Offene Themen für Projekt- und Diplomarbeiten
Weitere Webseiten mit Themen
- Themen am Institut für Rundfunktechnik (IRT) zu Multimedia-Technologien (SIP, RTSP, UPnP, DVB). Bei Interesse wenden Sie sich an Raphael Wimmer.
- Themen am Institut für Wirtschaftsinformatik und Neue Medien für Studierende mit Nebenfach Medienwirtschaft. Eine Betreuung durch die BWL ist nach Absprache mit dem Prüfungsausschuss kein Problem.
Freie Themen
Auf dieser Webseite sind freie Bachelor-, Projekt- oder Diplomarbeitsthemen bei unseren Mitarbeitern zu finden. Am Anfang jeder Zeile ist angegeben für welchen Typ von Arbeit sich das Thema eignet. Ein Klick auf ein Thema bringt weitere Informationen.
Show only: bachelor theses, master theses, project theses, diploma theses, PWAL,Type | Advisor | Title |
---|---|---|
MT/BT/PT/DT | Prof. Dr. Florian Alt |
Abschlussarbeiten im Bereich Usable Security and Privacy
Students interested in topics related to usable security and privacy have the opportunity to do their master theses / bachelor theses / practical research project (Einzelpraktikum) at the CODE Research Institute for Cyber Defense (University of the Bundeswehr, Munich). More information on the research group on Usable Security and Privacy Group can be found on our website. We offer a large variety of topics, including but not limited to:
If you are interested in working with us, please get in touch with the respective contact person. Details |
MT/PT | Florian Bemmann |
Deep Activity Tracking on Android Smartphones
[Updated 23.12.2022] In this Master Thesis you will develop novel solutions to make use of unstructured UI tree data yielded form Android Smartphones. Such data could be used in future adaptive systems to learn what the user is aiming for, to make more accurate and concrete predictions. Privacy is also a central aspect in this topic.Please check the PDF announcement on my webspace: Master Thesis: Deep Activity Tracking on Android Smartphones Details |
MT | Florian Bemmann |
Interactive Machine Learning
In this thesis you bring machine learning to end users. In a mobile application or game, you allow users to train models on their data. Aims can be education, rasising resistance against manipulative targeted content, or creating the user a benefit in a quantified-self application.Please check the PDF announcement on my webspace: InteractiveML2023.pdf Details |
BT/MT | Francesco Chiossi |
Design of a Virtual Reality Adaptive System based on Electrodermal Activity phasic components
DescriptionElectrodermal activity (EDA) denotes the measurement of continuous changes in the electrical conductance properties of the skin in response to sweat secretion by the sweat glands. EDA is autonomously modulated by sympathetic nervous system (SNS) activity, a component of the autonomic nervous system (ANS), which is involved in the control of involuntary bodily functions as well as cognitive and emotional states. Specifically, phasic EDA activity correlated with stress, cognitive load, and attention orienting. Therefore, measuring phasic EDA responses can give us information about the user's state.In this thesis project, we want to develop an adaptive system that modifies the visual complexity of the VR environment based on changes in phasic EDA. Specifically, we want to use new signal processing methodologies termed adaptive thresholding and gaussian filtering.The research consists of three main stages: (1) validation of the psychophysiological inference underpinning the adaptive system (2) implementation of a working VR prototype, and (3) an evaluation of the adaptive environment. You will
You need
References
Details |
BT/MT | Francesco Chiossi |
Physiologically adaptive MR Blending
DescriptionMixed reality (MR) systems refer to the entire broad spectrum that ranges from physical to virtual reality (VR). It includes instances that overlay virtual content on physical information, i.e., Augmented Reality (AR), and those that rely on physical content to increase the realism of virtual environments, i.e., Augmented Virtuality (AV). Such instances tend to be pre-defined for the blend of physical and virtual content. To what extent can MR systems rely on physiological inputs to infer user state and expectations and, in doing, adapt their visualization in response? Measurement sensors for eye and body motion, autonomic arousal (e.g., respiration, electrodermaland heart activity), and cortical activity (e.g., EEG, fNIRS) are widely used in