INTRODUCTION
Increasing digitalization, rapid developments of machine learning and artificial intelligence as well as exponentially growing accumulation of data and automisation lead to new jobs in the areas of IT, data science and research.
Likewise in the field of (maritime) logistics, digitalization is becoming increasingly important, resulting in an ever-increasing demand for trained personnel in the field of machine learning. One facilitator of maritime digitaliz- ation was the introduction of the Automated Identifica- tion System, which opened up a number of possibilities using machine learning in the maritime sector.
BASIC CONDITIONS
Funded by: Federal Ministry of Education and Research
Project Management: German Aerospace Center (DLR)
Project duration: 2017 - 2019 OBJECTIVE
The Institutes of Maritime Logistics and Software Techno- logy Systems of Hamburg University of Technology and Fraunhofer CML intend to develop and set up a training course entitled „Machine Learning in Theory and Practice“.
The aim of the course is to provide master‘s students of Logistics with an additional permanent academic offer in the field of machine learning. The methodological and content-related focus is on handling both static and incrementally growing large amounts of data, their classi- fication and correlation as well as the handling of data uncertainties.
MALITUP
MACHINE LEARNING IN THEORY AND PRACTICE
M. Sc. Tina Scheidweiler, M. Sc. Marvin Kastner, Dipl.-Wirtsch.-Ing. Univ. Hans-Christoph Burmeister Group ‚Sea Traffic and Nautical Solutions‘
Basic-Level
Data modelling
Supervised learning Regression
Decision trees
Bayesian networks Neural networks
Support vector machines Unsupervised learning
Hierarchical clustering K-means
Validation
Big data in [maritime] logistics AIS
Environment
Definition of applied questions and requirements
Titanic: Machine Learning from Disaster
Image recognition Usability of machine learning procedures in logistics
Coordination with associated partners
Advanced-Level
Administration
Contact partners from industry/administration
Definition of topics for practical studies
Provision of data
Presentation of the results to the partners
Content
Processing of real problems on big data
Basis: AIS, weather and traffic data
Graduation: Scientific work at conference incl.
presentation
Professional-Level Prerequisites
University degree + one year of professional experience
or
Successful completion of Basic- and Advanced-Level
Content
Compressed teaching of Basic- and Advanced-Level Adaption of Data Scientist
Specialized in Data Analy- tics course by Fraunhofer
Big Data alliance
Practical application of
machine learning methods to various topics of [maritime] logistics
Administration
Duration: 4 days + exam Certification by Fraunhofer
Certificate ISO 17024
STRUCTURE
Practice Project
Advanced Course: Data Scientist Specialized in Logistics Exercise
Basics of Machine Learning Digitalization in
Transport and Logistics
I N C O L L A B O R AT I O N B E T W E E N :
WWW.CML.FRAUNHOFER.DE
F R A U N H O F E R C E N T E R F O R M A R I T I M E L O G I S T I C S A N D S E R V I C E S C M L