MaLiTuP - Machine Learning in Theory und Practice

The project aims at developping and permanently establishing a qualification program called "Machine Learning in Theory und Practice" in order to teach the fundamentals of the field of machine learning to Master's students in logistics at TUHH.

Period
01.11.2017 - 30.04.2020
Project Funding
Funded by the Federal Ministry of Education and Research (BMBF)
Our Status
Partner
Contact Person
Marvin Kastner
PartnersMembers
  • TUHH, Institut for Software Systems
    Prof. Dr. Sibylle Schupp
  • Fraunhofer-Center for Maritime Logistics and Services
    Prof. Dr.-Ing. Carlos Jahn
  • TUHH, Institut of Maritime Logistics
    Prof. Dr.-Ing. Carlos Jahn
Partners
  • TRENZ AG
    The internationally active software company has been developing individual solutions since 1999. In the maritime sector, the company provides real-time information services for the maritime industry.
  • JAKOTA Cruise Systems GmbH / FleetMon
    The company has been working in the field of real-time vessel tracking since 2010 and uses 300 million position reports and weather data for analyses every day as a data basis.
  • Deutscher Wetterdienst
    The maritime weather centre of the German Meteorological Service performs tasks to increase the safety of maritime shipping. Meteorological predictions are made with the help of numerical prediction systems.

Description

Especially in the field of logistics, digitization is becoming more and more important, resulting in an ever increasing need for trained personnel in the field of machine learning. In addition to a class, practical projects are to be offered within the qualification program, which enable the students to apply the acquired knowledge in concrete and realistic case studies from the maritime world.

The methodological and content-related focus is on dealing with large amounts of data, their classification and correlation as well as the handling of data uncertainties. Furthermore, a further offer is aimed at university graduates with professional experience in the field of data analysis. In addition, the "MaLiTuP" research project is intended to enable the project partners to expand their own competencies in the field of big data analyses and forecasts.



Publications (excerpt)

  • Kastner, Marvin and Franzkeit, Janna and Lainé, Anna (2020). Teaching Machine Learning and Data Literacy to Students of Logistics using Jupyter Notebooks [DELFI Poster Award Winner]. DELFI 2020. 365-366. [Abstract] [pdf] [www] [BibTex]

  • Kastner, Marvin and Scheidweiler, Tina (2019). MaLiTuP: Machine Learning in Theory and Practice: Poster. All-Hands-Meeting Machine Learning 2019. [Abstract] [pdf] [www] [BibTex]

  • Kastner, Marvin (2019). Prüfungen mit JupyterHub. Blogbeitrag in INSIGHTS - Einblicke in Lehre und Forschung im digitalen Experimentierfeld der TUHH. [www] [BibTex]

  • Kastner, Marvin and Podleschny, Nicole (2019). Mit Jupyter Notebooks prüfen. Beitrag zur Poster-Session des e-Prüfungs-Symposiums (ePS) in Siegen. [Abstract] [pdf] [doi] [www] [BibTex]

  • Kastner, Marvin and Scheidweiler, Tina and Burmeister, Hans-Christoph (2018). MaLiTuP: Machine Learning in Theory and Practice: Poster. Leibniz-Symposium “Maschinelles Lernen – Intelligente Digitalisierung”. [Abstract] [pdf] [www] [BibTex]