AI-based Methods and Applications for Software Engineering
Permanent URI for this collectionhttps://hdl.handle.net/10125/107570
Browse
Recent Submissions
Item type: Item , Unsupervised Extraction of Test Scenarios from Time-Series Sensor Data using Trace Graphs(2024-01-03) Brinkmann, Jannik; Metzger, Noah; Bartelt, ChristianThe dependability of autonomous agents, such as self-driving cars, in complex and unpredictable real-world environments is a critical challenge. To address this, scenario-based testing attempts to assess agents across a range of diverse scenarios. However, the manual definition of these test scenarios is often labor-intensive and requires considerable domain expertise, while existing methods to extract scenarios from sensor data also depend on intricate assumptions about the data. To overcome these limitations, we introduce an unsupervised approach that uses trace graphs to determine meaningful scenario boundaries in time-series sensor data, without the need for additional domain knowledge or manual input. Our experimental results demonstrate that our method can extract a small but comprehensive set of test scenarios that captures the full spectrum of the agent's experiences as observed in the sensor data.Item type: Item , Representative Dataset Generation Framework for AI-based Failure Analysis during real-time Validation of Automotive Software Systems(2024-01-03) Abboush, Mohammad; Knieke, Christoph; Rausch , AndreasRecently, thanks to its ability of extracting knowledge from historical data, the data-driven approach has been widely used in various phases of the system development life cycle. In real-time system validation, remarkable achievements have been accomplished in developing an intelligent failure analysis based on historical data. However, despite its superiority over other conventional approaches, e.g., model-based and signal-based, the availability of representative datasets persists as a major challenge. Thus, for different engineering applications, new solutions to generate representative faulty data in different forms should be explored. Therefore, in this study, a novel approach based on Hardware-in-the-Loop (HIL) simulation and real-time Fault Injection (FI) method is proposed to generate and collect data samples under single and simultaneous faults for Machine Learning (ML) applications during system validation phases. The developed framework can generate not only sequential data, but also textual data including fault logs. The results show the applicability of the proposed framework in simulating and capturing the system behaviour under faults within the system components.Item type: Item , Towards Inductive Learning of Formal Software Architecture Rules(2024-01-03) Schindler, Christian; Rausch , AndreasThis paper explores the application of inductive learning for inferring software architecture rules from real-world systems. Traditional manual rule specification approaches are time-consuming and error-prone, motivating the need for automated rule discovery. Leveraging a dataset of software architecture instances and a metamodel capturing implementation facts, we train inductive learning algorithms to extract meaningful rules. The induced rules are evaluated against a predefined hypothesis and their generalizability across different system subsets is investigated. The research highlights the capabilities and limitations of inductive rule learning in the area of software architecture, aiming to inspire further innovation in data-driven rule discovery for more intelligent software architecture practices.Item type: Item , Agentic Relationship Dynamics in Human-AI Collaboration: A study of interactions with GPT-based agentic IS artifacts(2024-01-03) Svensson, Björn; Keller, ChristinaGenerative Artificial Intelligence (AI) having become increasingly embedded into work in both academia and industry has put a magnifying glass on Human-AI collaboration. With this paper, we seek to answer calls for research on the interactions between human and AI agents and their outcomes. We adopt the IS Delegation Framework (Baird & Maruping, 2021) to look at dynamics in relationships between human agents and Generative Pre-trained Transformer-based agentic IS artifacts and how these dynamics manifest. By conducting and analyzing data from semi-structured interviews, we were able to identify five salient agentic relationship dynamics affecting common understanding, willingness to delegate, cognitive load in human agents, confidence, and human agents' abilities to break GPT-based agentic IS artifacts' "thought loops". With this, we aim to provide nuanced insight into GPT-based agentic IS artifacts and agentic relationship dynamics involving cognitive tasks.Item type: Item , Introduction to the Minitrack on AI-based Methods and Applications for Software Engineering(2024-01-03) Wittek, Stefan; Herold, Sebastian; Rausch, Andres