Dresden 2026 – scientific programme
Parts | Days | Selection | Search | Updates | Downloads | Help
MA: Fachverband Magnetismus
MA 7: Poster Magnetism I
MA 7.23: Poster
Monday, March 9, 2026, 09:30–12:30, P2
Machine Learning assisted 3D Tracking, Evaluation and Analysis of near-substrate transported Superparamagnetic Microparticles for Intelligent Experimentation and Sensing Applications — •Nikolai Weidt1,2, Nikita Popkov2,3, Yahya Shubbak1,2, Rico Huhnstock1,2, Kristina Dingel2,3, Bernhard Sick2,3, and Arno Ehresmann1,2 — 1Institute for Physics and CINSaT, University of Kassel, Heinrich-Plett-Str. 40, 34132 Kassel, Germany — 2AIM-ED, Joint Lab of Helmholtzzentrum für Materialien und Energie, Berlin (HZB) and University of Kassel, Hahn-Meitner-Platz 1, 14109, Berlin, Germany — 3Intelligent Embedded Systems, University of Kassel, Wilhelmshöher Allee 71-73, 34121, Kassel, Germany
We present a framework for intelligent control and analysis of superparamagnetic microparticles transported above magnetic domain-patterned samples. Particles are actuated by tailored magnetic stray field landscapes and external field pulse sequences, enabling remote-controlled, near-surface motion. Implementing the open-source TANGO Controls system, the setup supports modular hardware integration, synchronized operation and live data evaluation. Real-time 3D particle trajectory reconstruction can be achieved by combining deep-learning-based tracking with an automated focus-sweep calibration. This closed-loop approach paves the way for rapid evaluation of particle interaction events and supports adaptive experiments, advancing lab-on-a-chip biosensing and machine-learning-assisted diagnostics.
Keywords: machine learning; lab-on-a-chip; sensor; bead; particle