Skip to content. | Skip to navigation

Informatik 5
Information Systems
Prof. Dr. M. Jarke
Sections
Personal tools
You are here: Home Theses Running Theses

Contact

Prof. Dr. M. Jarke
RWTH Aachen
Informatik 5
Ahornstr. 55
D-52056 Aachen
Tel +49/241/8021501
Fax +49/241/8022321

How to find us

Annual Reports

Disclaimer

Webmaster

 

 
Search

Running Theses


Bachelor
A Multimodal Mentoring Cockpit for Tutor Support
Learning analytics aim at providing an insight into the student’s learning process such that individual performance can be measured and thus provide the basis for individual student support. This thesis will utilize and evaluate existing mentoring solutions and aggregate them in a state-of-the-art progressive Web application. The outcome of this thesis will be a newly developed mentoring cockpit that meets the requirements of a holistic mentoring support experience.
Master
Extending the b-it Chain to execute smart contracts
Supervised by Prof. Dr. Thomas Rose; Advisor(s): Thomas Osterland
Often only noticed as a technology that enables the digital currency Bitcoin, blockchain is a novel protocol that allows the distributed and secure storing of information and untempered execution of program code in trust-less environments. Did you ever feel the intense desire to write a thesis about blockchain or do you have a slight hope that blockchain is the one-and-only topic that touches your heart? Use your chance now! We are looking forward to hear from you.
Bachelor, Master
Distributed Activity Coordination with Constraints
In cooperative user environments the distributed coordination of activities with hard and soft constraints is a challenging task. The objective of the thesis is the development of an heuristic for distributed coordination of activities with hard and soft constraints starting with a literature research, algorithm design and simulative evaluation.
Master
An Interactive Mixed Reality Visualization Framework for Immersive Analytics
Visualizations help humans in understanding complex data. A visual representation gives an overview of the data set so that it becomes possible to interpret it, e.g. to see patterns or correlations. With the rise of mixed reality technologies, various possibilities appeared in the field of Immersive Analytics. Instead of reducing the displayed content to a two-dimensional representation on a paper or screen, it is now possible to created three-dimensional visualizations. This enables the analyst to dive into the visual representation of the data and to freely explore it from different perspectives in a highly interactive manner.
Master
Graph-Structured Query Construction for Natural Language Questions
Supervised by Prof. Dr. Stefan Decker; Advisor(s): Dr. Michael Cochez
Graph-structured queries provide an efficient means to retrieve desired data from large-scale knowledge graphs. However, it is difficult for non-expert users to write such queries, and users prefer expressing their query intention through natural language questions. Recently, an increasing effort is being exerted to construct graph-structured queries for given natural language questions. At the core of the construction is to deduce the structure of the target query and retrieve vertices/edges of the underlying knowledge graph which constitute the query. Existing query construction methods rely on conventional graph-based algorithms and question understanding techniques, which lead to inefficient and degraded performances facing complicated natural language questions over knowledge graphs with large scales. In this thesis, we focus on this problem and propose novel construction models standing on recent knowledge graph embedding techniques. Extensive experiments were conducted on question answering benchmark datasets, and the results demonstrate that our models outperform baselines in terms of effectiveness and efficiency.
Master
Gamification of Serious Games with Recommendation Support
The goal of this master thesis is to unify both frameworks, that means, the serious game framework should be rebuilt with the help of the gamification framework.
Bachelor
Educational Escape Games for Mixed Reality
Supervised by PD Dr. Ralf Klamma, AOR
Based on our GAMR framework for gamification of mixed reality training we want to explore the design and implementation of mixed reality escape rooms in various educational settings.
Master
Using Deep Neural Networks and Copy Number Variations for Cancer Detection
Recently copy number variations got lot of attention due to their association with complex diseases like cancer. Finding their association with cancer is an active research eld. We propose a method to identify copy number variations which might be associated with a cancer by comparing copy numbers across 14 major cancer types. Selected CNV regions were used as features for cancer detection using deep belief networks, a deep learning technique. To our knowledge this is the rst study involving that many cancers and highest number of control samples for validation.
Master
Modeling for Street Level Crime Prediction
Supervised by Prof. Dr. Stefan Decker; Advisor(s): Dr. Michael Cochez, Cristina Kadar, Raquel Rosés Brüngger
The aim of this master thesis is to build a predictive model of crime at street level for a Swiss city, including a tool implementation for visualizing the data and results.
Master
Deep Learning-based Knee Osteoarthritis Diagnosis from Radiographs and Magnetic Resonance Images
In this thesis, the student investigates the use of deep learning techniques (especially computer vision) to perform diagnosis of osteoarthritis. The input to the system are both radiographs (X-RAY) and magnetic resonance images (MRI).
Master
Post-Mortem Community Information Systems Success Analytics
Supervised by PD Dr. Ralf Klamma, AOR
Goal of this thesis is an integration of post-mortem community data dumps with the MobSOS real-time community information systems success awareness framework.
Master
Classification of Mechanically Ventilated Patients Based on Weaning Difficulty
Supervised by Prof. Dr. Christoph Quix, Johannes Bickenbach; Advisor(s): Dr. Sandra Geisler, Jermain Kaminski, Arne Peine
Master
Analysis of Breast Cancer Genomic Data with Multimodal Deep Belief Network
