Semantische Suche

Freitag, 18. März 2022, 12:00 Uhr

iCal (Download)
Ort: MS Teams
Webkonferenz: https://sdqweb.ipd.kit.edu/wiki/SDQ-Oberseminar/Microsoft_Teams

Vortragende(r) Niko Benkler
Titel Architecture-based Uncertainty Impact Analysis for Confidentiality
Vortragstyp Masterarbeit
Betreuer(in) Sebastian Hahner
Vortragsmodus online
Kurzfassung In times of highly interconnected systems, confidentiality becomes a crucial security quality attribute. As fixing confidentiality breaches becomes costly the later they are found, software architects should address confidentiality early in the design time. During the architectural design process, software architects take Architectural Design Decisions (ADDs) to handle the degrees of freedom, i.e. uncertainty. However, ADDs are often subjected to assumptions and unknown or imprecise information. Assumptions may turn out to be wrong so they have to be revised which re-introduces uncertainty. Thus, the presence of uncertainty at design time prevents from drawing precise conclusions about the confidentiality of the system. It is, therefore, necessary to assess the impact of uncertainties at the architectural level before making a statement about confidentiality. To address this, we make the following contributions: First, we propose a novel uncertainty categorization approach to assess the impact of uncertainties in software architectures. Based on that, we provide an uncertainty template that enables software architects to structurally derive types of uncertainties and their impact on architectural element types for a domain of interest. Second, we provide an Uncertainty Impact Analysis (UIA) that enables software architects to specify which architectural elements are directly affected by uncertainties. Based on structural propagation rules, the tool automatically derives further architectural elements which are potentially affected. Using the large-scale open-source contract tracing application called Corona Warn App (CWA) as a case study, we show that the UIA achieves 100% recall while maintaining 44%-91% precision when analyzing the impact of uncertainties on architectural elements.

Freitag, 1. April 2022, 11:30 Uhr

iCal (Download)
Ort: MS Teams

Vortragende(r) Felix Griesau
Titel Data-Preparation for Machine-Learning Based Static Code Analysis
Vortragstyp Masterarbeit
Betreuer(in) Robert Heinrich
Vortragsmodus online
Kurzfassung Static Code Analysis (SCA) has become an integral part of modern software development, especially since the rise of automation in the form of CI/CD. It is an ongoing question of how machine learning can best help improve SCA's state and thus facilitate maintainable, correct, and secure software. However, machine learning needs a solid foundation to learn on. This thesis proposes an approach to build that foundation by mining data on software issues from real-world code. We show how we used that concept to analyze over 4000 software packages and generate over two million issue samples. Additionally, we propose a method for refining this data and apply it to an existing machine learning SCA approach.
Vortragende(r) Patrick Spiesberger
Titel Verfeinerung des Angreifermodells und Fähigkeiten in einer Angriffspfadgenerierung
Vortragstyp Bachelorarbeit
Betreuer(in) Maximilian Walter
Vortragsmodus online
Kurzfassung Eine Möglichkeit zur Wahrung der Vertraulichkeit in der Software-Entwicklung ist die frühzeitige Erkennung von potentiellen Schwachstellen und einer darauf folgenden Eindämmung von möglichen Angriffspfaden. Durch Analysen anhand von Software-Architektur Modellen können frühzeitig Angriffspunkte gefunden und bereits vor der Implementierung behoben werden. Dadurch verbessert sich nicht nur die Wahrung von Vertraulichkeit, sondern erhöht auch die Qualität der Software und verhindert kostenintensive Nachbesserungen in späteren Phasen. Im Rahmen dieser Arbeit wird eine Erweiterung hinsichtlich der Vertraulichkeit des Palladio-Komponenten-Modells (PCM) Angreifermodell verfeinert, welches den Umgang mit zusammengesetzten Komponenten ermöglicht, Randfälle der attributbasierten Zugriffskontrolle (ABAC) betrachtet und die Modellierung und Analyse weiterer Aspekte der Mitigation erlaubt. Die Evaluation erfolgte mithilfe einer dafür angepassten Fallstudie, welche eine mobile Anwendung zum Buchen von Flügen modelliert. Das Ergebnis der Evaluation ergab ein zufriedenstellendes F1-Maß.

Freitag, 22. April 2022, 11:30 Uhr

iCal (Download)
Ort: Raum 348 (Gebäude 50.34)
Webkonferenz: https://kit-lecture.zoom.us/j/67744231815

Vortragende(r) Hatem Nouri
Titel On the Utility of Privacy Measures for Battery-Based Load Hiding
Vortragstyp Bachelorarbeit
Betreuer(in) Vadim Arzamasov
Vortragsmodus in Präsenz
Kurzfassung Hybrid presentation : https://kit-lecture.zoom.us/j/67744231815

Battery based load hiding gained a lot of popularity in recent years as an attempt to guarantee a certain degree of privacy for users in smart grids. Our work evaluates a set of the most common privacy measures for BBLH. For this purpose we define logical natural requirements and score how well each privacy measure complies to each requirement. We achieve this by scoring the response for load profile altering (e.g. noise addition) using measures of displacement. We also investigate the stability of privacy measures toward load profile length and number of bins using specific synthetic data experiments. Results show that certain private measures fail badly to one or many requirements and therefore should be avoided.

