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


Master
Batch Recommender for Fast Ontology Prototyping
The goal is to expand the structure of Neologism with a batch recommender that does the following. We want the user to be supported with live recommendations for text while creating nodes in the graph. After the user created the graph, we want to give the user the option to run a batch recommender. This batch recommender will connect the terms inside the graph to terms in already existing ontologies. The connection will be based on ranking the terms in such a way, that it supports the user in publishing the ontology with its desired meaning. The results will be displayed in a simple and readable manner, such that the user can choose the best fitting term for every node.
Bachelor
Bachelor
Reach for the Stars: Gamified Group Work in Mixed Reality
Supervised by PD Dr. Ralf Klamma, AOR; Advisor(s): Benedikt Hensen, M.Sc.
Collaboration and group work are essential parts of learning since they encourage students to exchange ideas, to learn from each other and to support each other. The ability to work as a team increases the quality and amount of results and is therefore a highly demanded soft skill. However, students who face group work in courses still encounter challenges regarding efficient coordination, motivation and communication when working on group assignments or in learning groups. This becomes evident in processes where one person does all the work. Other common examples include a lack of communication where the group accumulates their individual results only at the end of the project and the participants cannot compensate if some members failed to deliver their results on time. Mixed Reality bears the potential to provide a structured 3D environment for organization and collaboration where group tasks can be split up visually between participants in virtual meetings. Additionally, Gamification can provide means of motivation to continue with a learning task and to strengthen the unity of the team.
Bachelor
Chatbot-assisted Community Analysis
The goal of this thesis is a chatbot that can be used by a community to query usage data and visualizations from an existing system.
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.
Master
Utilize Chat Interfaces for Social Bot Creation
Social Bots (software robots) are computer algorithms that automatically produce content and interact with humans on social media. This thesis will utilize chat interfaces and a social bot framework to create social bots. It will also extend the framework to support various social bot types (e.g. chatbots, crawlers, transactional bots or informational bots).
Master
Privacy Attack on Social Networks Using Network Embeddings
Supervised by Prof. Dr. Markus Strohmaier, Prof. Dr. Stefan Decker; Advisor(s): Dr. Florian Lemmerich, Dr. Michael Cochez
Abstract. A company that runs a social network trains a node embedding on the network where each account is represented by one node. One user deletes his account. Thus, the company is legally required to remove all private information of that user. This includes the node associated with the user’s account and the vector representation of that node that is generated by the embedding. The company, however, does likely not delete the vector representations of the other nodes even though the removed node was used during training of these. Is it possible to identify the neighbors of the removed node? Which kinds of neighbors can be identified best, which cannot be identified? First results suggest that the identification of neighbors works well for some kind of nodes and is more difficult for others.
Bachelor
Systematic Literature Reviews - Pushing the Limits
Supervised by PD Dr. Ralf Klamma, AOR
A systematic literature review is a "systematic, explicit, comprehensive, and reproducible method for identifying, evaluating, and synthesizing the existing body of completed and recorded work produced by researchers, scholars, and practitioners".
Bachelor
Realitybox: A WebXR Library for Virtual Learning Environments
Supervised by PD Dr. Ralf Klamma, AOR; Advisor(s): Benedikt Hensen, M.Sc.
Existing Virtual Learning Environments like Moodle include different multi-media modules to allow lecturers to convey the learning material in a suitable way. However, Virtual Learning Environments have not yet adapted Mixed Reality technology despite its large potential to support learning processes.
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
A Neural Network Model for Visualization Recommendation System
A Recommendation Tool for Data Visualization using Artificial Neural Networks
Master
Machine Economy for Dynamic Configurations of Production Processes
Supervised by Prof. Dr. Thomas Rose; Advisor(s): Thomas Osterland
In the context of Industry 4.0 and the Internet of Things, the autonomization of cyber physical systems is increasingly coming to the fore. Just imagine an autonomous vehicle that offers commuter services against payment. The electric vehicle has to pay tolls, requires energy from charging stations and employs washing services from time to time. Considering all entities in this process as agents that can interact and carry wallets, one can easily envision a machine-to-machine economy. Technical agents decide what tasks to conduct regarding costs, capabilities and earnings as illustrated by the demonstrators of Smart Replenishment Box and Smart Vehicle Control1.
Bachelor
Gamification of habit forming in Distance Education
Recent developments show a rise in popularity of Learning Management Systems in an increasingly digital teaching enviroment. However, students can encounter difficulties with sustained motivation without extrinsic influences like communicating with peers. The application of gamification principles to the digital learning process provides motivating factors for students to aid their learning process. Participation in educational courses is a process often spanning many weeks, so a habit-based approach to learning seems prudent.
