Kurzbeschreibung

Tatjana Legler studierte Maschinenbau an der Technischen Universität Kaiserslautern. In ihrer Masterarbeit beschäftigte sie sich mit der „Optimierung der Bildverarbeitung von Hochdruckspeichern unter Einsatz von neuronalen Netzen”. Seit November 2017 ist sie als wissenschaftlicher Mitarbeiterin am Lehrstuhl für Werkzeugmaschinen und Steuerungen tätig.

Forschungsgebiete

Tatjana Legler beschäftigt sich mit dem Einsatz künstlicher Intelligenz im Produktionsumfeld. Dies umfasst bspw. die Auswertung von Prozessdaten zur Vorhersage von Produktqualität und Federated Learning.

Veröffentlichungen

Link zu ORCID und Google Scholar

T. Legler, V. Hegiste, A. Anwar and M. Ruskowski, Addressing Heterogeneity in Federated Learning: Challenges and Solutions for a Shared Production Environment, 2025. Procedia Computer Science, 253, pp. 2831–2840. Link

T. Legler, V. Hegiste and M. Ruskowski, Benchmarking Federated Learning Under Realistic Non-IID Conditions. A Structured Partitioning Approach Using ImageNet, 2025.

A. Anwar, B. Moser, D. Herurkar, F. Raue, V. Hegiste, T. Legler and A. Dengel, FedAD-Bench: A Unified Benchmark for Federated Unsupervised Anomaly Detection in Tabular Data, 2024. 2nd International Conference on Federated Learning Technologies and Applications (FLTA), Valencia, Spain, pp. 115–122. IEEE.

V. Hegiste, T. Legler and M. Ruskowski, Towards Robust Federated Image Classification: An Empirical Study of Weight Selection Strategies in Manufacturing, 2024. 2nd International Conference on Federated Learning Technologies and Applications (FLTA), Valencia, Spain, pp. 55–62. IEEE.

V. Hegiste, S. Walunj, J. Antony, T. Legler and M. Ruskowski, Enhancing Object Detection with Hybrid Dataset in Manufacturing Environments: Comparing Federated Learning to Conventional Techniques, 2024. 1st International Conference on Innovative Engineering Sciences and Technological Research (ICIESTR), Muscat, Oman, pp. 1–6. IEEE.

T. Legler, V. Hegiste and M. Ruskowski, Seamless Integration: Sampling Strategies in Federated Learning Systems, 2024. 2nd International Conference on Federated Learning Technologies and Applications (FLTA), Valencia, Spain, pp. 148–155. IEEE.

V. Hegiste, T. Legler, K. Fridman and M. Ruskowski, Federated Object Detection for Quality Inspection in Shared Production, 2023. Eighth International Conference on Fog and Mobile Edge Computing (FMEC), Tartu, Estonia, pp. 151–158. IEEE.

V. Hegiste, T. Legler and M. Ruskowski, Federated Ensemble YOLOv5 – A Better Generalized Object Detection Algorithm, 2023. Eighth International Conference on Fog and Mobile Edge Computing (FMEC), Tartu, Estonia, pp. 7–14. IEEE.

T. Legler, V. Hegiste and M. Ruskowski, Mapping of Newcomer Clients in Federated Learning Based on Activation Strength, 2023. 32nd International Conference on Flexible Automation and Intelligent Manufacturing.

V. Hegiste, T. Legler and M. Ruskowski, Application of Federated Machine Learning in Manufacturing, 2022. International Conference on Industry 4.0 Technology (I4Tech), Pune, India, pp. 1–8. IEEE. Link

M. Volkmann, T. Legler, A. Wagner and M. Ruskowski, A CAD Feature-Based Manufacturing Approach with OPC UA Skills, 2020. Procedia Manufacturing, 51, pp. 416–423. Link