Abstract | ||
---|---|---|
We describe an ensemble approach to learning from arbitrarily partitioned data. The partitioning comes from the distributed processing requirements of a large scale simulation. The volume of the data is such that classifiers can train only on data local to a given partition. As a result of the partition reflecting the needs of the simulation, the class statistics can vary from partition to partition. Some classes will likely be missing from some partitions. We combine a fast ensemble learning algorithm with probabilistic majority voting in order to learn an accurate classifier from such data. Results from simulations of an impactor bar crushing a storage canister and from facial feature recognition show that regions of interest are successfully identified in spite of the class imbalance in the individual training sets. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1016/j.inffus.2007.08.001 | Information Fusion |
Keywords | Field | DocType |
random forest,partitioned data,imbalanced training data,k-nearest centroids,impactor bar,accurate classifier,probabilistic voting,individual training set,class statistic,saliency,spatially disjoint data,fast ensemble,classifier ensemble,large scale simulation,facial feature recognition show,k -nearest centroids,ensemble approach,class imbalance,out-of-partition,region of interest,ensemble learning,majority voting,distributed processing | Data mining,Disjoint sets,Computer science,Artificial intelligence,Probabilistic logic,Random forest,Classifier (linguistics),Ensemble learning,Pattern recognition,Feature recognition,Partition (number theory),Partition refinement,Machine learning | Journal |
Volume | Issue | ISSN |
9 | 1 | Information Fusion |
Citations | PageRank | References |
5 | 0.42 | 23 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Larry Shoemaker | 1 | 13 | 1.93 |
Robert E. Banfield | 2 | 358 | 17.16 |
Lawrence O. Hall | 3 | 5543 | 335.87 |
Kevin W. Bowyer | 4 | 11121 | 734.33 |
W. Philip Kegelmeyer | 5 | 3498 | 146.54 |