Want to keep learning?

This content is taken from the University of Twente's online course, Geohealth: Improving Public Health through Geographic Information. Join the course to learn more.

But how do you apply SOMs?

Even when you conceptually understand how a technique works, it does not necessarily mean that you can apply it. Your software package may not have a tool called “Self-Organizing Maps”. In case you want to try how it works you can follow the steps below.

In this research we applied the following stepwise approach stating with the data preparation:

  • Prepare data in Excel
  • Save as .csv

In case your dataset is very large, this may not work, but as explained earlier the dataset of this case study was rather small. In case your dataset is in a GIS, open the attribute table and copy all records to Excel or export this table directly to a .csv file.

The software that was used in this case study was R. This is because it is open source but other options are also available for example in Matlab. Within R the Kohonen package was used(see Downloads beneath this article). Again other packages are available and might work also. Earlier we already referred to the journal article describing this research. You can download the article (titled “Self-organizing maps as an approach to exploring spatiotemporal diffusion patterns”) underneath.

In the supplement materials of this article you will find the scripts of this study for you to re-use, this is entirely optional. A link to download the scripts is also included below.

After the preparation of your data, the next steps would be:

  • Install R
  • Install the Kohonen package
  • Open the scripts from the article
  • Make sure you link to your own data
  • Run the script and evaluate the outcome

Share this article:

This article is from the free online course:

Geohealth: Improving Public Health through Geographic Information

University of Twente

Get a taste of this course

Find out what this course is like by previewing some of the course steps before you join: