Project: Visual interactive grouping: follow the leader!
Description
Clustering is a technique for grouping similar data. It is not evident what similar data is; this depends on a domain or even on a specific situation. Therefore, a user might be engaged in the clustering process, so he1 can transfer his domain knowledge. To do so, clustering tools usually allow users to set input parameters beforehand, to control, for instance, a similarity measure for the data.
If users are allowed to interact with the data and with the grouping, in particular in a visual way, the user is provided with better means to add his knowledge. Moreover, from the step-by-step user interaction, the intended grouping can even be assessed automatically, and,also takes away the requirement to thoroughly understand the underlying algorithms.
We allow for interactive grouping of multi-relational data. For instance, all grades from a student can represent that student; or all treatments of a patient together represent that patient.
Details
- Student
-
TLThomas Lammers
- Supervisor
-
Huub van de Wetering
- Link
- Thesis