The interdisciplinary research group "Machine Learning for Time Series and Images" (ML4TIME) mainly deals with the analysis of images and data from biology/biochemistry/medicine/material sciences (e.g., high-resolution 3D+t light sheet microscopy images, quantitative analysis of motions), and from energy systems (e.g., forecasting, anomaly detection).
Various methods from digital image processing, time series analysis, statistics, data mining and machine learning are developed or adapted to different problems enabling automated data evaluation. For many problems, it is important to generate measures and decisions based on large, partially redundant and strongly disturbed amounts of data. In the case of purely manual data evaluation, it is often difficult for users to deal with the multitude of features and their complex interrelationships. When evaluating the data, the focus lies therefore not only on automated classification, but also on a comprehensible and interpretable solution. This increases the reliability of the decisions made and their acceptance by users.
apl. Prof. Dr. Ralf Mikut
Jorge Ángel González Ordiano
Nicole Ludwig (IPD)
Marian Turowski (TM)
- Automated Image and Data Analysis
- 3D+t Terabyte Image Analysis
- Imaging of the corneal sub-basal nerve plexus
- Energie System 2050
- EnergyLab 2.0
- Robot and Computer Assisted Microscopy
- Demand Side Management
- Gait Analysis
- Humanoid Robots
- Establishment of a New Method to Interactively Segment and Visualize Complex 3D Image Data