Student Projects

Browse all posts in the Student Projects category.

1 total

31MAR 2026
Master Thesis
Explainable Failure Analysis in Time-Series Data Using SHAP
Explainability is critical for the adoption of machine learning models in industrial systems, particularly for failure detection and prediction. This thesis explores the application of SHapley Additive exPlanations (SHAP) to time-series data containing failure events, focusing on attributing model decisions to both relevant features and critical time steps to improve transparency and trust. Requirements Please […]Explainability is critical for the adoption of machine learning models in industrial systems, particularly for failure detection and prediction. This thesis explores the application of SHapley Additive exPlanations (SHAP) to time-series data containing failure events, focusing on attributing model decisions to both relevant features and critical time steps to improve transparency and trust. Requirements Please […]
Read more about Explainable Failure Analysis in Time-Series Data Using SHAP
19NOV 2025
Ongoing Project
Joint Reconstruction from Upper-Limb Motion-Capture Markers Data
Upper-limb motion is mechanically complex, yet the nervous system performs these movements with effortless coordination. To understand this behavior and enable human-like control in robotics or neurorehabilitation, upper-limb movement datasets are essential. One of the interesting dataset available with extensive modalities is the U-Limb dataset. It consists of a database collected across six European universities, […]Upper-limb motion is mechanically complex, yet the nervous system performs these movements with effortless coordination. To understand this behavior and enable human-like control in robotics or neurorehabilitation, upper-limb movement datasets are essential. One of the interesting dataset available with extensive modalities is the U-Limb dataset. It consists of a database collected across six European universities, […]
Read more about Joint Reconstruction from Upper-Limb Motion-Capture Markers Data
17JUL 2025
Forschungspraktikum
Unified Microcontroller Inference Platform (UMIP)
Problem: Aktuelle Microcontroller-Evaluierungs- und Entwicklerboards eignen sich nur bedingt, um verschiedenste KI-Methoden – zum Beispiel tiefe neuronale Netze – plattform- und herstellerübergreifend zu testen. EdgeVolution, eine Plattform zur Suche neuer neuronaler Architekturen für Edge-KI auf Basis evolutionärer Algorithmen, nutzt daher eine Auswahl an Entwicklerboards inklusive zugehöriger Power Profiler Kits (etwa Nordic nRFxxx mit PPK2). Allerdings […]Problem: Aktuelle Microcontroller-Evaluierungs- und Entwicklerboards eignen sich nur bedingt, um verschiedenste KI-Methoden – zum Beispiel tiefe neuronale Netze – plattform- und herstellerübergreifend zu testen. EdgeVolution, eine Plattform zur Suche neuer neuronaler Architekturen für Edge-KI auf Basis evolutionärer Algorithmen, nutzt daher eine Auswahl an Entwicklerboards inklusive zugehöriger Power Profiler Kits (etwa Nordic nRFxxx mit PPK2). Allerdings […]
Read more about Unified Microcontroller Inference Platform (UMIP)
26MAY 2025
Bachelor Thesis
Evaluating Optimization Algorithms for Human Gait Simulations
Are you interested in helping us improve our human gait simulations? We use these simulations to predict the effect of interventions like prostheses and exoskeletons, and to perform detailed biomechanical movement analysis from wearable sensor data. We are looking for a student to investigate the optimization algorithm that we use to generate the simulation. It […]
Read more about Evaluating Optimization Algorithms for Human Gait Simulations
25APR 2025
Master Thesis
Benchmarking Energy Expenditure Estimation: AI vs. Metabolic Cost Models
In clinical and sports science applications, the accurate estimation of energy expenditure (EE) is critical for evaluating physical performance, rehabilitation progress, and overall health. Traditionally, EE has been estimated through metabolic cost models based on joint kinematics and musculoskeletal dynamics. However, recent advances in AI particularly in machine learning and deep learning have opened new […]In clinical and sports science applications, the accurate estimation of energy expenditure (EE) is critical for evaluating physical performance, rehabilitation progress, and overall health. Traditionally, EE has been estimated through metabolic cost models based on joint kinematics and musculoskeletal dynamics. However, recent advances in AI particularly in machine learning and deep learning have opened new […]
Read more about Benchmarking Energy Expenditure Estimation: AI vs. Metabolic Cost Models