Completed Theses

Here you can find a list with completed theses by students.

[ 2021 ] [ 2020 ] [ 2019 ] [ 2018 ] [ 2017 ] [ 2016 ] [ 2015 ] [ 2014 ] [ 2013 ] [ 2012 ] [ 2011 ] [ 2009 ] [ 20-- ]

2021 [ nach oben ]

Machine Learning for question answering in the context of websites Gabler, Michael (2021).

[ BibTeX ] [ EndNote ]

Fraud Detection using Graph Neural Networks Fries, Pascal (2021).

[ BibTeX ] [ EndNote ]

2020 [ nach oben ]

Evaluating the multi-task learning approach for land use regression modelling of air pollution Dulny, Andrzej (M) (2020).

[ BibTeX ] [ EndNote ]

Pointwise Shape Construction From 3D Data with Spatial Deep Features Chibane, Julian (2020).

[ BibTeX ] [ EndNote ]

Increasing Scalability in Deep Reinforcement Learning based Recommender Systems Grimm, Alexander (2020).

[ BibTeX ] [ EndNote ]

Using Neural Networks as a Metric Towards Optimal Automated Image Enhancement Fischer, Michael (2020).

[ BibTeX ] [ EndNote ]

Gesichtserkennung zur automatischen Erfassung von Kaffeestatistik Vogell, Jonathan (2020).

[ BibTeX ] [ EndNote ]

Applying Reinforcement Learning to an ERP-System Simulation Gils, Dominik (2020).

[ BibTeX ] [ EndNote ]

Domain Specific Anomaly Detection Mahlmeister, Thomas (2020).

[ BibTeX ] [ EndNote ]

Stylebased Pairwise Image Aesthetic Assessment Training Pfister, Jan (2020).

[ BibTeX ] [ EndNote ]

2019 [ nach oben ]

Muli-Hop-Multi-Party Kalibrierung von mobilen Sensornetzwerken Stock, Maximilian (2019).

[ BibTeX ] [ EndNote ]

Sentiment-Klassifizierung von Chatnachrichten twitch.tv Tritscher, Julian (2019).

[ BibTeX ] [ EndNote ]

2018 [ nach oben ]

OSM-Seg: Training satellite image segmentation models on automatically derived, weakly labelled datasets from OpenStreetMap. Werthmann, Alexander (2018).

[ BibTeX ] [ EndNote ]

Classification of Fake Health Web Pages Loos, Tobias (2018).

[ BibTeX ] [ EndNote ]

Neural modeling of user task completion Koopmann, Tobias (2018).

[ BibTeX ] [ EndNote ]

Learning the relation of pollution to land usage Steininger, Michael (2018).

[ BibTeX ] [ EndNote ]

Ontology Learning on Word Embeddings with and without Background Knowledge Hahn, Luzian (2018).

[ BibTeX ] [ EndNote ]

Predicting subjective ratings of perceived exertion using related exercises Davidson, Padraig (2018).

[ BibTeX ] [ EndNote ]

Deep Learning zur automatischen Ergebniszählung im Tischtennis mittels akustischen Emissionssensoren Leppich, Lukas (2018).

[ BibTeX ] [ EndNote ]

2017 [ nach oben ]

Active Learning in der Emotion Analysis Wilke, Nina (2017).

[ BibTeX ] [ EndNote ]

Sentiment Analysis on German Novels Zehe, Albin (2017).

[ BibTeX ] [ EndNote ]

2016 [ nach oben ]

Echtzeit-Sentimentanalyse von Chatnachrichten auf Twitch.tv Lechner, Magnus (2016).

[ BibTeX ] [ EndNote ]

Stimmungsanalyse von Chatnachrichten bei Live-Streaming-Videoportalen am Beispiel von Twitch.tv Katzenberger, Tobias (2016).

[ BibTeX ] [ EndNote ]

Automatic Summarization of German Novels Sangeorzan, Ion Alexandru (2016).

[ BibTeX ] [ EndNote ]

Real-time Topic and Event Detection in Twitch Message Streams with Apache Storm Aulbach, Maximilian (2016).

[ BibTeX ] [ EndNote ]

Kalibrierung von Schalldruckmessungen auf Smartphones mit neuronalen Netzen Grimm, Alexander (2016).

[ BibTeX ] [ EndNote ]

A MapReduce Implementation of the General Pattern Tree Algorithm Mewes, Hauke (2016).

[ BibTeX ] [ EndNote ]

2015 [ nach oben ]

Erkennung von Beziehungen zwischen Entitäten in Zeitungsartikeln Davidson, Padraig (2015).

[ BibTeX ] [ EndNote ]

Generierung und Vergleich von Bewegungsmodellen auf Flickr-Daten Dürr, Johannes (2015).

[ BibTeX ] [ EndNote ]

Evaluierung und Erweiterung des Klassifikationsframeworks zur Spammerkennung in BibSonomy Baier, Clemens (2015).

[ BibTeX ] [ EndNote ]

Semantische Analyse von Web-Traffic Schlör, Daniel (2015).