psychological and neuroscience research to infer hidden user states, such as stress, overt/covert attention, working memory load, etc.However, it is unclear if such inferences can serve as useful real-time inputs in controlling the presentation parameters of MR environments.In this thesis project, we will investigate whether this blend can be adaptive to user states, which are inferred from physiological measurements derived from gaze behavior, peripheral physiology (e.g.., electrodermal activity (EDA); electrocardiography (ECG)), and cortical activity (i.e.., electroencephalography (EEG)). In other words, we will investigate the viability and usefulness of MR use scenarios that vary in their blend of virtual and physicalcontent according to user physiology. In particular, we will focus on understanding how physiological readings can passively determine the appropriate amount ofvisual information to present within an MR system. You will
You need
References
Details |
BT/MT | Francesco Chiossi |
Evaluation of an Adaptive VR environment that Uses EEG Measures as Inputs to a Biocybernetic Loop
DescriptionBiocybernetic adaptation is a form of physiological computing where real-time physiological data from the brain and the body can be used as an input to adapt the user interface. In this way, from the physiological data, we can infer the userâs state and design implicit interactions in VR to change the scene to support certain goals. This thesis aims the develop and evaluate an adaptive VR environment designed to maximize users' performance by exploiting changes in real-time electroencephalography (EEG) to adjust the level of visual complexity. The research consists of three main stages: (1) validation of the input EEG measures underpinning the loop; (2) implementation of a working VR prototype; and (3) an evaluation of the adaptive environment. Specifically, we aim to demonstrate the sensitivity of EEG power in the (frontal) theta and (parietal) alpha bands to adapt levels of visual complexity. You will
You need
References
Details |
BT/MT | Francesco Chiossi |
Modulating distraction by adapting the perceptual load: implementation of a biocybernetic loop to support performance and prevent distraction
DescriptionResearch from cognitive science and computerized displays of simple stimuli has shown how perceptual load is a critical factor for modulating distraction. Perceptual load is the amount of information involved in processing task stimuli. According to Lavie (1995), our attentional resources are limited and mainly directed towards task-relevant goals, but we might be more prone to distractors if we have cognitive spare resources. Previous research showed that human faces have bigger distracting power than non-face objects. This project aims to assess the distracting potential distracting effect of human avatars in a social VR scenario. We aim to transfer of traditional paradigms that assess attention and distraction to immersive VR. Lastly, we adapt the target-distractor recognizability to evaluate if a physiologically-adaptive system that optimizes for perceptual load can support task performance. The research consists of three main stages: (1) validation of the psychophysiological inference underpinning the physiological loop (2) implementation of a working VR prototype, and (3) an evaluation of the adaptive environment. You will
You need
ReferencesDetails |
BT/MT | Francesco Chiossi |
Design of a physiological loop settled in a Social VR scenario to support task performance and user experience
DescriptionPhysiological computing is a multidisciplinary research field in HCI wherein the interaction depends on measuring and responding to the user's physiological activity in real-time (Fairclough, 2009). Physiological computing allows for implicit interaction; by monitoring the physiological signals of the user, the computer can infer, e.g., if the task demands are either too challenging or easy, and either adapt the difficulty level or when users are getting distracted from the task, the system could give them a notification. Measuring the psychological state of the user creates intriguing possibilities for Social VR scenarios as we can either adapt the number of displayed avatars, their form or even their proxemic distance. This thesis aims the develop an adaptive Social VR environment designed to support users' performance when engaged in a cognitive task using a measure of physiological state (electrodermal activity: EDA) as input for adaptation. The research consists of three main stages: (1) validation of the psychophysiological inference underpinning the physiological loop (2) implementation of a working VR prototype, and (3) an evaluation of the adaptive environment. You will
