Ensembles of classifiers from spatially disjoint data

Authors:
Robert E. Banfield;Lawrence O. Hall;Kevin W. Bowyer;W. Philip Kegelmeyer
Affiliations:
Department of Computer Science and Engineering, ENB118, University of South Florida, Tampa, FL;Department of Computer Science and Engineering, ENB118, University of South Florida, Tampa, FL;Department of Computer Science and Engineering, University of Notre Dame, South Bend, IN;Biosystems Research Department, Sandia National Laboratories, Livermore, CA
Venue:
MCS'05 Proceedings of the 6th international conference on Multiple Classifier Systems
Year:
2005

Citing 5
Cited 5

Learning and making decisions when costs and probabilities are both unknown

Proceedings of the seventh ACM SIGKDD international conference on Knowledge discovery and data mining
Random Forests

Machine Learning
Distributed learning with bagging-like performance

Pattern Recognition Letters
Bayes and Pseudo-Bayes Estimates of Conditional Probabilities and Their Reliability

ECML '93 Proceedings of the European Conference on Machine Learning
Toward a Query Language on Simulation Mesh Data: An Object-oriented Approach

DASFAA '01 Proceedings of the 7th International Conference on Database Systems for Advanced Applications

Wrapper-based computation and evaluation of sampling methods for imbalanced datasets

UBDM '05 Proceedings of the 1st international workshop on Utility-based data mining
Using classifier ensembles to label spatially disjoint data

Information Fusion
Automatically countering imbalance and its empirical relationship to cost

Data Mining and Knowledge Discovery
A divide-and-conquer recursive approach for scaling up instance selection algorithms

Data Mining and Knowledge Discovery
Detecting and ordering salient regions

Data Mining and Knowledge Discovery

Quantified Score

Hi-index	0.00

Visualization

Abstract

We describe an ensemble learning approach that accurately learns from data that has been partitioned according to the arbitrary spatial requirements of a large-scale simulation wherein classifiers may be trained only on the data local to a given partition. As a result, the class statistics can vary from partition to partition; some classes may even be missing from some partitions. In order to learn from such data, we combine a fast ensemble learning algorithm with Bayesian decision theory to generate an accurate predictive model of the simulation data. Results from a simulation of an impactor bar crushing a storage canister and from region recognition in face images show that regions of interest are successfully identified.