On the quality of ship arrival predictions and more / Towards grading automation of open questions using machine learning: Design and implementation of a web-based tool”

Title: On the quality of ship arrival predictions and more - given by Rogier Harmelink

• Abstract: The arrival of a ship is a complex process. It has been reported that ships in port can spend 5–10% of their time in unnecessary anchorage. Predicting the accurate time of ship arrivals could support port actors to optimally allocate their resources and reduce this time, to the benefit of port competitiveness. Currently, the rise of real-time automated ship identification data has given ports, shipping lines and other actors the possibility to predict but also to follow the consecutive steps a ship undertakes while entering a port. Much work has been done on the development of advanced estimated time of arrival (ETA) predictors, but little is known about the quality of ETA information that shipping lines provide to ports.
  
  In this talk, we explore these ETAs, their predictive value and potential evaluation measures. Next to that, we show the first results into a process analysis in the Port of Antwerp.

• Bio: Rogier is working since 2019 as a researcher within IEBIS on the MARCONI (Maritime Remote Control Tower for Service Logistics Innovation) project on control tower architectures. His background is in Industrial Engineering & Management (specialization: finance). Next to the MARCONI project, Rogier has a particular interest in Game Theory, Data Science and Esports (Sim Racing). Rogier is also the co-founder of Hive01, a non-profit entrepreneurship program and co-founder of Awaves, a start-up that uses Artificial Intelligence technology to build an autonomous DJ.

Title: Towards grading automation of open questions using machine learning: Design and implementation of a web-based tool” - talk given by Adina Aldea

• Abstract: Assessing the academic capabilities of students plays a key role in both stimulating their learning process (formative assessment - FA) and in the accurate evaluation of their knowledge and capabilities in relation to a topic (summative assessment - SA). However, this is a challenging task, due to the substantial amount of time teachers need to spend on assessing open questions. Moreover, due to a steady yearly increase in the number of students enrolling in our study programmes, assessing open questions is becoming more and more time-consuming and less scalable. A direct consequence of this is the proliferation of Multiple-Choice questions in the tests of some of our bachelor programmes. This form of assessment has received criticism, from students, teachers and scholars alike, due to it being considered inappropriate for assessing critical thinking and problem-solving skills, and also being very difficult to use reliably for online testing.
  
  
• Bio; Adina Aldea completed her Ph.D., in three years, at the University of Twente, on the topic of strategic alignment, enterprise architecture (EA), strategic management, capability-based planning (CBP). During her PhD, Adina also worked as a Research Consultant at BiZZdesign where she implemented parts of her PhD research. Besides the topics of her PhD, Adina’s other interests include model-based engineering and analysis, resilience, education, industry 4.0, business intelligence, machine learning, user experience, serious gaming, etc. Besides publishing several papers in conferences and journals, Adina is also a contributor to the development of standards (ArchiMate 3.1), guides (TOGAF CBP guide, BIZBOK guide - Metamodels), and several whitepapers.