The objective of this thesis is to analyse breast cancer genomic data with the potential of predicting breast cancer genomic biomarker. Specifically, these analysis will include classification and regression of breast cancer patients based on their genetic information.
Master
Smart Quality Check for FHIR Resources System
Supervised by Prof. Dr. Stefan Decker; Advisor(s): Dr. Oya Deniz Beyan
Fast Healthcare Interoperability Resources defines a set of "Resources" that represent granular clinical concepts. It is a standard for exchanging healthcare information electronically between stakeholders of the healthcare environment including care providers, patients, and mobile application developers. Aim of this thesis is to develop tools to validate conformance of the resources against a set of business rules.
Bachelor
Evaluation of Approximate Hierarchical Clustering Algorithms
Supervised by Prof. Dr. Martin Reißel; Advisor(s): Dr. Michael Cochez
There are several algorithms to perform a hierarchical clustering, resulting in approximate dendrogram. This makes it possible to perform a clustering on big data sets. In this thesis the student will evaluate of several existing algorithms in terms of resource use and clustering quality. As part of this work, the student has to implement some of the algorithms to work on a GPU as they are not scalable enough for CPU computing. External resources: http://users.jyu.fi/~miselico/papers/twister_tries.pdf http://users.jyu.fi/~miselico/papers/TT_aposteriori_elimination.pdf, mainly IV. SIDESTEP: MEASURING THE QUALITY OF A DENDROGRAM
Bachelor
Chat Interfaces for Social Bots in a Peer-to-Peer Environment
Social Bots (software robots) are computer algorithms that automatically produce content and interact with humans on social media. This thesis will utilize and evaluate a social bot framework with different community applications. It will also extend the framework to support two-way chat interfaces with the system via common chat applications (e.g. Slack).
Master
Context based Travel Information Service
Travel information services provide itinerary based user travel assistance. The objective of the thesis is the user context analysis for multimodal travel situations, the design of a mobile device based context detection service and an information rendering service for user travel assistance. As proof of concept a functional prototype should be implemented and evaluated.
Bachelor
Accelerating KGlove Graph Embedding
Supervised by Prof. Dr. Stefan Decker; Advisor(s): Dr. Michael Cochez
Lately several methods for embedding graphs nodes into a vector space have been proposed. These embeddings can then used to train other machine learning models. Learning these embeddings is typically done using CPUs. In this thesis the student would look into the use of other hardware, like GPUs and distributed computation options to speed up the learning process. The challenge is that algorithms working on graphs have typically a bad memory locality. Hence, existing algorithms might need profound modification in order to use them on GPUs or in a distributed fashion.
Master
Patterns for Integrating Rule Based and Process Based Model Components of Computerized Clinical Guidelines
Supervised by Prof. Dr. Stefan Decker, Dr. rer. nat. Cord Spreckelsen; Advisor(s): 692050c6199c8bbfb9be2189e82ff904
Master
Feature Clustering and Visualization of High Dimensional Data using Clique Cover Theory
Approaches such as clustering and classification that are analytically or computationally manageable in low dimensions become intractable as the dimensions increases. This happens because of a phenomenon known as “the curse of dimensionality” which is commonly observed in high dimensional data. Thus the aim of this thesis is to come up with a novel approach for feature clustering, selection, and visualization using the graph theoretical approach of Clique Covers.
Master
Semantic Anomaly Detection in Medical Time Series
Supervised by Prof. Dr. Stefan Decker, Dr. rer. nat. Cord Spreckelsen; Advisor(s): Dr. Oya Deniz Beyan
Master
Guided Search Algorithm for the Mobility-Oriented Agenda Planning Problem
The need of mobility arises from activities such as a meeting or a doctor's appointment. Often, when planning these kinds of activities the mobility to these locations is only planned after the activity is already scheduled, which may be a sub-optimal approach. While planning it is hard to comprehend which consequences a particular action, such as moving the location or time of an activity, has on the agenda and mobility schedule. The objective of this thesis is the analysis, design, implementation and evaluation of a mobility agenda planning assistance system in form of a graphical user interface which interweaves the mobility and agenda planning processes.
Master
Continuous Learning for Indoor Localization based on Wi-Fi-Fingerprinting in Dynamic Environments
Supervised by PD Dr. Ralf Klamma, AOR, Jörg Blankenbach
In this thesis it shall be investigated how to apply deep learning to Wi-Fi finger- printing by continuously improving the models. Therefore, the stated challenges of dynamic environments and few labeled data, will be tackled.
Bachelor, Master
Social Recommender Systems for Professional Communities
Supervised by PD Dr. Ralf Klamma, AOR
This thesis aims to develop social recommender system service for Open Source Software (OSS) Communities.
Master
Data Dependence and Indecisiveness for Locality-Sensitive Hashing
Supervised by Prof. Dr. Stefan Decker; Advisor(s): Dr. Michael Cochez
Locality-sensitive hashing is used to speed up near-neighbor search in high dimensional space. When the distance of interest is cosine distance, Random hyperplane hashing (RHH) is used. This technique is based on randomly selecting hyperplanes. However, in some cases (when we have more information about the dataset) it seems reasonable to not choose the hyperplanes completely randomly. Further, if normal RRH is performed with a low number of hyperplanes, then the hyperplanes are likely to not cover the space very well. This thesis will be about choosing the hyperplane in a data dependent way and try to sample the hyperplanes such that they cover the space nicely (including a comparison with angular quantization).