[ BibTeX ] [ EndNote ]

Evaluation verschiedener Techniken zur Erkennung von Themen in einem großen Corpus von Zeitungsartikeln Zehe, Albin (2015).

[ BibTeX ] [ EndNote ]

Kalibrierung von Smartphones für Lautstärkenmessungen Stehr, Florian (2015).

[ BibTeX ] [ EndNote ]

Playlist recommendation using LDA Behringer, Julian (2015).

[ BibTeX ] [ EndNote ]

Recommender Systems - Vergleich zweier LDA Systeme Niebler, Stefan (2015).

[ BibTeX ] [ EndNote ]

2014 [ nach oben ]

Vergleich von Latent Dirichlet Allocation und Fuzzy C-Means-Clustering Scheuerpflug, Stefan (2014).

[ BibTeX ] [ EndNote ]

Datenmodellierung für Internet-of-Things Plattformen Allendorf, Fabian (2014).

[ BibTeX ] [ EndNote ]

Ereigniserkennung in Audiostreams mit Android Fischer, Elisabeth (2014).

[ BibTeX ] [ EndNote ]

Rating und Vorhersage von Sport- und Spielergebnissen Mühr, Johannes (2014).

[ BibTeX ] [ EndNote ]

Zeitbasiertes Clusterin in EveryAware Airprobe/Widenoise Jobst, Michael (2014).

[ BibTeX ] [ EndNote ]

GPS-Track-Glättung mithilfe von Map-Matching-Algorithmen Kalkus, Jona (2014).

[ BibTeX ] [ EndNote ]

Evaluation of Event Detection Systems in Twitter Grimm, Gerhard (2014).

[ BibTeX ] [ EndNote ]

2013 [ nach oben ]

Tag Sense Disambiguation through Clusterring Sangeorzan, Ion Alexandru (2013).

[ BibTeX ] [ EndNote ]

Small worlds in Twitter Deinlein, Michael (2013).

[ BibTeX ] [ EndNote ]

Ratgeber für die gute Abschlussarbeit. Wegner, Lutz (2013).

[ BibTeX ] [ EndNote ] [ Download ]

Training recurrent neural networks. Sutskever, Ilya in University of Toronto, Toronto, Ont., Canada (2013).

[ BibTeX ] [ EndNote ] [ URL ]

2012 [ nach oben ]

XML-Databinding in Objective-C und BibSonomy API-Client Baier, Clemens (2012).

[ BibTeX ] [ EndNote ]

Topic- und Eventerkennung in Twitter als Android Applikation Grimm, Gerhard (2012).

[ BibTeX ] [ EndNote ]

Evaluation aktueller Datenbanksysteme bzgl. geo-spezifischer Anfragen König, Frederik (2012).

[ BibTeX ] [ EndNote ]

Entwurf und Analyse eines Recommenders für Android Apps Perlia, Stephanie (2012).

[ BibTeX ] [ EndNote ]

Wifi Indoor-Lokalisierung für Android Geräte Dürr, Johannes (2012).

[ BibTeX ] [ EndNote ]

Servlet-Framework zur Visualisierung von Android-Sensordaten Filbrich, Andreas (2012).

[ BibTeX ] [ EndNote ]

2011 [ nach oben ]

aPub: BibSonomy als Android Anwendung Plischke, Alex (2011).

[ BibTeX ] [ EndNote ]

Aktives Lernen zur Entdeckung von Spam in Social Book-marking Systemen Borchert, Kathrin (2011).

[ BibTeX ] [ EndNote ]

Sensing with Android Mobile Devices and Detection of Surroundings using Audio Classification Gürültücü, Inac (2011).

[ BibTeX ] [ EndNote ]

How to write a good PhD thesis and survive the viva Rüger, Stefan (2011).

[ Abstract ] [ BibTeX ] [ EndNote ] [ URL ] [ Download ]

2009 [ nach oben ]

Recommender Systems for Social Bookmarking. Technical Report (PhD dissertation), Bogers, Toine PhD thesis, Tilburg, The Netherlands. (2009, December).

[ Abstract ] [ BibTeX ] [ EndNote ] [ URL ] [ Download ]

Recommender systems belong to a class of personalized information filtering technologies that aim to identify which items in a collection might be of interest to a particular user. Recommendations can be made using a variety of information sources related to both the user and the items: past user preferences, demographic information, item popularity, the metadata characteristics of the products, etc. Social bookmarking websites, with their emphasis on open collaborative information access, offer an ideal scenario for the application of recommender systems technology. They allow users to manage their favorite bookmarks online through a web interface and, in many cases, allow their users to tag the content they have added to the system with keywords. The underlying application then makes all information sharable among users. Examples of social bookmarking services include Delicious, Diigo, Furl, CiteULike, and BibSonomy. In my Ph.D. thesis I describe the work I have done on item recommendation for social bookmarking, i.e., recommending interesting bookmarks to users based on the content they bookmarked in the past. In my experiments I distinguish between two types of information sources. The first one is usage data contained in the folksonomy, which represents the past selections and transactions of all users, i.e., who added which items, and with what tags. The second information source is the metadata describing the bookmarks or articles on a social bookmarking website, such as title, description, authorship, tags, and temporal and publication-related metadata. I compare and combine the content-based aspect with the more common usage-based approaches. I evaluate my approaches on four data sets constructed from three different social bookmarking websites: BibSonomy, CiteULike, and Delicious. In addition, I investigate different combination methods for combining different algorithms and show which of those methods can successfully improve recommendation performance. Finally, I consider two growing pains that accompany the maturation of social bookmarking websites: spam and duplicate content. I examine how widespread each of these problems are for social bookmarking and how to develop effective automatic methods for detecting such unwanted content. Finally, I investigate the influence spam and duplicate content can have on item recommendation.