You need
References
Details |
BT/MT | Sarah Delgado |
Offline (Quantum) Key Distribution
Imagine Bob's office is connected via a (quantum-)encrypted connection to a server. How could Bob access this server from his home office if he does not have the necessary hardware at home? Well, he could get keys in his office and save them on his personal key-safe token. He could subsequently use the token at home and connect to the server. The topic of offline distribution of cryptographic keys is interesting for researchers and practitioners alike, even outside the QKD context. Hence, exemplary open questions include: Which use cases for offline key distribution exist? How could the key-safe token look like (design, usability and security)? Is there a possibility to detect unauthorized access to the token? Details |
MT | Dennis Dietz |
Self-made tracking system for sports analysis in VR
DescriptionThis projects purpose is to investigate in building a full body tracking system based on self-made trackers which are usable by the HTC VIVE and its Lighthouses. We want to compare the original HTC VIVE tracker with a varying amount of self-made trackers in order to use it for VR sport analysis. Tasks
Preferred qualification
Suggested Reading
Details |
MT | Linda Hirsch, Julian Rasch |
Tracking Socio-Spatial Activities in Virtual Reality (VR)
VR offers the possibility to create own realities independent from the physical reality. Immersed in VR, users can explore and interact with their virtual surroundings. In this work, you will explore how to comprehensibly display user triggered changes, movement patterns and interactions in a shared spatial VR across time and space. It will be your task to implement different layers of information for a VR scene before developing a menu in which users can alter the displayed information linked to prior usersâ activities. You will deal with the time and scalability dimensions of such traces and explore the duration of displaying such information as well as the tracking time.
Tasks:
Requirements:
Suggested Reading:
Details |
BT/MT | Sören Klingner |
Development of Occupant Monitoring Methods in Virtual Reality in the Automotive Domain
DescriptionDevelopment of a method in virtual reality to measure user behavior or user states (occupant monitoring) in the automotive domain. Tasks
Requirements
ContactEmail: klingner ät fortiss.orgDetails |
BT/MT | Sören Klingner |
Development of Situational Awareness Measurement Methods in Virtual Reality in the Automotive Domain
DescriptionCar accidents are a significant concern, as they claim a high number of yearly fatalities. These accidents have been accounted to originate from recognition errors, including driver's inattention, internal and external distraction, and inadequate surveillance, causing decision errors. These errors can be attributed to a lack of situation awareness.Thus the development of a tool to measure people's situation awareness in VR could be very beneficial. It could be used to assess the user's situation awareness and compare different scenarios and interfaces and their respective effects. Tasks
Requirements
ContactEmail: klingner ät fortiss.orgDetails |
BT/MT | Sören Klingner |
Smoking Simulation in Virtual Reality
DescriptionSmoking lead to long-term health issues, causes death and big costs in the economy and health system. Many people would like to stop smoking, but many attempts stay unsuccessful. That is why new ways of treating nicotine addiction are being sought. Virtual Reality (VR) has developed rapidly with many important technical advancements that is becoming more widely available and user-friendly. This opens new therapy possibilities. Tasks
Requirements
ContactEmail: klingner ät fortiss.orgDetails |
BT/MT | Sören Klingner |
User Profiling through Interaction and User Reaction
DescriptionIn this thesis project, we will investigate how an AI-system learns characteristics about the user through interaction patterns and user reactions. The final goal is a system in a specific domain, that adapts to the user based on their characteristics. Tasks
Requirements
ContactEmail: klingner ät fortiss.orgDetails |
PT | Yuanting Liu |
