ?ve workshops achieved this goal, demonstrating signi?cant advances in the theory, algorithms, and appli- tions of multiple classi?er systems. Followingits?vepredecessorspublishedbySpringer,thisvolumecontainsthe proceedings of the 6th International Workshop on Multiple Classi?er Systems (MCS2005)heldattheEmbassySuitesinSeaside,California,USA,June13 15, 2005. Forty-two papers were selected by the Scienti?c Committee, and they were organized into the following sessions: Boosting, Combination Methods, Design of Ensembles, Performance Analysis, and Applications.

Contenuti

Future Directions.- Semi-supervised Multiple Classifier Systems: Background and Research Directions.- Boosting.- Boosting GMM and Its Two Applications.- Boosting Soft-Margin SVM with Feature Selection for Pedestrian Detection.- Observations on Boosting Feature Selection.- Boosting Multiple Classifiers Constructed by Hybrid Discriminant Analysis.- Combination Methods.- Decoding Rules for Error Correcting Output Code Ensembles.- A Probability Model for Combining Ranks.- EER of Fixed and Trainable Fusion Classifiers: A Theoretical Study with Application to Biometric Authentication Tasks.- Mixture of Gaussian Processes for Combining Multiple Modalities.- Dynamic Classifier Integration Method.- Recursive ECOC for Microarray Data Classification.- Using Dempster-Shafer Theory in MCF Systems to Reject Samples.- Multiple Classifier Fusion Performance in Networked Stochastic Vector Quantisers.- On Deriving the Second-Stage Training Set for Trainable Combiners.- Using Independence Assumption to Improve Multimodal Biometric Fusion.- Design Methods.- Half-Against-Half Multi-class Support Vector Machines.- Combining Feature Subsets in Feature Selection.- ACE: Adaptive Classifiers-Ensemble System for Concept-Drifting Environments.- Using Decision Tree Models and Diversity Measures in the Selection of Ensemble Classification Models.- Ensembles of Classifiers from Spatially Disjoint Data.- Optimising Two-Stage Recognition Systems.- Design of Multiple Classifier Systems for Time Series Data.- Ensemble Learning with Biased Classifiers: The Triskel Algorithm.- Cluster-Based Cumulative Ensembles.- Ensemble of SVMs for Incremental Learning.- Performance Analysis.- Design of a New Classifier Simulator.- Evaluation of Diversity Measures for Binary Classifier Ensembles.- Which Is the Best Multiclass SVM Method? An Empirical Study.- Over-Fitting in Ensembles of Neural Network Classifiers Within ECOC Frameworks.- Between Two Extremes: Examining Decompositions of the Ensemble Objective Function.- Data Partitioning Evaluation Measures for Classifier Ensembles.- Dynamics of Variance Reduction in Bagging and Other Techniques Based on Randomisation.- Ensemble Confidence Estimates Posterior Probability.- Applications.- Using Domain Knowledge in the Random Subspace Method: Application to the Classification of Biomedical Spectra.- An Abnormal ECG Beat Detection Approach for Long-Term Monitoring of Heart Patients Based on Hybrid Kernel Machine Ensemble.- Speaker Verification Using Adapted User-Dependent Multilevel Fusion.- Multi-modal Person Recognition for Vehicular Applications.- Using an Ensemble of Classifiers to Audit a Production Classifier.- Analysis and Modelling of Diversity Contribution to Ensemble-Based Texture Recognition Performance.- Combining Audio-Based and Video-Based Shot Classification Systems for News Videos Segmentation.- Designing Multiple Classifier Systems for Face Recognition.- Exploiting Class Hierarchies for Knowledge Transfer in Hyperspectral Data.