Predictive Model Fusion: A Modular Approach to Big, Unstructured Data

dc.contributor.authorHoegh, Andrew B.en
dc.contributor.committeechairLeman, Scotland C.en
dc.contributor.committeememberFerreira, Marco A. R.en
dc.contributor.committeememberRamakrishnan, Narenen
dc.contributor.committeememberHigdon, Daviden
dc.description.abstractData sets of increasing size and complexity require new approaches for prediction as the sheer volume of data from disparate sources inhibits joint processing and modeling. Rather modular segmentation is required, in which a set of models process (potentially overlapping) partitions of the data to independently construct predictions. This framework enables individuals models to be tailored for specific selective superiorities without concern for existing models, which provides utility in cases of segmented expertise. However, a method for fusing predictions from the collection of models is required as models may be correlated. This work details optimal principles for fusing binary predictions from a collection of models to issue a joint prediction. An efficient algorithm is introduced and compared with off the shelf methods for binary prediction. This framework is then implemented in an applied setting to predict instances of civil unrest in Central and South America. Finally, model fusion principles of a spatiotemporal nature are developed to predict civil unrest. A novel multiscale modeling is used for efficient, scalable computation for combining a set of spatiotemporal predictions.en
dc.description.degreePh. D.en
dc.publisherVirginia Techen
dc.rightsIn Copyrighten
dc.subjectModel Fusionen
dc.subjectSpatiotemporal Modelingen
dc.subjectAreal Dataen
dc.subjectSequential Monte Carloen
dc.titlePredictive Model Fusion: A Modular Approach to Big, Unstructured Dataen
dc.typeDissertationen Polytechnic Institute and State Universityen D.en


Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
1.13 MB
Adobe Portable Document Format