Form diffusion physics to machine learning
This internship explores methods for extracting meaningful information from complex physical data. The student will investigate state-based representations of temporal signals to identify patterns, operating regimes, and behavioral changes. The work includes data analysis, visualization, statistical modeling, and evaluation on real-world datasets. Applications may include anomaly detection, condition monitoring, and predictive analytics in system reliability. The project offers hands-on experience in Python, machine learning, and dynamical data analysis.
Type of internship : Master internship
Duration : 3 months (90 days)
Required educational background : Electrotechnics/Electrical Engineering, Physics, Materials Engineering, Mechanical Engineering
University promotor : Houman Zahedmanesh (KU Leuven)
Imec allowance will be provided for students studying at a non-Belgian university.
Incomplete applications will not be considered.
#J-18808-LjbffrThis listing is sourced from a third-party job board. Applying will redirect you to the original posting.
Woopel
Jing Hau
Jing Hau