Vortragende(r) Niels Modry
Titel Theory-guided Load Disaggregation in an Industrial Environment
Vortragstyp Bachelorarbeit
Betreuer(in) Pawel Bielski
Vortragsmodus in Präsenz
Kurzfassung The goal of Load Disaggregation (or Non-intrusive Load Monitoring) is to infer the energy consumption of individual appliances from their aggregated consumption. This facilitates energy savings and efficient energy management, especially in the industrial sector.

However, previous research showed that Load Disaggregation underperforms in the industrial setting compared to the household setting. Also, the domain knowledge available about industrial processes remains unused.

The objective of this thesis was to improve load disaggregation algorithms by incorporating domain knowledge in an industrial setting. First, we identified and formalized several domain knowledge types that exist in the industry. Then, we proposed various ways to incorporate them into the Load Disaggregation algorithms, including Theory-Guided Ensembling, Theory-Guided Postprocessing, and Theory-Guided Architecture. Finally, we implemented and evaluated the proposed methods.

Freitag, 29. April 2022, 11:30 Uhr

iCal (Download)
Ort: Raum 348 (Gebäude 50.34)
Webkonferenz: https://sdqweb.ipd.kit.edu/wiki/SDQ-Oberseminar/Microsoft_Teams

Vortragende(r) Sebastian Weber
Titel Co-Simulation von Hardware und Software im Palladio Komponentenmodell
Vortragstyp Masterarbeit
Betreuer(in) Jörg Henß
Vortragsmodus online
Kurzfassung Das Palladio Komponentenmodell (PCM) ermöglicht die Modellierung und Simulation der Qualitätseigenschaften eines Systems aus komponentenbasierter Software und für die Ausführung gewählter Hardware. Stehen dabei bereits Teile des Systems zur Verfügung können diese in die Co-Simulation von Workload, Software und Hardware integriert werden, um weitere Anwendungsgebiete für das PCM zu ermöglichen oder die Anwendung in bestehenden zu verbessern.

Die Beiträge dieser Arbeit sind das Erarbeiten von sechs verschiedenen Ansätzen zur Anpassung des PCM für unterschiedliche Anwendungsgebiete und deren Einstufung anhand von Bewertungskriterien. Für den dabei vielversprechendsten Ansatz wurde ein detailliertes Konzept entwickelt und prototypisch umgesetzt. Dieser Ansatz, ein Modell im PCM mittels einer feingranularen Hardwaresimulation zu parametrisieren, wird in Form des Prototyps bezüglich seiner Umsetzbarkeit, Erweiterbarkeit und Vollständigkeit evaluiert. Die Evaluation der prototypischen Umsetzung erfolgt unter anderem anhand der Kriterien Benutzbarkeit, Genauigkeit und Performance, die in Relation zum PCM betrachtet werden. Der Prototyp ermöglicht die Ausführung einer Hardwaresimulation mit im PCM spezifizierten Parametern, die Extraktion dabei gemessener Leistungsmerkmale und deren direkte Verwendung in einer Simulation des PCM.

Vortragende(r) Jonas Koch
Titel Verbesserung von Worteinbettungs-basierter Rückverfolgbarkeitsanalyse durch Konzeptwissen
Vortragstyp Bachelorarbeit
Betreuer(in) Tobias Hey
Vortragsmodus in Präsenz
Kurzfassung Anforderungsrückverfolgbarkeit, also das Auffinden von Umsetzungen oder Beschreibungen von Anforderungen in anderen Software-Artefakten, spielt eine wichtige Rolle bei der Pflege und Weiterentwicklung großer Softwaresysteme. So können automatisierte Anforderungsrückverfolgungsverfahren beispielsweise dabei helfen Implementierungen von Anforderungen zu finden. Bei diesen Verfahren können allerdings Probleme auftreten, wenn Anforderung und Quelltextstelle viele unterschiedliche Worte enthalten. In dieser Arbeit wird untersucht, ob die Performanz des automatisierten Anforderungsrückverfolgungsverfahrens FTLR durch Einbindung von hinter den Begriffen der Anforderungen stehenden Konzepten und Themen zu Anforderungen verbessert werden kann. Hierfür wurden mehrere Verfahren zur Konzeptanreicherung sowie verschiedene Einbindungen der gefundenen Konzepte in FTLR entworfen und analysiert. Hierzu wurden Konzepte durch den Einsatz von Informationen aus Wissensgraphen und Verfahren zur Themenmodellierung/Themenbeschriftung angereicht. Durch die Einbindung der gefundenen Konzepte verbesserte sich der MAP-Wert um bis zu 4 % und der F1-Wert um bis zu 3,8 %.

