GloBiMap implementation published
The (sample) implementation of the GloBiMap data structure has just been uploaded to GitHub at https://github.com/mwernerds/globimap.
GloBiMaps - A randomized data structure capable of storing high-resolution low-cardinality raster like built-up areas in few megabytes
We are happy to announce that our latest research on a randomized data structure GloBiMap (Werner, 2019) for high-resolution, low-cardinality global raster information (e.g., which place on Earth contains a building) has been selected for full-paper presentation at ACM SIGSPATIAL GIS. We are excited about the positive reviews.
CODE Jahrestagung 2019 and Price for GeoDialog
Last week, I was joining the CODE Jahrestagung 2019. On the first day, I was organizing the Workshop on Geoinformation Systems which we turned into a cross-disciplinary overview of the field. With topics as wide as GIS, trajectory analysis, information networks, change point detection in large (high-dimensional) spatio-temporal processes, remote sensing and deep learning, we showed the fact that working with geo data is a perfect instance of data science. There are challenges with respect to volume, variety, veracity, data is usually observed, incomplete and inaccurate, and the user interface is very limited compared to the richness of the data. Soon, the workshop will publish a summary report and some of the slides on the workshop page
Using the TRACLUS trajectory clustering algorithm from within R
A short tutorial on how to use the TRACLUS algorithm from within the R programming language.
Implementing the TRACLUS trajectory clustering algorithm
This article explains a C++ implementation of the TRACLUS trajectory clustering algorithm step by step.
CfP: GeoInformatica - Special Issue on Spatial Computing for Urbanization Research
CfP: GeoInformatica Special Issue on Spatial Computing for Urbanization Research
A short Introduction to Python
Python course from my BMBF-funded project ICAML.
Programming Languages for Big Data
A short video explaining the pro's and con's of various popular programming langues for big data.
New Web Page
Changing to Jekyll - what a nice CMS...
Apache Spark on Amazon with Docker - A Video Tutorial
In this article, we go through deploying a full Apache Spark application on the Amazon Cloud relying on Docker for organizing our Cloud instances. There is a video tutorial and all source code available.
Opponent for Doctoral Dissertation of Jussi Parviainen
The Tampere University of Technology invited me as an opponent for Jussi Parviainens dissertation.
Difference Between Trajectory Computing and Time Series Analytics
Trajectory Computing and Time Series Analytics are partially overlapping research areas. In this blog post, I explain, why they are not the same while algorithms from each of those domains can be applied in the other domain.
On Data Science Tools
A short article introducing the pro's and con's of my personal choice of data science tools.