Abstract:

Becoming aware of the variety of ways that teachers and students experience and apply research in higher education sets all key holders to become more reflective of the environment in which learning is taking place.

With the increasing need to implement teaching-student-research nexus, self-responsibility and self-motivation is moving to the forefront of higher education. The paper is based on the findings of a research project that is implemented into bachelor final works at the Antwerp Maritime Academy. We examine how research knowledge can generate innovative outcomes that meaningfully benefit a wider set of key-holders. The project is based on cooperation between teaching staff and third year undergraduate and master student. The project involves the following field ‘Big Data analytics in Nautical Sciences’ with implementation of its work towards Estimated Time of Arrival of vessels at the Port of Antwerp.

Big Data refers to datasets whose size is beyond the ability of typical database software tools to capture, store, manage and analyze. The size of Big Data not only differs by sector, but also grows over time, since technology advances allow to process more data than before. Therefore Big Data encompasses a few dozen terabytes to multiple petabytes.

Big Data analytics uses predictive and prescriptive analytics and is changing the analytics landscape. The use of Big Data analytics is currently exploding with the ever becoming cheaper and more accessible technology. However in Nautical Sciences there are still some opportunities left, waiting to take part of the optimization process which is currently the new way of improving revenue and operational efficiency.

Some research examples in this work include together with his outcomes for the key-holders:
1. Routing taking in account operational risk, fuel prices,…
2. Monitoring a student’s progress while on the simulator
3. Monitoring crew’s performance taking into account weather conditions,…

The goal is to discover a certain systematics in ship delays in the Port of Antwerp. This value was established by subtracting the Actual Time of Arrival (ATA) from the Estimated Time of Arrival (ETA) in the Automatic Identification System (AIS) when passing Flushing. First of all we determined the distribution of ETA deviations to be loglogistic. Most delays are concentrated around a certain ship type-specific value. Finally 5 nonlinear formulas were established, each representing the delays for each of the 5 most important ship types in Antwerp in function of 40 parameters. These equations were implemented in a small software program, which permits to fill in 40 variables, after which the software returns the expected delay.

Keywords:

Teaching-students-education-research nexus, big data analytics, Research Development and Innovation projects, Estimated Time Arrival (ETA), Actual Time (ATA)