Freitag, 29. April 2022, 11:30 Uhr

iCal (Download)
Ort: Raum 010 (Gebäude 50.34)
Webkonferenz: https://kit-lecture.zoom.us/j/67744231815

Vortragende(r) Anton Winter
Titel Reducing Measurements of Voltage Sensitivity via Uncertainty-Aware Predictions
Vortragstyp Bachelorarbeit
Betreuer(in) Bela Böhnke
Vortragsmodus in Präsenz
Kurzfassung Due to the energy transition towards weather-dependent electricity sources like wind and solar energy, as well as new notable loads like electric vehicle charging, the voltage quality of the electrical grid suffers. So-called Smart Transformers (ST) can use Voltage Sensitivity (VS) information to control voltage, frequency, and phase in order to enhance the voltage quality. Acquiring this VS information is currently costly, since you have to synthetically create an output variability in the grid, disturbing the grid even further. In this thesis, I propose a method based on Kalman Filters and Neural Networks to predict the VS, while giving a confidence interval of my prediction at any given time. The data for my prediction derives from a grid simulation provided by Dr. De Carne from the research center Energy Lab 2.0.
Vortragende(r) Thomas Frank
Titel Tabular Data Augmentation for Mixed Data
Vortragstyp Proposal
Betreuer(in) Federico Matteucci
Vortragsmodus in Präsenz
Kurzfassung Augmentation techniques can be helpful, for instance, to improve the performance of a weak predictor or to satisfy privacy constraints. Our plan is to devise and compare augmentation pipelines on mixed data.
Vortragende(r) Elizaveta Danilova
Titel Wichtigkeit von Merkmalen für die Klassifikation von SAT-Instanzen (Proposal)
Vortragstyp Proposal
Betreuer(in) Jakob Bach
Vortragsmodus in Präsenz
Kurzfassung SAT gehört zu den wichtigsten NP-schweren Problemen der theoretischen Informatik, weshalb die Forschung vor allem daran interessiert ist, besonders effiziente Lösungsverfahren dafür zu finden. Deswegen wird eine Klassifizierung vorgenommen, indem ähnliche Probleminstanzen zu Instanzfamilien gruppiert werden, die man mithilfe von Verfahren des maschinellen Lernens automatisieren will. Die Bachelorarbeit beschäftigt sich unter anderem mit folgenden Themen: Mit welchen (wichtigsten) Eigenschaften kann eine Instanz einer bestimmten Familie zugeordnet werden? Wie erstellt man einen guten Klassifikator für dieses Problem? Welche Gemeinsamkeiten haben Instanzen, die oft fehlklassifiziert werden? Wie sieht eine sinnvolle Familieneinteilung aus?

Freitag, 6. Mai 2022, 11:30 Uhr

iCal (Download)
Ort: Raum 348 (Gebäude 50.34)
Webkonferenz: https://sdqweb.ipd.kit.edu/wiki/SDQ-Oberseminar/Microsoft_Teams

Vortragende(r) Patrick Deubel
Titel Investigating Variational Autoencoders and Mixture Density Recurrent Neural Networks for Code Coverage Maximization
Vortragstyp Masterarbeit
Betreuer(in) Daniel Zimmermann
Vortragsmodus online
Kurzfassung Graphical User Interfaces (GUIs) are a common interface to control software. Testing the graphical elements of GUIs is time-consuming for a human tester because it requires interacting with each element, in each possible state that the GUI can be in. Instead, automated approaches are desired, but they often require many interactions with the software to improve their method. For computationally-intensive tasks, this can become infeasible. In this thesis, I investigate the usage of a reinforcement learning (RL) framework for the task of automatically maximizing the code coverage of desktop GUI software using mouse clicks. The framework leverages two neural networks to construct a simulation of the software. An additional third neural network controls the software and is trained on the simulation. This avoids the possibly costly interactions with the actual software. Further, to evaluate the approach, I developed a desktop GUI software on which the trained networks try to maximize the code coverage. The results show that the approach achieves a higher coverage compared to a random tester when considering a limited amount of interactions. However, for longer interaction sequences, it stagnates, while the random tester increases the coverage further, and surpasses the investigated approach. Still, in comparison, both do not reach a high coverage percentage. Only random testers, that use a list of clickable widgets for the interaction selection, achieved values of over 90% in my evaluation.
Vortragende(r) Daniel Jungkind
Titel Wissensanreicherung von Begriffen im Quelltext
Vortragstyp Bachelorarbeit
Betreuer(in) Tobias Hey
Vortragsmodus in Präsenz
Kurzfassung Anforderungsrückverfolgung spielt im Bereich der Softwarewartung eine große Rolle. Worteinbettungsbasierte Verfahren zur Anforderungsrückverfolgung nutzen Wörter, die in Anforderungen und Quelltext vorkommen, um Rückverfolgbarkeitsverbindungen herzustellen. Semantisch äquivalente aber sprachlich unterschiedliche Formulierungen können dies erschweren. Wissen über derartige semantische Zusammenhänge zwischen verschiedenen Begriffen kann helfen, die Rückverfolgbarkeit zu verbessern. Diese Arbeit hat zum Ziel, in Quelltext vorkommende natürlichsprachliche Begriffe mit Wissen in Form von semantisch verwandten Begriffen anzureichern, um worteinbettungsbasierte Anforderungsrückverfolgung zu verbessern. Hierzu werden zunächst DBpedia-Artikel bestimmt, welche den Bedeutungen der Begriffe im Quelltext entsprechen. Daraufhin werden die Verbindungen dieser DBpedia-Artikel zu weiteren Artikeln dazu genutzt, um Begriffe zu identifizieren, die das gemeinsame Thema der Eingabe beschreiben. Hierzu werden Kategorien- und Oberbegriffsbeziehungen genutzt, um einen DBpedia-Subgraphen aufzubauen und in diesem Zusammenhangskomponenten zu identifizieren. Zentrale Knoten in diesen Zusammenhangskomponenten liefern dabei Kandidaten für die Themenbeschriftung.

