Rob Loke

Rob Loke
Amsterdam University of Applied Sciences/Centre for Applied Research on Education · Centre for Applied Research on Economics and Management

Assistant professor data science

Publications

Publications (32)
Technical Report
Full-text available
Het PBL-normenkader voor modellen maakt inzichtelijk of noodzakelijke procedures rond de ontwikkeling, het beheer en het gebruik van modellen correct doorlopen worden en is dus een praktisch regelgevend instrument voor kwaliteitszorg rond modellen. Aan de hand van de in het normenkader vastgestelde normen beoordeelt het PBL modellen op een uniforme...
Article
Full-text available
Het PBL en het CBS hebben in 2011 voor de vierde keer de Regionale bevolkings- en huishoudensprognose met het model PEARL uitgebracht. In deze prognose spelen veronderstellingen over de gemeentelijke sterfte een belangrijke rol. In dit kader is een analyse uitgevoerd naar de verklaring van gemeentelijke verschillen in de levensverwachting aan de ha...
Article
Full-text available
Discretized Marching Cubes (DMC) is a standard method in computer graphics and visualization for constructing 3D surfaces in data represented on a regular grid. After thresholding, it builds high-resolution surfaces by tiling surface patches halfway between objects and background in the data. This paper shows that if surfaces are built locally, in...
Thesis
This thesis describes a visualization pipeline for sonar profiling data that show reflections of multiple sediments in the sea bottom and that cover huge survey areas with many gaps. Visualizing such data is not trivial, because they may be noisy and because data sets may be very large. The developed techniques are: (1) Quadtree interpolation for e...
Article
Morphometric shape analysis and ultrastructural data are provided for six genodemes of the Sellaphora pupula species complex that have been studied during the last 20 years from Blackford Pond, Edinburgh, UK. The demes have previously been shown to be separated by prezygotic reproductive barriers: cells of different demes do not pair, though they m...
Article
We apply new contour features: (1) Point features by computing the convexity and curvature in small contour neighborhoods. (2) Segment features by segmenting the contour into convex, concave and straight segments, and computing length and curvature measures for each segment. (3) Global features by computing the mean, maximum and minimum of all poin...
Article
Bottom-penetrating sonar can be used to visualize large areas, for example by normal logging and printing of collected pings. In many applications, it is necessary to obtain an impression of three-dimensional (3-D) structures, but this is not easy because of the irregular spatial sampling due to coarse ship trajectories. Normally, the ping map and...
Conference Paper
Sonar profiling of the seabottom provide 3D data sets that can cover huge survey areas with many gaps. We describe a multiresolution framework or visualization pipeline that is being optimized for dealing with such data, taking into account both the CPU time and the user interactivity. We describe the techniques employed: (a) the construction of a...
Article
Full-text available
The general objective of EXOCET/D is to develop, implement and test specific instruments aimed at exploring, describing, quantifying and monitoring biodiversity in deep-sea fragmented habitats as well as at identifying links between community structure and environmental dynamics. Onboard experimental devices will complement the approach, enabling e...
Conference Paper
We present a multiresolution framework for the visualiza- tion of structures in very large volumes. Emphasis is given to an in the framework embedded, new algorithm for triangulating 18-connected ob- ject boundaries which preserves 6-connectivity details. Such boundaries cannot be triangulated by standard 6-connectivity algorithms such as Marching...
Conference Paper
We apply a fast segmenter to planar range images. By segmenting normal vectors of estimated planes in a quadtree, we can analyze very noisy data at high tree levels and guarantee interactivity in visualizing underlying 3D scenes. Techniques to enhance data at the original spatial resolution are given. Results on the ABW range dataset are better tha...
Conference Paper
Full-text available
We describe a new contour feature set. A contour is segmented into convex, concave and straight segments, after which length and curvature features are computed. A symmetry analysis allows the detection of the number of elementary segments. Results on two contour test sets were obtained: Using only four features, a simple nearest-mean classifier yi...
Conference Paper
Sonar profiler data of the seabottom are 3D data sets that can cover huge survey areas with many gaps. This paper describes a multiresolution visualization framework that is being optimized for dealing with such data taking into account both the CPU time and the user interactivity. The paper describes the techniques employed: (a) the construction o...
Article
A range image segmentation contest was organized in conjunction with ICPR'2000. The goal is to continue the effort of experimentally evaluating range image segmentation algorithms initiated in [3, 4]. This paper summarizes the results of the contest.
Article
Full-text available
: In this paper we describe a fast method for the segmentation of very large data volumes. The method is highly robust to both noise and gaps in the data by performing the data processing in a multiresolution pyramid, or octree. First the tree is built by spatially smoothing the available data. This reduces the noise and the number of gaps facilita...
Article
Full-text available
This paper describes an interactive method for the visualisation of 3D tomographic data with an emphasis on segmentation and surface construction. In the method multiresolution data representations are employed which have the advantage that results at low spatial resolutions are quickly obtained. This facilitates a fast user interaction, even for h...
Conference Paper
Full-text available
A range image segmentation contest was organized in conjunction with ICPR'2000. The goal is to continue the effort of experimentally evaluating range image segmentation algorithms initiated by Hoover et al. (1996) and Powell et al. (1998). This paper summarizes the results of the contest
Conference Paper
The authors describe a new method for the detection and visualization of objects in 3D sonar data. The method has been applied to data obtained at a site which contains a well-defined target, being a buried tractor tire, sized 130 cm in diameter and 30 cm high. The surfaces of the corresponding sonar object have been accurately extracted using fast...
Article
Full-text available
The algorithm developed uses an octree pyramid in which noise is reduced at the expense of the spatial resolution. At a certain level an unsupervised clustering without spatial connectivity constraints is applied. After the classification, isolated voxels and insignificant regions are removed by assigning them to their neighbours. The spatial resol...
Conference Paper
The authors describe an unsupervised processing pipeline for the analysis and visualization of sonar data. Recently developed 3D interpolation and segmentation methods are introduced, as well as a completely new surface construction method. All methods are based on employing quad- and octrees, which results in a fast processing. Accurate results ar...
Conference Paper
Full-text available
The analysis of seabed structure is important in a wide variety of scientific and industrial applications. In this paper, underwater acoustic data produced by bottom-penetrating sonar (Topas) are analyzed using unsupervised volumetric segmentation, based on a three dimensional Gibbs-Markov model. The result is a concise and accurate description of...
Conference Paper
This paper describes the application of unsupervised volumetric reconstruction, segmentation and visualization techniques to underwater acoustic data for a 3D seabed analysis. New 3D interpolation and segmentation, methods are introduced and applied to both artificial and real seabed data. In the interpolation, all calculations are done in 3D. For...
Chapter
This paper describes the application of two different adaptive control schemes based on neural networks to the control of a bioreactor. The results are a useful assessment of the adequacy of neural networks for identification and control of nonlinear systems.
Article
This paper describes the application of two different adaptive control schemes based on neural networks to the control of a bioreactor. The results are a useful assessment of the adequacy of neural networks for identification and control of nonlinear systems.

About

32
Publications
2,598
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
475
Citations

Network

Cited By