Filters








7 Hits in 5.1 sec

Clustering to Improve One-Class Classifier Performance in Data Streams [article]

Richard Hugh Moulton, University, My, University, My
2018
This thesis identifies that the idea of breaking the majority class into subconcepts to simplify the OCC problem has been demonstrated for static data sets, [100], but has n [...]  ...  More worrying, often the minority class is the class of interest, e.g. for detecting abnormal conditions from streaming sensor data.  ...  Hayat and Hashemi proposed the Discrete Cosine Transform (DCT)-based approach to address the task of novelty and concept drift detection in data streams [47] .  ... 
doi:10.20381/ruor-22285 fatcat:swfukoqoifbfhefnruyj36o56y

Aktives maschinelles Lernen bei unvollständiger Information [article]

Georg Krempl, Universitäts- Und Landesbibliothek Sachsen-Anhalt, Martin-Luther Universität, Myra Spiliopoulou
2018
Furthermore, this habilitation thesis shows that this strategy is not limited to the pool-based scenario: for evolving data streams, it proposes two approaches that use this strategy.  ...  In addition, it also models the true posterior in the candidate's neighbourhood as a random variable. Then, it calculates the expectation of the performance gain over both random variables.  ...  ACKNOWLEDGEMENTS We would like to thank the Pychoinformatics Labs at OVG-University Magdeburg for letting us use their cluster, in particular Michael Hanke and Alex Waite, as well as our colleague Pawel  ... 
doi:10.25673/4479 fatcat:otzvgqgzvnecjonjbxsul2riky

Scalable and accurate knowledge discovery in real world databases

Martin Scholz, Technische Universität Dortmund, Technische Universität Dortmund
2007
Dies gilt in erster Linie für das gesamte LS8-Team der letzten Jahre.  ...  Schließlich (aber sicherlich "not least") möchte ich noch meiner Familie für vielerlei Unterstützung in den letzten Jahren danken. iv  ...  Validity checking for objects was realized by automatically deriving annotations in the form of boolean attributes for meta-data entities in the database.  ... 
doi:10.17877/de290r-872 fatcat:oix2yq4qyffu5hld65qvtbkrgm

Ontology-based information retrieval: methods and tools for cooperative query answering

Nenad Stojanovic
2005
This leads to a very low usefulness of the results of a retrieval process for a user's task at hand.  ...  In the last ten years ontologies have been emerged from an interesting conceptualisation paradigm to a very promising (semantic) modelling technology, especially in the context of the Semantic Web.  ...  the rich data modelling capabilities supported by the object oriented data model.  ... 
doi:10.5445/ir/1000004667 fatcat:egufkn5eg5doxhpz7nzfnm37ve

IMMM 2014 COMMITTEE IMMM Advisory Committee

France Paris, Andreas Schmidt, Abdulrahman Yarali, Philip Davis, Andreas Schmidt, David Newell, Bournemouth University -Bournemouth, Kuan-Ching Li, Abdulrahman Yarali, Alain Casali, Christian Ernst, Paolo Garza (+118 others)
unpublished
a series of academic and industrial events focusing on advances in all aspects related to information mining, management, and use.  ...  We are convinced that the participants found the event useful and communications very open.  ...  Each cluster is based on a probabilistic model, namely a first-order Markov chain.  ... 
fatcat:o5d5shizvratfpaaiibw7o2dhm

Large-Scale Pattern-Based Information Extraction from the World Wide Web

Sebastian Blohm
2010
This thesis explores the potential of using textual patterns for Information Extraction from the World Wide Web.  ...  Extracting information from text is the task of obtaining structured, machine-processable facts from information that is mentioned in an unstructured manner.  ...  In their most general version, they are an undirected graphical model.  ... 
doi:10.5445/ir/1000015423 fatcat:4ptk57kpcjh4ncjfnqj7uqtfle

Towards exploratory faceted search systems

Alex Ksikes, Apollo-University Of Cambridge Repository, Apollo-University Of Cambridge Repository
2014
Second, the interface uses a common pattern of zooming in on a particular search result in order to display more information.  ...  The second system, Cloud Mining, is an attempt at implementing the vision set forth in this thesis. The system is a framework used to instantiate ESSs.  ...  Google Earth lets us navigate and explore a virtual version of the planet. The user can see all kinds of interesting data onto the globe through the use of layers.  ... 
doi:10.17863/cam.14080 fatcat:z4vxxsi3ubddbhv4aythyrlfza