Durch das Hinzufügen dieser Themenbeschriftungen konnten auf den Datensätzen eTour und eAnci Verbesserungen der F1-Werte von bis zu +9.4 % für das Bestimmen von Rückverfolgbarkeitsverbindungen erzielt werden. Dabei lagen die Verbesserungen der Präzisionswerte zwischen +1.5 % und +11.5 %.

Donnerstag, 12. Mai 2022, 13:00 Uhr

iCal (Download)
Ort: Raum 348 (Gebäude 50.34)

Vortragende(r) Thomas Weber
Titel Entwurf und Umsetzung von Zugriffskontrolle in der Sichtenbasierten Entwicklung
Vortragstyp Masterarbeit
Betreuer(in) Heiko Klare
Vortragsmodus in Präsenz
Kurzfassung Um der steigenden Komplexität technischer Systeme zu begegnen, werden in ihrer Entwicklung sichtenbasierte Entwicklungsprozesse eingesetzt. Die dabei definierten Sichten zeigen nur die für ein bestimmtes Informationsbedürfnis relevanten Daten über das System, wie die Architektur, die Implementierung oder einen Ausschnitt davon und reduzieren so die Menge an Informationen und vereinfachen dadurch die Arbeit mit dem System. Neben dem Zweck der Informationsreduktion kann auch eine Einschränkung des Zugriffs aufgrund fehlender Zugriffsberechtigungen notwendig sein. Die Notwendigkeit ergibt sich beispielsweise bei der organisationsübergreifenden Zusammenarbeit zur Umsetzung vertraglicher Vereinbarungen. Um die Einschränkung des Zugriffs umsetzen zu können, wird eine Zugriffskontrolle benötigt. Bestehende Arbeiten nutzen eine Zugriffskontrolle für die Erzeugung einer Sicht. Die Definition weiterer Sichten darauf ist nicht vorgesehen. Außerdem fehlt eine allgemeine Betrachtung einer Integration einer Zugriffskontrolle in einen sichtenbasierten Entwicklungsprozess. Daher stellen wir in dieser Arbeit das Konzept einer Integration einer rollenbasierten Zugriffskontrolle in einen sichtenbasierten Entwicklungsprozess für beliebige Systeme vor. Mit dem Konzept ermöglichen wir die feingranulare Definition und Auswertung von Zugriffsrechten für einzelne Modellelemente für beliebige Metamodelle. Das Konzept implementieren wir prototypisch in Vitruv, einem Framework für sichtenbasierte Entwicklung. Wir evaluieren diesen Prototypen hinsichtlich seiner Funktionalität mithilfe von Fallstudien. Die Zugriffskontrolle konnten wir dabei für verschiedene Fallstudien erfolgreich einsetzen. Außerdem diskutieren wir die Integrierbarkeit des Prototypen in einen allgemeinen sichtenbasierten Entwicklungsprozess.

Freitag, 13. Mai 2022, 11:30 Uhr

iCal (Download)
Ort: MS Teams
Webkonferenz: https://sdqweb.ipd.kit.edu/wiki/SDQ-Oberseminar/Microsoft_Teams

Vortragende(r) Nathan Hagel
Titel Modellierung und Simulation von dynamischen Container-basierten Software-Architekturen in Palladio
Vortragstyp Bachelorarbeit
Betreuer(in) Jörg Henß
Vortragsmodus online
Kurzfassung Mit dem Palladio Komponentenmodell (PCM) lassen sich Softwaresysteme modellieren und simulieren. Moderne verteilte Software-Systeme werden jedoch nicht mehr einfach statisch deployed, sondern es wird ein gewünschter Zustand definiert, der mithilfe einer Kontrollschleife dann eingehalten werden soll. Das passiert dann bspw. durch das Starten oder Stoppen von Containern und Pods.

In dieser Arbeit wurde eine Erweiterung des PCM um die Konzepte von Containerorchestrierungswerkzeugen wie Kubernetes erarbeitet und umgesetzt. Zusätzlich wurde ein Konzept erarbeitet um dynamische Containerbasierte Systeme zu simulieren. Es wurde dabei insbesondere die Allokation bzw. Reallokation von Pods zur Simulationszeit betrachtet. Abschließend wurde die Modellerweiterung evaluiert.

Freitag, 13. Mai 2022, 11:30 Uhr

iCal (Download)
Ort: Raum 010 (Gebäude 50.34)

Vortragende(r) Manuel Müllerschön
Titel Developing a Framework for Mining Temporal Data from Twitter as Basis for Time-Series Correlation Analysis
Vortragstyp Proposal
Betreuer(in) Fabian Richter
Vortragsmodus in Präsenz
Kurzfassung In the last decade, ample research has been produced regarding the value of user-generated data from microblogs as a basis for time series analysis in various fields.In this context, the objective of this thesis is to develop a domain-agnostic framework for mining microblog data (i.e., Twitter). Taking the subject related postings of a time series (e.g., inflation) as its input, the framework will generate temporal data sets that can serve as basis for time series analysis of the given target time series (e.g., inflation rate).