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.
Bachelor
An Intelligent Menu Placement System for Mixed Reality Applications
Supervised by PD Dr. Ralf Klamma, AOR; Advisor(s): Benedikt Hensen, M.Sc.
A common problem with spatial immersive applications is the placement of UI elements in the space. On the one hand, a menu needs to be accessible and on the other hand, it must not be in the way of the user when it is not needed. Moreover, the menus need to adapt to the room’s characteristics, e.g. to avoid problems where menus clip through walls and become unreachable. For mixed reality applications, the environment can vary from small rooms to large lecture halls. UI systems must account for this. For instance, UI elements cannot be placed in a fixed position in space without respecting the spatial mapping of the real environment. Instead, a more intelligent solution is required for positioning UI elements in space.
Bachelor
Dynamic Embeddings of Evolving Knowledge Graphs
Supervised by Prof. Dr. Stefan Decker; Advisor(s): Dr. Michael Cochez, Dr. Florian Lemmerich
The goal of this Bachelor thesis is the research of updating KG embeddings with new information in order to obtain a dynamic and stable embedding of the fast-evolving KG while reducing the computational effort.
Bachelor, Master
Utilize Mentoring Bots in Learning Management Systems
Social Bots (software robots) are computer algorithms that automatically produce content and interact with humans on social media. This thesis will utilize bots in learning management systems (LMSs) and aims to assist students during their course.
Bachelor, Master
Bachelor, Master
Performing Distributed Analytics on Decentralised Geo- and Hydrological Data
Supervised by Prof. Dr. Stefan Decker, Prof. Dr. Holger Schüttrumpf; Advisor(s): Sascha Martin Welten, M.Sc., Lennart Schelter, Julian Hofmann
In times of increasing weather extremes, weather forecasts and early warning systems for extreme weathers have gained great promise to prevent property damage or to mitigate the risk to the civilian population. Current approaches are based on different data types, such as geo basic data, weather forecasts or other hydrological data, in several data sources (Salas et al., 2020; Kreklow et al., 2020; Hofmann and Schüttrumpf, 2019) However, these approaches rely on data centralisation, which can pose several challenges. First, the centralisation process itself could act as a bottleneck since vast amounts of spatiotemporal data from multiple data sources are transmitted to one single location. Second, the data has to be harmonised locally such that lightweight data analysis tasks or even data model training can be conducted. Lastly, depending on the data type, well-known data privacy regulations hinder institutions to share their data. One solution to circumvent these immanent problems of data centralisation could be Distributed Analytics (DA) approaches. DA poses a paradigm shift to address the mentioned challenges by bringing the analysis algorithm to the data instead of vice versa. By design, data stays within institutional borders and the data owner keeps the sovereignty over the data.
Bachelor
Development of Generative Models Trained on Decentralised Geo- and Hydrological Data
Supervised by Prof. Dr. Stefan Decker, Prof. Dr. Holger Schüttrumpf; Advisor(s): Sascha Martin Welten, M.Sc., Julian Hofmann, Lennart Schelter
In times of increasing weather extremes, weather forecasts and early warning systems for extreme weathers have gained great promise to prevent property damage or to mitigate the risk to the civilian population. Current approaches are based on different data types, such as geo basic data, weather forecasts or other hydrological data, in several data sources (Salas et al., 2020; Kreklow et al., 2020; Hofmann and Schüttrumpf, 2019) However, these approaches rely on data centralisation, which can pose several challenges. First, the centralisation process itself could act as a bottleneck since vast amounts of spatiotemporal data from multiple data sources are transmitted to one single location. Second, depending on the data type, well-known data privacy regulations hinder institutions to share their data. Lastly, data sets suffer from sparsity and incomplete features, which makes data analysis difficult. In particular, weather datasets provide high spatiotemporal data whereas hydrological well data or geobase data are generally incomplete.
Bachelor
Machine Learning for Anonymization of Unstructured Text
Supervised by Prof. Dr. Stefan Decker; Advisor(s): Dr. Michael Cochez
This thesis addresses the problem of identifying personal information in unstructured text using supervised Machine Learning (ML). The final application should be able to recognize and annotate the tokens that make up personal data in an English input text as accurately as possible. First, supervised learning methods, suitable for the task, will be identified. Then, models based on the most promising approaches will be designed and implemented. For comparison, suitable evaluation metrics have to be determined. Finally, the approaches are compared and evaluated against a baseline and each other.