Praktikum Entwicklung von Mediensystemen: Stress Management mit eingebetteten Geräten
InhalteDas bayerische Landesforschungsinstitut fortiss und IBM werden im Rahmen des IBM fortiss Center forAI das Thema Stress-Management für sicherheitskritische Anwendungen erforschen. Dafuür wird einKonzept entwickelt, um Stress bei Einsatzkräften der Feuerwehr zu überwachen und managen. Die Ideen werden prototypisch umgesetzt und präsentiert. Die Workshops und Gespräche während desPraktika können entweder in englischer oder deutscher Sprache gehalten werden. BewerbungBeschreiben Sie kurz Ihre Motivation, relevante Fachkenntnisse, beispielsweise aus früheren Kursen,Jobs und anderen Projekten, die Ihre Fähigkeiten in einem oder mehreren der folgenden Bereichedemonstrieren: Programmierung, Benutzererfahrung, Nutzerstudien, Prototyping. Details |
MT | Prof. Dr. Sven Mayer |
Machine Learning Based Capacitive Sensing for Tangible Interaction
After an initial induction into existing marker technologies and conducive 3D printed objects, the goal is to design and build new a machine learning (ML) pipeline to detect conductive markers. Therefore the prototyping of physical markers is required, these will be used to record capacitive tangible footprints using the screen of a large capacitive screen as ML ground truth data. Based on that a model will be trained to distinguish and classify capacitive markers on touchscreens using a new ML classifier. You will:
You need:
References
Details |
MT | Prof. Dr. Sven Mayer |
Body- and Hand-Aware In-Environment Selection Techniques
The goal of this work is to get an overview of the vast variety of selection methods in smart environments, mixed reality, and VR. Through a literature review, the first step is to select a handful of selected methods. Therefore, in the next step, these interactions need to be implemented, to allow them to be compared in a lab study. Here, the aim is to compare these technologies with respect to measurements such as accuracy, speed, immersion, presence, and their effect on the embodiment. You will:
You need:
References
Details |
MT | Prof. Dr. Sven Mayer |
Push-To-Talk over WebRTC
This project aims to build a push-to-talk (PTT) system on top of the WebRTC API. PTT is a communication technique that allows the user to talk to others through a microphone only when the user presses a button (or similar). The project will start with a literature study to determine how PTT can be implemented on top of WebRTC. After that, the focus will be on implementing a PTT system. You will:
You need:
References
Details |
MT | Prof. Dr. Sven Mayer |
Wireless Mesh Networking App
This project aims to use the ad hoc network functionality of iPhones to build a mesh network (especially if the provider network is down) within a manageable area). A mesh network is a network where each device can act as a router for other devices. This allows for a network that is very robust against failures of individual devices. The project will start with a literature study to find out how to build such a network. After that, the focus will be on the implementation of the network. You will:
You need:
References
Details |
BT/MT | Florian Müller |
Augmented Reality on the go
With the increasing proliferation of augmented reality glasses (e.g. Hololens), we are getting closer to the vision of truly mobile interaction in a digitally augmented physical world. As a consequence, a major part of the interaction with such devices will happen on the go. This establishes a need for interaction and visualization techniques that support the user in highly mobile situations. In this thesis, we will prototype and evaluate such interaction and visualization techniques to better support users while interacting on the go.
Tasks:
Requirements:
Details |
BT/MT | Florian Müller |
How much Reality in Mixed Reality?
Mixed reality describes a continuum between physical reality and complete digitality (i.e., virtual reality). Both, reality and digitality, offer inherent advantages and disadvantages depending on the use case. For example, a higher degree of digitality causes a loss of connection to the real world and, on the other hand, a higher degree of reality decreases the immersiveness of the experience.In this thesis, we will investigate how the positive and negative factors of reality and digitality affect different usage scenarios. Furthermore, we want to investigate how users can move on this continuum, i.e., how they can control the amount of digitality and reality.