To accomplish this, we will analyze and summarize the prevalent research related to microblog data-based forecasting and analysis, with a focus on the data processing and mining approach. Based on the findings, one or several candidate frameworks are developed and evaluated by testing the correlation of their generated data sets against the target time series they are generated for.

While summative research on microblog data-based correlation analysis exists, it is mainly focused on summarizing the state of the field. This thesis adds to the body of research by applying summarized findings and generating experimental evidence regarding the generalizability of microblog data mining approaches and their effectiveness.

Vortragende(r) Moritz Teichner
Titel Standardized Real-World Change Detection Data
Vortragstyp Proposal
Betreuer(in) Florian Kalinke
Vortragsmodus in Präsenz
Kurzfassung The reliable detection of change points is a fundamental task when analysing data across many fields, e.g., in finance, bioinformatics, and medicine.

To define “change points”, we assume that there is a distribution, which may change over time, generating the data we observe. A change point then is a change in this underlying distribution, i.e., the distribution coming before a change point is different from the distribution coming after. The principled way to compare distributions, and to find change points, is to employ statistical tests.

While change point detection is an unsupervised problem in practice, i.e., the data is unlabelled, the development and evaluation of data analysis algorithms requires labelled data. Only few labelled real world data sets are publicly available and many of them are either too small or have ambiguous labels. Further issues are that reusing data sets may lead to overfitting, and preprocessing (e.g., removing outliers) may manipulate results. To address these issues, van den Burg et al. publish 37 data sets annotated by data scientists and ML researchers and use them for an assessment of 14 change detection algorithms. Yet, there remain concerns due to the fact that these are labelled by hand: Can humans correctly identify changes according to the definition, and can they be consistent in doing so?

The goal of this Bachelor's thesis is to algorithmically label their data sets following the formal definition and to also identify and label larger and higher-dimensional data sets, thereby extending their work. To this end, we leverage a non-parametric hypothesis test which builds on Maximum Mean Discrepancy (MMD) as a test statistic, i.e., we identify changes in a principled way. We will analyse the labels so obtained and compare them to the human annotations, measuring their consistency with the F1 score. To assess the influence of the algorithmic and definition-conform annotations, we will use them to reevaluate the algorithms of van den Burg et al. and compare the respective performances.

Freitag, 20. Mai 2022, 11:30 Uhr

iCal (Download)
Ort: MS Teams
Webkonferenz: https://sdqweb.ipd.kit.edu/wiki/SDQ-Oberseminar/Microsoft_Teams

Vortragende(r) Jonathan Schenkenberger
Titel Architectural Generation of Context-based Attack Paths
Vortragstyp Masterarbeit
Betreuer(in) Maximilian Walter
Vortragsmodus online
Kurzfassung In industrial processes (Industry 4.0) and other fields in our lives like the energy or health sector, the confidentiality of data becomes increasingly important. For the protection of confidential information on critical systems, it is crucial to be able to find relevant attack paths in different access-control contexts to a critical element. In order to minimize costs, it is important to already consider this issue in the design phase of the software architecture. There are already approaches considering the topic of attack path generation. However, they do not consider software architecture modeling or they do not consider both vulnerabilities and access control mechanisms. Hence, this thesis presents an approach for finding all potential attack paths in a software architecture model considering access control and vulnerabilities. However, all attack paths are often to many, so the approach presented here introduces and utilizes meaningful filter criteria based on wide-spread vulnerability classification standards.
Vortragende(r) Limanan Nursalim
Titel Automated Test Selection for CI Feedback on Model Transformation Evolution
Vortragstyp Masterarbeit
Betreuer(in) Timur Sağlam
Vortragsmodus online
Kurzfassung The development of the transformation model also comes with the appropriate system-level testing to verify its changes. Due to the complex nature of the transformation model, the number of tests increases as the structure and feature description become more detailed. However, executing all test cases for every change is costly and time-consuming. Thus, it is necessary to conduct a selection for the transformation tests. In this presentation, you will be introduced to a change-based test prioritization and transformation test selection approach for early fault detection.

Freitag, 3. Juni 2022, 11:30 Uhr

iCal (Download)
Ort: Raum 348 (Gebäude 50.34)
Webkonferenz: https://kit-lecture.zoom.us/j/67744231815

Vortragende(r) Tobias Haßberg
Titel Development of an Active Learning Approach for One Class Classifi cation using Bayesian Uncertainty
Vortragstyp Masterarbeit
Betreuer(in) Bela Böhnke
Vortragsmodus in Präsenz
Kurzfassung In One-Class classification, the classifier decides if points belong to a specific class. In this thesis, we propose an One-Class classification approach, suitable for active learning, that models for each point, a prediction range in which the model assumes the points state to be. The proposed classifier uses a Gaussian process. We use the Gaussian processes prediction range to derive a certainty measure, that considers the available labeled points for stating its certainty. We compared this approach against baseline classifiers and show the correlation between the classifier's uncertainty and misclassification ratio.

