News
Papers accepted at LOD 2025
We are happy to announce that our paper Empirical Evidence for Data-Centric AI: A Comparative Study of Data Complexity and Hyperparameter Effects (by Emmanuel Charleson Dapaah and Jens Grabowski) have been accepted at the The 11th International Conference on Machine Learning, Optimization, and Data Science (LOD 2025). This paper presents a comprehensive empirical study comparing the relative influence of dataset complexity and hyperparameter settings on the performance of five widely-used classification algorithms: Random Forest, Support Vector Machine, Decision Tree, Adaptive Boosting, and Multi-Layer Perceptron. The findings reveal that data-centric factors—especially class overlap (N1)—consistently exert a far stronger impact on both bias and variance than hyperparameter settings.
New TTF for TDL Maintenance
Poster accepted at HCII 2025
- Evaluation of Data Sharing in Interaction-Based Emotion Recognition Research by Carina Bieber, Patrick Harms, and Jens Grabowski
Journal First Presentation at ICST 2025
Posters and Presentations accepted for the UCAAT 2025
- Importance of Data Sharing for the Validation of Interaction-based Emotion Recognition for User Experience Evaluation
- Representativeness of Deep Learning Mutants in Simulating Real Faults
- Exploring the Landscape of Machine Learning Data Bugs: Frequency, Impacts, and Relationships for Enhanced Automation
- Generating Test Artifacts using Large Language Models
- Documentation Approaches for AI/ML Systems
- ETSI TR103910: Test Methodology and Test Specification for AI-enabled Systems
- TDL Takes on the Edge
- Towards a Harmonized Documentation Scheme for Trustworthy AI
Workshop accepted at MUC 2024
We are pleased to announce that a workshop from our research group has been accepted at the Mensch und Computer 2024 conference. This year’s conference will take place from September 1st to 4th at the Karlsruhe Institute of Technology in Karlsruhe, Germany.
The accepted workshop is:
- Improving UX Evaluation with AI-based Emotion Recognition by Carina Bieber, Patrick Harms, and Carolin Ebermann
Papers accepted at SAM 2024
We are pleased to announce that two papers from our research group have been accepted at the 16th System Analysis and Modeling Conference (SAM 2024). This year’s conference will take place on September 23rd and 24th, co-located with the ACM/IEEE 27th International Conference on Model Driven Engineering Languages and Systems (MODELS 2024) in Linz, Austria.
Our accepted papers are:
- Exploring the Fundamentals of Mutations in Deep Neural Networks by Zaheed Ahmed and Philip Makedonski
- AI-based User Emotion Recognition from Interaction Data: Challenges and Guidelines for Training Data Creation by Carina Bieber, Patrick Harms, Dominick Leppich, and Katrin Proschek