@phdthesis{bogers2009recommender,
  abstract = {Recommender systems belong to a class of personalized information filtering technologies that aim to identify which items in a collection might be of interest to a particular user. Recommendations can be made using a variety of information sources related to both the user and the items: past user preferences, demographic information, item popularity, the metadata characteristics of the products, etc. Social bookmarking websites, with their emphasis on open collaborative information access, offer an ideal scenario for the application of recommender systems technology. They allow users to manage their favorite bookmarks online through a web interface and, in many cases, allow their users to tag the content they have added to the system with keywords. The underlying application then makes all information sharable among users. Examples of social bookmarking services include Delicious, Diigo, Furl, CiteULike, and BibSonomy. In my Ph.D. thesis I describe the work I have done on item recommendation for social bookmarking, i.e., recommending interesting bookmarks to users based on the content they bookmarked in the past. In my experiments I distinguish between two types of information sources. The first one is usage data contained in the folksonomy, which represents the past selections and transactions of all users, i.e., who added which items, and with what tags. The second information source is the metadata describing the bookmarks or articles on a social bookmarking website, such as title, description, authorship, tags, and temporal and publication-related metadata. I compare and combine the content-based aspect with the more common usage-based approaches. I evaluate my approaches on four data sets constructed from three different social bookmarking websites: BibSonomy, CiteULike, and Delicious. In addition, I investigate different combination methods for combining different algorithms and show which of those methods can successfully improve recommendation performance. Finally, I consider two growing pains that accompany the maturation of social bookmarking websites: spam and duplicate content. I examine how widespread each of these problems are for social bookmarking and how to develop effective automatic methods for detecting such unwanted content. Finally, I investigate the influence spam and duplicate content can have on item recommendation.},
  address = {Tilburg, The Netherlands},
  author = {Bogers, Toine},
  keywords = {bookmarking item recommender social tagging thesis},
  month = {dec},
  school = {Tilburg University},
  title = {Recommender Systems for Social Bookmarking},
  year = 2009
}

%0 Thesis
%1 bogers2009recommender
%A Bogers, Toine
%C Tilburg, The Netherlands
%D 2009
%T Recommender Systems for Social Bookmarking
%U http://ilk.uvt.nl/~toine/phd-thesis/
%X Recommender systems belong to a class of personalized information filtering technologies that aim to identify which items in a collection might be of interest to a particular user. Recommendations can be made using a variety of information sources related to both the user and the items: past user preferences, demographic information, item popularity, the metadata characteristics of the products, etc. Social bookmarking websites, with their emphasis on open collaborative information access, offer an ideal scenario for the application of recommender systems technology. They allow users to manage their favorite bookmarks online through a web interface and, in many cases, allow their users to tag the content they have added to the system with keywords. The underlying application then makes all information sharable among users. Examples of social bookmarking services include Delicious, Diigo, Furl, CiteULike, and BibSonomy. In my Ph.D. thesis I describe the work I have done on item recommendation for social bookmarking, i.e., recommending interesting bookmarks to users based on the content they bookmarked in the past. In my experiments I distinguish between two types of information sources. The first one is usage data contained in the folksonomy, which represents the past selections and transactions of all users, i.e., who added which items, and with what tags. The second information source is the metadata describing the bookmarks or articles on a social bookmarking website, such as title, description, authorship, tags, and temporal and publication-related metadata. I compare and combine the content-based aspect with the more common usage-based approaches. I evaluate my approaches on four data sets constructed from three different social bookmarking websites: BibSonomy, CiteULike, and Delicious. In addition, I investigate different combination methods for combining different algorithms and show which of those methods can successfully improve recommendation performance. Finally, I consider two growing pains that accompany the maturation of social bookmarking websites: spam and duplicate content. I examine how widespread each of these problems are for social bookmarking and how to develop effective automatic methods for detecting such unwanted content. Finally, I investigate the influence spam and duplicate content can have on item recommendation.

20-- [ nach oben ]

A Framework for Stream Processing an Visualization Hartmann, Tobias

[ BibTeX ] [ EndNote ]

Hubland Süd, Geb. M2

Completed Theses

Hinweis zum Datenschutz

Hinweis zum Datenschutz

Bildnachweise