Freitag, 24. Juni 2022, 11:30 Uhr

iCal (Download)
Ort: MS Teams
Webkonferenz: https://sdqweb.ipd.kit.edu/wiki/SDQ-Oberseminar/Microsoft_Teams

Vortragende(r) Kevin Werber
Titel Assessing Word Similarity Metrics For Traceability Link Recovery
Vortragstyp Bachelorarbeit
Betreuer(in) Jan Keim
Vortragsmodus online
Kurzfassung The software development process usually involves different artifacts that each describe different parts of the whole software system. Traceability Link Recovery is a technique that aids the development process by establishing relationships between related parts from different artifacts. Artifacts that are expressed in natural language are more difficult for machines to understand and therefore pose a challenge to this link recovery process. A common approach to link elements from different artifacts is to identify similar words using word similarity measures. ArDoCo is a tool that uses word similarity measures to recover trace links between natural language software architecture documentation and formal architectural models. This thesis assesses the effect of different word similarity measures on ArDoCo. The measures are evaluated using multiple case studies. Precision, recall, and encountered challenges for the different measures are reported as part of the evaluation.

Freitag, 24. Juni 2022, 11:30 Uhr

iCal (Download)
Ort: Raum 348 (Gebäude 50.34)
Webkonferenz: https://kit-lecture.zoom.us/j/67744231815

Vortragende(r) Tobias Hombücher
Titel Generalized Monte Carlo Dependency Estimation and Anytime Supervised Filter Feature Selection
Vortragstyp Masterarbeit
Betreuer(in) Edouard Fouché
Vortragsmodus online
Kurzfassung Dependency estimation is an important problem in statistics and is applied frequently in data science. As modern datasets can be very large, dependency estimators should be efficient and leverage as much information from data as possible. Traditional bivariate and multivariate dependency estimators are only capable to estimate dependency between two or n one-dimensional datasets, respectively. In this thesis, we are interested in how to develop estimators that can estimate the dependency between n multidimensional datasets, which we call "generalized dependency estimators".

We extend the recently introduced methodology of Monte Carlo Dependency Estimation (MCDE), an effective and efficient traditional multivariate dependency estimator. We introduce Generalized Monte Carlo Dependency Estimation (gMCDE) and focus in particular on the highly relevant subproblem of generalized dependency estimation, known as canonical dependency estimation, which aims to estimate the dependency between two multidimensional datasets. We demonstrate the practical relevance of Canonical Monte Carlo Dependency Estimation (cMCDE) by applying it to feature selection, introducing two methodologies for anytime supervised filter feature selection, Canonical Monte Carlo Feature Selection (cMCFS) and Canonical Multi Armed Bandit Feature Selection (cMABFS). cMCFS directly applies the methodology of cMCDE to feature selection, while cMABFS treats the feature selection problem as a multi armed bandit problem, which utilizes cMCDE to determine relevant features.

Vortragende(r) Jonas Zoll
Titel Injection Molding Simulation based on Graph Neural Networks (GNNs)
Vortragstyp Bachelorarbeit
Betreuer(in) Daniel Ebi
Vortragsmodus in Präsenz
Kurzfassung Numerical filling simulations are an important tool for the development of injection molding parts. Existing simulations rely on numerical solvers based on the finite element method. These solvers are reliable and precise, but very computationally expensive even on simple part geometries.

In this thesis, we aim to develop a faster injection molding simulation based on Graph Neural Networks (GNNs) as a surrogate model. Our approach learns a simulation as a composition of three functions: an encoder, a processor and a decoder. The encoder takes in a graph representation of a 3D geometry of an injection molding part and returns a numeric embedding of each node in the graph. The processor updates the embeddings of each node multiple times based on its neighbors. The decoder then decodes the final embeddings of each node into physically meaningful variables, say, the fill state of the node. Our model can predict the progression of the flow front during a time step with a fixed size. To simulate a full mold filling process, our model is applied sequentially until the entire mold is filled. Our architecture is applicable to any kind of material, geometry and injection process parameters. We evaluate our architecture by its accuracy and runtime when predicting node properties. We also evaluate our models transfer learning ability on a real world injection molding part.

Vortragende(r) Mingzhe Tao
Titel Meta-learning for Encoder Selection
Vortragstyp Proposal
Betreuer(in) Federico Matteucci
Vortragsmodus in Präsenz
Kurzfassung In the real world, mixed-type data is commonly used, which means it contains both categorical and numerical data. However, most algorithms can only learn from numerical data. This makes the selection of encoder becoming very important. In this presentation, I will present an approach by using ideas from meta-learning to predict the performance from the meta-features and encoders.

Freitag, 1. Juli 2022, 11:30 Uhr

iCal (Download)
Ort: Raum 348 (Gebäude 50.34)
Webkonferenz: https://sdqweb.ipd.kit.edu/wiki/SDQ-Oberseminar/Microsoft_Teams