Tasks:
Requirements:
Details |
MT | Prof. Dr. Sylvia Rothe |
Entwicklung einer graphischen Oberfläche für KI-basierte Anwendungen im Audio-Bereich
Um Töne zu generieren oder ein Bildsequenzen anzupassen, können KI-basierte Methoden Sounddesignern große Unterstützungsmöglichkeiten bieten. Dabei ist es wichtig, die richtigen Eingabemethoden zu finden. Aufgaben:
Details |
MT | Prof. Dr. Sylvia Rothe |
Entwicklung einer graphischen Oberfläche für KI-basierte Anwendungen im Filmschnitt
Eine Reihe KI-basierter Tools, die momentan veröffentlicht werden, haben das Potential, Filmschaffende in ihrer kreativen Arbeit zu unterstützen. Momentan braucht es dazu noch für jeden Task unterschiedliche Tools. Auch sind die Eingabemöglichkeiten noch nicht so, wie sie Filmschaffende für ihre Arbeit benötigen. Aufgaben:
Details |
MT | Prof. Dr. Sylvia Rothe |
KI-basierte Bildgenerierung zur Unterstützung Leichter Sprache
Leichte Sprache ist ein wichtiges Mittel, um Medieninhalte Menschen mit Lernbehinderungen zugänglich zu machen. Neben der Umsetzung von Texten in Leichte Sprache, werden im Print- und Webbereich zur Unterstützung des Textverständnisses auch Bilder genutzt.Die Arbeit untersucht die Möglichkeit, dafür KI-generierte Bilder zu nutzen. Aufgaben:
Details |
MT | Prof. Dr. Sylvia Rothe |
Erkennung von Ironie in Filmen zur Kennzeichnung dieser in leichter Sprache
Für Menschen mit Lernbehinderung ist es nicht immer leicht, Ironie zu erkennen. Deshalb wird sie bei der Umsetzung in Leichter Sprache besonders gekennzeichnet. Aufbauend auf der Masterarbeit von Christoph Weber (http://www.medien.ifi.lmu.de/lehre/arbeiten/detail.xhtml-php?pub=rothe_NLP ) sollen neue Netzwerkarchitekturen und Herangehensweisen erprobt werden (z.B. Transformer, Few-Shot-Learning). Aufgaben:
Details |
PT/MT/BT | Sophia Sakel, Svenja Schött |
A Social Robot to support mental health
|
BT/MT/PT | Dr. Daniel Ullrich |
"Fernstudent": Ein Roboter-Avatar für Studenten in Lehrveranstaltungen
Problem StatementStudierende haben das Remote-Studium (aus dem Home-Office) zu schätzen gelernt und möchten es weiterhin (situativ) nutzen.Die Interaktion in Lehrveranstaltungen leidet allerdings unter einem Mix von teilweise physisch anwesenden und teilweise physisch abwesenden Studierenden.Der "Fernstudent" ist ein Konzept, um diesem Problem zu begegnen: Studierende, die sich remote zuschalten, erhalten einen "Avatar" in Form Roboters, der physisch in der Lehrveranstaltung präsent ist. Dieser Avatar kann aus der Ferne gesteuert werden, um so in der Lehrveranstaltung teilnehmen und interagieren zu können (beispielsweise in Diskussionen). TasksZiel des Projekts ist die Entwicklung eines Prototypens, der das Konzept "Fernstudent" implementiert.Das Konzept wird anschliessend mittels Prototypens in Live-Lehrveranstungen eingesetzt und evaluiert. Bevorzugte Skills und Interessen
Details |
MT | Thomas Weber |
Perception of Code Style
How easy it is to read and understand a piece of code can very much depend on the code style and whether its author took care of this. Particularly novice programmers could greatly benefit from well styled code. At the same time, they can lack the experience and expertise to adhere to code style conventions in their own code. In this thesis, you will analyze an existing data set of novice code contributions with respect to code style. Based on these insights, you will perform additional empricial experiments, i.e. using surveys, lab experiments, eye tracking studies, etc. to further determine how code style is perceived by programmers of different levels of expertise and how we can support them to create better code. This thesis is supervised in collaboration with the chair on Technology-Enhanced Learning. Details |
BT = bachelor thesis - PT = project thesis - DT = diploma thesis - MT = master thesis - PWAL = practical research course