PK
P.O. Klaassen
info
Please Note
<p>This page displays the records of the person named above and is not linked to a unique person identifier. This record may need to be merged to a profile.</p>
2 records found
1
The contemporary trend shows a shift from rule-based algorithms to deep learning. In the last few years, this field has been developing rapidly and its popularity has increased to a large extent. This happened for a good reason, since deep learning was able to solve some of the hardest problems in fields like image recognition, natural language processing and speech recognition. A large proportion of its success has to be credited to the explosion of big data in the past two decades. Structured data sets are essential to deep learning systems. The rising amount of automatic identification system data is a key example in the current big data boom. The automatic identification system produces spatiotemporal movement data of vessels. It was designed as a collision avoidance system, but researchers have been looking into ways to leverage its data for other tasks. Analyzing behavior in the movement data of vessels can help policymakers and monitoring operators with decision making processes. Improving these processes lead to safer and more resilient marine environments. Unfortunately, the possibility of applying deep learning on vessel movement data is an underexposed topic. This project attempts to explore the research gap in this topic. The objective is therefore to give an overview of the possibilities, complications and opportunities given the current state of the art. Ultimately, this project may serve as a rough guide for those who wish to explore the crossings where deep learning and vessel movement data meet.
...
The contemporary trend shows a shift from rule-based algorithms to deep learning. In the last few years, this field has been developing rapidly and its popularity has increased to a large extent. This happened for a good reason, since deep learning was able to solve some of the hardest problems in fields like image recognition, natural language processing and speech recognition. A large proportion of its success has to be credited to the explosion of big data in the past two decades. Structured data sets are essential to deep learning systems. The rising amount of automatic identification system data is a key example in the current big data boom. The automatic identification system produces spatiotemporal movement data of vessels. It was designed as a collision avoidance system, but researchers have been looking into ways to leverage its data for other tasks. Analyzing behavior in the movement data of vessels can help policymakers and monitoring operators with decision making processes. Improving these processes lead to safer and more resilient marine environments. Unfortunately, the possibility of applying deep learning on vessel movement data is an underexposed topic. This project attempts to explore the research gap in this topic. The objective is therefore to give an overview of the possibilities, complications and opportunities given the current state of the art. Ultimately, this project may serve as a rough guide for those who wish to explore the crossings where deep learning and vessel movement data meet.
Student report
(2018)
-
Freek Boersma, Shenglan Du, Pim Klaassen, Pablo Ruben, Martijn Meijers, Edward Verbree
Vario-scale is a new mapping technique which automatically generalizes maps from a baselayer of faces. Applications of vario-scale are continuous, smooth zoom in web maps,multi-scale representation in one map and being able to generate maps at arbitrary scale. Also,this would only require having to maintain the dataset at the highest scale level, since all otherscales are derived from it.Potentially, vario-scale could be an alternative for current web maps and generalizationalgorithms. The Dutch national mapping agency, Kadaster, currently employs its owngeneralization process. However, they would like to know whether the users of theirtopographic datasets are interested in vario-scale. At this moment, there is a workingimplementation of vario scale (made by dr. ir. Martijn Meijers). This implementation,however, is still lacking in, for example, cartographic quality. Therefore the research questionin this project is: how can the implementation of vario-scale be improved to better meet theneeds for end users of Kadaster topographic data?This question is answered by questioning surveying users of Kadaster data on what theywould like to see improved about the existing implementation. Combining this with anexploration of the current software leads to an attempt at improving the currentimplementation. The project goal is set as enabling the road network visualization and mobilemap adaptation. Road network visualization is achieved by building the roads space scalecube and overlay with the background area at the front-end. Mobile map adaptation is realizedby creating the touch screen interaction between the device and the user. Finally, a validationsurvey is conducted to examine the difference between the original vario scaleimplementation and the adapted one.
...
Vario-scale is a new mapping technique which automatically generalizes maps from a baselayer of faces. Applications of vario-scale are continuous, smooth zoom in web maps,multi-scale representation in one map and being able to generate maps at arbitrary scale. Also,this would only require having to maintain the dataset at the highest scale level, since all otherscales are derived from it.Potentially, vario-scale could be an alternative for current web maps and generalizationalgorithms. The Dutch national mapping agency, Kadaster, currently employs its owngeneralization process. However, they would like to know whether the users of theirtopographic datasets are interested in vario-scale. At this moment, there is a workingimplementation of vario scale (made by dr. ir. Martijn Meijers). This implementation,however, is still lacking in, for example, cartographic quality. Therefore the research questionin this project is: how can the implementation of vario-scale be improved to better meet theneeds for end users of Kadaster topographic data?This question is answered by questioning surveying users of Kadaster data on what theywould like to see improved about the existing implementation. Combining this with anexploration of the current software leads to an attempt at improving the currentimplementation. The project goal is set as enabling the road network visualization and mobilemap adaptation. Road network visualization is achieved by building the roads space scalecube and overlay with the background area at the front-end. Mobile map adaptation is realizedby creating the touch screen interaction between the device and the user. Finally, a validationsurvey is conducted to examine the difference between the original vario scaleimplementation and the adapted one.