Topics for Master Theses at the Chair for Artificial Intelligence

Smart City / Smart Mobility

• Traffic Forecasting with Graph Attention Networks
• Learning Traffic Simulation Parameters with Reinforcement Learning
• Extending the Mannheim Mobility Model with Individual Bike Traffic

AI for Business Process Management

• Probabilistic Online Conformance Checking with  Declarative Process Monitoring and Deep Neural Networks
• Continual Learning for Predictive Process Monitoring with Event Streams
• Explainable predictive process monitoring with Graph Neural Networks
• New Learning Strategies for Predictive Process Monitoring: Addressing Imbalanced and Redundant Data Challenges
• Predictive Process Monitoring with Mixed Effects Neural Networks
• New Evaluation Approaches for Predictive Process Monitoring: Tackling Data Leakage and Concept Drift

Explainable and Fair Machine Learning

• Extracting Causal Models from Module Handbooks for Explainable Student Success Prediction
• Detecting Differences in Course Difficulty for Different Demographic Groups
• Investigating Different Techniques to Improve Fairness for Tabular Data
• Data-induced Bias in Social Simulations
• Learing Causal Models from Tabular Data

Human Activity and Goal Recognition

• Reinforcement Learning for Goal Recognition
• Investigating the Difficulty of Goal Recognition Problems
• Enhancing Audio-Based Activity Recognition through Autoencoder Encoded Representations
• Activity Recognition from Audio Data in a Kitchen Scenario
• Speaker Diarization and Identification in a Meeting Scenario

Machine Learning for Supply Chain Optimization

• Time Series Analysis & Forecasting of Events (Sales, Demand, etc.)
• Integrated vs. separated optimization: theory and practice
• Leveraging deep learning to build a versatile end-to-end inventory management model
• Reinforcement learning for the vehicle routing problem
• Metaheuristics in SCM: Overview and benchmark study
• Finetuning parametrized inventory management system

Anomaly Detection on Server Logs

• Analyse real-life server logs stored in an existing opensearch library (Graylog)
• Learning values describing normal behavior of servers and detect anomalies in logged messages
• Implement simple alert system (existing systems like Icinga can be used)
• Prepare results in a (Web-)Gui

Other

• Creating eLearning Recommender Systems using NLP
• Hyperparameter Optimization for Symbolic Knowledge Graph Completion
• Applying Symbolic Knowledge Graph Completion to Inductive Link Prediction
• Data Augmentation via Generative Adversarial Networks (GANs)
• Autoencoders for Sparse, Irregularly Spaced Time Series Sequences