Vortragende(r) Anne-Kathrin Hermann
Titel Bewertung der Qualität von Low-Code-Programmen für Datenfluss-Beschreibungen
Vortragstyp Bachelorarbeit
Betreuer(in) Thomas Kühn
Vortragsmodus in Präsenz
Kurzfassung Das Messen der Qualität von Datenfluss-Low-Code-Programmen und auch das Erstellen qualitativ hochwertiger Programme ist schwer. Es entstehen viele Programme mit Anzeichen für schlechte Qualität, die zwar Ergebnisse liefern, aber schlecht wartbar und unverständlich sind. Im Laufe dieser Arbeit wurde die Übertragbarkeit, von klassischen Codemetriken und Graphmetriken überprüft und durchgeführt, um zu evaluieren, welche Metriken sich für die Messung der Qualität von Low-Code-Programmen eignen?
Vortragende(r) Quang Dao
Titel Coreference Resolution for Software Architecture Documentation
Vortragstyp Bachelorarbeit
Betreuer(in) Jan Keim
Vortragsmodus in Präsenz
Kurzfassung In software engineering, software architecture documentation plays an important role. It contains many essential information regarding reasoning and design decisions. Therefore, many activities are proposed to deal with documentation for various reasons, e.g., extract- ing information or keeping different forms of documentation consistent. These activities often involve automatic processing of documentation, for example traceability link recovery (TLR). However, there can be problems for automatic processing when coreferences are present in documentation. A coreference occurs when two or more mentions refer to the same entity. These mentions can be different and create ambiguities, for example when there are pronouns. To overcome this problem, this thesis proposes two contributions to resolve coreferences in software architecture documentation.

The first contribution is to explore the performance of existing coreference resolution models for software architecture documentation. The second is to divide coreference resolution into many more specific type of resolutions, like pronoun resolution, abbreviation resolution, etc.

Freitag, 22. Juli 2022, 11:30 Uhr

iCal (Download)
Ort: MS Teams
Webkonferenz: https://sdqweb.ipd.kit.edu/wiki/SDQ-Oberseminar/Microsoft_Teams

Vortragende(r) Philipp Uhrich
Titel Empirical Identification of Performance Influences of Configuration Options in High-Performance Applications
Vortragstyp Masterarbeit
Betreuer(in) Larissa Schmid
Vortragsmodus online
Kurzfassung Many modern high-performance applications are highly-configurable software systems that provide hundreds or even thousands of configuration options. System administrators or application users need to understand all these options and their impacts on the software performance to choose suitable configuration values. To understand the influence of configuration options on the run-time characteristics of a software system, users can use performance prediction models, but building performance prediction models for highly-configurable high-performance applications is expensive. However, not all configuration options, which a software system offers, are performance-relevant. Removing these performance-irrelevant configuration options from the modeling process can reduce the construction cost. In this thesis, we explore and analyze two different approaches to empirically identify configuration options that are not performance-relevant and can be removed from the performance prediction model. The first approach reuses existing performance modeling methods to create much cheaper prediction models by using fewer samples and then analyzing the models to identify performance-irrelevant configuration options. The second approach uses white-box knowledge acquired through dynamic taint analysis to systematically construct the minimal number of required experiments to detect performance-irrelevant configuration options. In the evaluation with a case study, we show that the first approach identifies performance-irrelevant configuration options but also produces misclassifications. The second approach did not perform to our expectations. Further improvement is necessary.

Freitag, 12. August 2022, 11:30 Uhr

iCal (Download)
Ort: Raum 348 (Gebäude 50.34)
Webkonferenz: https://kit-lecture.zoom.us/j/67744231815

Vortragende(r) Maximilian Georg
Titel A Comparative Analysis of Data-Efficient Dependency Estimators
Vortragstyp Bachelorarbeit
Betreuer(in) Bela Böhnke
Vortragsmodus online
Kurzfassung Dependency estimation is a significant part of knowledge

discovery and allows strategic decisions based on this information. Many dependency estimation algorithms require a large amount of data for a good estimation. But data can be expensive, as an example experiments in material sciences, consume material and take time and energy. As we have the challenge of expensive data collection, algorithms need to be data efficient. But there is a trade-off between the amount of data and the quality of the estimation. With a lack of data comes an uncertainty of the estimation. However, the algorithms do not always quantify this uncertainty. As a result, we do not know if we can rely on the estimation or if we need more data for an accurate estimation. In this bachelor’s thesis we compare different state-of-the-art dependency estimation algorithms using a list of criteria addressing the above-mentioned challenges. We partly developed the criteria our self as well as took them from relevant publications. Many of the existing criteria where only formulated qualitative, part of this thesis is to make these criteria measurable quantitative, where possible, and come up with a systematic approach of comparison for the rest. We also conduct a quantitative analysis of the dependency estimation algorithms by experiment on well-established and representative data sets that performed well in the qualitative analysis.

Freitag, 19. August 2022, 11:30 Uhr

iCal (Download)
Ort: Raum 348 (Gebäude 50.34)
Webkonferenz: https://kit-lecture.zoom.us/j/67744231815

Vortragende(r) Sönke Jendral
Titel Refining Domain Knowledge for Domain Knowledge Guided Machine Learning
Vortragstyp Bachelorarbeit
Betreuer(in) Pawel Bielski
Vortragsmodus online
Kurzfassung Advances in computational power have led to increased in interest in machine learning techniques. Sophisticated approaches now solve various prediction problems in the domain of healthcare. Traditionally, machine learning techniques integrate domain knowledge implicitly, by statistically extracting dependencies from their input data. Novel approaches instead integrate domain knowledge from taxonomies as an external component.