Bachelor
Web-based Cluster Deployment for a Large-Scale Distributed Infrastructure
Nowadays, agile development processes use cloud container orchestration platforms for continuous integration, deployment and delivery. Technologies like Docker and Kubernetes are used here as the state-of-the-art cloud-native infrastructures the software is deployed on. However, deployment of heterogeneous service environments, developed by multiple teams with different technical proficiency levels, is not a trivial task. The thesis should investigate possibilities of automatic Web-based deployment of microservices in a Kubernetes cluster.
Bachelor
Developing Data Quality Metrics for Power System Modeling
Supervised by Prof. Dr. Stefan Decker; Advisor(s): Dr. Oya Deniz Beyan, 660b75904e3b7e318151bbdc353d734d
Linked data is gaining new attention in the last years because of its natural connection to knowledge-based applications. The quality of decisions depends heavily on the quality of the underlying data, for reasoning such quality reports are mandatory for each decision. The W3Cs Best Practices Working Groups "Data on the Web Best Practices: Data Quality Vocabulary" defines a vocabulary to archive linking results of data quality assessments to linked data. Also, a basic set of quality dimensions and metrics based on the work of Zaveri et al. (https://dx.doi.org/10.3233/SW-150175) are presented. This thesis aims to fill the gaps between the DQV, the definitions by Zaveri et al. and the realization of linked data quality assessments, to fulfil all requirements to link data quality assessments.
Master
A Visualization Recommendation Tool for Production Systems
Supervised by Prof. Dr. Christoph Quix, Günther Schuh; Advisor(s): Arnab Chakrabarti, M.Sc., Frederick Sauermann (WZL, RWTH)
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
Collaborative Immersive Learning Analytics
Supervised by PD Dr. Ralf Klamma, AOR; Advisor(s): Benedikt Hensen, M.Sc.
Our approach is a comprehensive and evolutionary sociotechnological learning analytics and design process leading to a flexible infrastructure where professional communities can co-create their wearable enhanced learning solution.
Bachelor
Data Analysis of Micromobility in the City of Aachen
This thesis focuses on the data analysis of micromobility data in Aachen. The goal is to use data science methods to gain insights from the already gathered data. To this end, a suitable data model should be defined, which then enables the analysis of both station-based, free-floating and hybrid shared mobility modes. On this defined data basis, various analyses should be performed.
Bachelor
Disaggregating Traffic Demand Data for Agent-Based Traffic Simulations
Traditional Traffic Demand Analysis as implemented in most commercial tools operate given variations of the so called four-step model. During this four-stepped modelling process origin-destination matrices are generated as output. With a rising amount of computation power, so called agent-based simulation tools are emerging. Here the traffic demand is not generated using a statistical model, but the decisions of each agent is evaluated in a simulation framework. In agent-based simulation frameworks more information is necessary, for example, complete activity chains for each agent. In this thesis a novel method for generating activity chains from origin-desination matrices is explored and compared with traditional demand forecasting methods.
Bachelor
Citation recommendation bot
Current advances in recommender systems allow for context-specific suggestions of relevant literature based on various parameters. As a contextual help in writing scientific papers, a citation recommender system should aid the student by providing a personalized suggestion of publications to consider for the Related Work section of a publication. Hence, for this project, we want to employ mentoring bots to provide suggestions of relevant scientific publications to students to support their literature research.
Bachelor
Celsius or Fahrenheit? Extracting Ontologies from OPC UA for a Plastic Processing Use-Case
Supervised by Johannes Lipp, M.Sc., Patrick Sapel; Advisor(s): IKV Univ.-Prof. Christian Hopmann (RWTH), Prof. Dr. Stefan Decker
Analyzing a live data integration of an injection molding machine at the IKV, implementing an ontology extraction feature to the existing software (Java, .net or Python) and adding semantics to the process. Demonstrate the results in a demo scenario
Bachelor, Master
A Cognitive Modeling-Based Architecture for Realistic Agents in Mixed Reality
Supervised by PD Dr. Ralf Klamma, AOR; Advisor(s): Benedikt Hensen, M.Sc.
Courses in higher education, e.g. at universities, face a challenge regarding scalability. Ideally, every student should be able to contact a mentor to benefit from the mentor’s experience and to reach the learning goals. However, if the number of participants in a course rises, the limited resources of the institution are quickly exhausted. This leads to a high workload for academic staff and decreases the mentoring quality since there is less time for mentors to address the individual needs of the students. A solution to this problem is socio-technical support for mentoring processes which combines social processes like peer mentoring and technological processes, e.g. for student’s feedback. As a result, text-based chat bots were created which can answer student’s questions and give feedback about exercises. We would now like to enhance the interaction with such bots by upgrading them to Mixed Reality agents. Such agents are shown as an avatar in a Mixed Reality environment and can interact with virtual content, users and other bots. They form a natural user interface where students can talk to the agent to get advice and it can also make autonomous decisions to guide the learning process. If the agent cannot answer a question, it can call a human mentor to join the conversation. This system considerably lowers the workload of the mentors while improving the mentoring experience of the students.
