Show simple item record

dc.contributor.advisorDarken, Christian
dc.contributor.authorTan, Kian-Moh Terence
dc.dateMar-13
dc.date.accessioned2013-05-08T20:42:54Z
dc.date.available2013-05-08T20:42:54Z
dc.date.issued2013-03
dc.identifier.urihttp://hdl.handle.net/10945/32907
dc.description.abstractPrediction of events is fundamental to both human and artificial agents. The main problem with previous prediction techniques is that they cannot predict events that have never been experienced before. This dissertation addresses the problem of predicting such novelty by developing algorithms and computational models inspired from recent cognitive science theories conceptual blending theory and event segmentation theory. We were able to show that prediction accuracy for event or state prediction can be significantly improved using these methods. The main contribution of this dissertation is a new class of prediction techniques inspired by conceptual blending that improves prediction accuracy overall and has the ability to predict even events that have never been experienced before. We also show that event segmentation theory, when integrated with these techniques, results in greater computational efficiency. We implemented the new prediction techniques, and more traditional alternatives such as Markov and Bayesian techniques, and compared their prediction accuracy quantitatively for three domains a role-playing game, intrusion-system alerts, and event prediction of maritime paths in a discrete-event simulator. Other contributions include two new unification algorithms that improve over a nave one, and an exploration of ways to maintain a minimum-size knowledge base without affecting prediction accuracy.en_US
dc.description.urihttp://archive.org/details/learningandpredi1094532907
dc.publisherMonterey, California. Naval Postgraduate Schoolen_US
dc.titleLEARNING AND PREDICTION OF RELATIONAL TIME SERIESen_US
dc.typeThesisen_US
dc.contributor.departmentComputer Science
dc.subject.authorRelational time seriesen_US
dc.subject.authorlearningen_US
dc.subject.authorpredictionen_US
dc.subject.authorconceptual blendingen_US
dc.subject.authorCyber intrusion alerten_US
dc.description.serviceCivilian, Singaporeen_US
etd.thesisdegree.nameDoctor Of Philosophy In Modeling, Virtual Environments And Simulation (Moves)en_US
etd.thesisdegree.levelDoctoralen_US
etd.thesisdegree.disciplineModeling, Virtual Environments, and Simulation Institute (MOVES)en_US
dc.description.distributionstatementApproved for public release; distribution is unlimited.


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record