A case study of stacked multi-view learning in dementia research

Authors:
Rui Li;Andreas Hapfelmeier;Jana Schmidt;Robert Perneczky;Alexander Drzezga;Alexander Kurz;Stefan Kramer
Affiliations:
Institut für Informatik, Technische Universität München, Garching b. München, Germany;Institut für Informatik, Technische Universität München, Garching b. München, Germany;Institut für Informatik, Technische Universität München, Garching b. München, Germany;Klinik u. Poliklinik für Psychiatrie u. Psychotherapie, Technische Universität München, München, Germany;Nuklearmedizinische Klinik, Technische Universität München, München, Germany;Klinik u. Poliklinik für Psychiatrie u. Psychotherapie, Technische Universität München, München, Germany;Institut für Informatik, Technische Universität München, Garching b. München, Germany
Venue:
AIME'11 Proceedings of the 13th conference on Artificial intelligence in medicine
Year:
2011

Citing 7
Cited 0

Original Contribution: Stacked generalization

Neural Networks
Is Combining Classifiers with Stacking Better than Selecting the Best One?

Machine Learning
SVM Feature Selection for Classification of SPECT Images of Alzheimer's Disease Using Spatial Information

ICDM '05 Proceedings of the Fifth IEEE International Conference on Data Mining
Combining Information Extraction Systems Using Voting and Stacked Generalization

The Journal of Machine Learning Research
When does Co-training Work in Real Data?

PAKDD '09 Proceedings of the 13th Pacific-Asia Conference on Advances in Knowledge Discovery and Data Mining
Issues in stacked generalization

Journal of Artificial Intelligence Research
Interpreting PET scans by structured patient data: a data mining case study in dementia research

Knowledge and Information Systems

Quantified Score

Hi-index	0.00

Visualization

Abstract

Classification of different types of dementia commonly involves examination from several perspectives, e.g., medical images, neuropsychological tests, etc. Thus, dementia classification should lend itself to so-called multi-view learning. Instead of simply combining several views, we use stacking to make the most of the information from the various views (PET scans, MMSE, CERAD and demographic variables). In the paper, we not only show the performance of stacked multiview learning on classifying dementia data, we also try to explain the factors contributing to its performance. More specifically, we show that the correlation of views on the base and the meta level should be within certain ranges to facilitate successful stacked multi-view learning.