Master
A Cross-Platform User Interface Description Language for Mixed Reality
Supervised by PD Dr. Ralf Klamma, AOR; Advisor(s): Benedikt Hensen, M.Sc.
In order to provide content for the many mixed reality devices with their varying display technologies and input methods, there is a trend in mixed reality development to incorporate cross-platform support in applications. Cross reality (XR) also takes this a step further by providing cross-platform support for both augmented and virtual reality devices. The technical foundation for this is already established by 3D engines such as Unity which allow an application with one code base to be deployed to a large variety of end devices, e.g. the Microsoft HoloLens or AR-capable smartphones alike. Furthermore, libraries like the Mixed Reality Toolkit have formed a hardware abstraction layer so that the input devices are mapped onto a general input event system that can handle touch input on smartphones, 3D pointers of head-mounted displays and direct 3D in-air touch interactions alike. This foundation allows developers to port an application to multiple devices. However, one big challenge that MR developers still face is that the UI does not automatically adapt to the input specifics of each MR device in order to provide a comfortable user experience. For instance, floating 3D menus can work well on head-mounted displays but on smartphone with AR mode, they can be replaced with an on-screen touchable menu.
Bachelor, Master
Text Mining Techniques for Student Assessments
The goal of this thesis is to integrate the open-source framework ReaderBench into the Kubernetes cluster of the tech4comp project. The thesis should investigate related work in the domain of text mining, natural language processing and educational data mining. The developed extension should integrate into the existing project's infrastructure and provide mentees and their mentors/tutors with advanced feedback on the mentee's reading comprehension.
Master
Master
Incident Reporting and Security in Smart Supply Chains
Supervised by Lars Gleim, M. Sc., Jan Pennekamp; Advisor(s): Prof. Dr. Stefan Decker, Prof. Dr.-Ing. Klaus Wehrle
Development of a content security model for authenticity and integrity in resource oriented architectures, based on content signing (public-key cryptography) and hash-chaining/Merkle trees (incorporating the hash/signature of previous revisions and referenced existing resources).
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.
Bachelor
Authenticity, Integrity and Trust for Data Reuse in Resource Oriented Architectures
Supervised by Prof. Dr. Stefan Decker, Prof. Dr.-Ing. Klaus Wehrle; Advisor(s): Lars Gleim, M. Sc., Jan Pennekamp
Development of a content security model for authenticity and integrity in resource oriented architectures, based on content signing (public-key cryptography) and hash-chaining/Merkle trees (incorporating the hash/signature of previous revisions and referenced existing resources).
Bachelor
A Mixed Reality-Based Card Game for Formal and Informal Education
Supervised by PD Dr. Ralf Klamma, AOR; Advisor(s): Benedikt Hensen, M.Sc.
A challenge of existing educational Mixed Reality applications concerns the difficult accessibility of technology for students. Many applications require expensive head-mounted displays or high-end smartphones which can only be tried by students at the university for a limited amount of time. However, Mixed Reality content can also be shown on a broader range of devices using marker-based technology. Here, a marker is used as an anchor to show a 3D model above it. If the marker is filmed by a smartphone, it can calculate the view angle and render the 3D model from the same perspective. A challenge of marker-based applications is to find a meaningful integration of the markers into the environment. The markers should be easily recognizable but also need to give the user an idea about the 3D model that they can show.
Bachelor
Computer Supported Peer Review - An analysis
The goal of this bachelor thesis is the determine the current state of the art in peer review support systems.
Bachelor
Component Crawler for Mixed Reality Projects
Supervised by PD Dr. Ralf Klamma, AOR; Advisor(s): Benedikt Hensen, M.Sc.
For mixed reality applications, developers usually choose a modular development approach where the application-logic is segmented into separate components which only realize one feature. In well-designed projects, the components are reusable in different contexts within the project but also outside of it. Additionally, code from these projects can be used to find examples how to use APIs or libraries. However, many elementary features of mixed reality applications are re-implemented in new projects, instead of leveraging components from existing open-source projects.
Bachelor
Retrofitting Industrial Machines on the Edge With WebAssembly
Supervised by PD Dr. Ralf Klamma, AOR, Thomas Gries; Advisor(s): Dr. István Koren, Florian Brillowski
ENGLISH BELOW ↓ Datenstromverarbeitung an Industriemaschinen mit nativen Webtechnologien – Enabling sandboxed processing close to industrial machines with native web technologies.