However, these approaches assume the existence of high quality domain knowledge and do not acknowledge issues stemming from low quality domain knowledge. It is thus unclear what low quality domain knowledge in the context of Domain Knowledge Guided Machine Learning looks like and what its causes are. Further it is not clearly understood what the impact of low quality domain knowledge on the machine learning task is and what steps can be taken to improve the quality in this context.

In this Thesis we describe low quality domain knowledge and show examples of such knowledge in the context of a sequential prediction task. We further propose methods for identifying low quality domain knowledge in the context of Domain Knowledge Guided Machine Learning and suggest approaches for improving the quality of domain knowledge in this context.

Vortragende(r) Elizaveta Danilova
Titel Wichtigkeit von Merkmalen für die Klassifikation von SAT-Instanzen (Abschlusspräsentation)
Vortragstyp Bachelorarbeit
Betreuer(in) Jakob Bach
Vortragsmodus in Präsenz
Kurzfassung Das SAT-Problem ist ein zentrales Problem der theoretischen Informatik. Wegen seiner NP-Schwere sind Forscher insbesondere an effizienten Lösungsverfahren dafür interessiert. Die Kenntnis der Familie einer Instanz kann zur Problemlösung beitragen. In unserer Arbeit haben wir untersucht, wie SAT-Instanzen durch maschinelles Lernen effizient klassifiziert werden können und welche Verfahren sich am besten dazu eignen. Außerdem betrachteten wir, welche Merkmale die Instanzen am eindeutigsten charakterisieren und wie sich die Anzahl der verwendeten Merkmale auf das Klassifikationsergebnis auswirkt. Letztlich untersuchten wir, welche Familien vermehrt fehlklassifiziert werden und was die Gründe dafür sind.

Freitag, 26. August 2022, 11:30 Uhr

iCal (Download)
Ort: Raum 348 (Gebäude 50.34)
Webkonferenz: https://kit-lecture.zoom.us/j/67744231815

Vortragende(r) Manuel Müllerschön
Titel Deriving Twitter Based Time Series Data for Correlation Analysis
Vortragstyp Bachelorarbeit
Betreuer(in) Fabian Richter
Vortragsmodus in Präsenz
Kurzfassung Twitter has been identified as a relevant data source for modelling purposes in the last decade. In this work, our goal was to model the conversational dynamics of inflation development in Germany through Twitter Data Mining. To accomplish this, we summarized and compared Twitter data mining techniques for time series data from pertinent research. Then, we constructed five models for generating time series from topic-related tweets and user profiles of the last 15 years. Evaluating the models, we observed that several approaches like modelling for user impact or adjusting for automated twitter accounts show promise. Yet, in the scenario of modelling inflation expectation dynamics, these more complex models could not contribute to a higher correlation between German CPI and the resulting time series compared to a baseline approach.

Freitag, 2. September 2022, 11:30 Uhr

iCal (Download)
Ort: Raum 348 (Gebäude 50.34)
Webkonferenz: https://kit-lecture.zoom.us/j/67744231815

Vortragende(r) Benjamin Jochum
Titel Surrogate models for crystal plasticity - predicting stress, strain and dislocation density over time
Vortragstyp Proposal
Betreuer(in) Daniel Betsche
Vortragsmodus in Präsenz
Kurzfassung When engineers design structures, prior knowledge of how they will react to external forces is crucial. Applied forces introduce stress, leading to dislocations of individual molecules that ultimately may cause material failure, like cracks, if the internal strain of the material exceeds a certain threshold. We can observe this by applying increasing physical forces to a structure and measure the stress, strain and the dislocation density curves.

Finite Elemente Analysis (FEM) enables the simulation of a material deforming under external forces, but it comes with very high computational costs. This makes it unfeasible to conduct a large number of simulations with varying parameters. In this thesis, we use neural network based sequence models to build a data-driven surrogate model that predicts stress, strain and dislocation density curves produced by an FEM-simulation based on the simulation’s input parameters.

Freitag, 9. September 2022, 11:30 Uhr

iCal (Download)
Ort: Raum 348 (Gebäude 50.34)
Webkonferenz: https://kit-lecture.zoom.us/my/floriankalinke_(292608)

Vortragende(r) Moritz Teichner
Titel Standardized Real-World Change Detection Data Defense
Vortragstyp Bachelorarbeit
Betreuer(in) Florian Kalinke
Vortragsmodus in Präsenz
Kurzfassung The reliable detection of change points is a fundamental task when analyzing data across many fields, e.g., in finance, bioinformatics, and medicine.

To define “change points”, we assume that there is a distribution, which may change over time, generating the data we observe. A change point then is a change in this underlying distribution, i.e., the distribution coming before a change point is different from the distribution coming after. The principled way to compare distributions, and thus to find change points, is to employ statistical tests.

While change point detection is an unsupervised problem in practice, i.e., the data is unlabeled, the development and evaluation of data analysis algorithms requires labeled data. Only a few labeled real-world data sets are publicly available, and many of them are either too small or have ambiguous labels. Further issues are that reusing data sets may lead to overfitting, and preprocessing may manipulate results. To address these issues, Burg et al. publish 37 data sets annotated by data scientists and ML researchers and assess 14 change detection algorithms on them. Yet, there remain concerns due to the fact that these are labeled by hand: Can humans correctly identify changes according to the definition, and can they be consistent in doing so?