The project is in the context of automated (pre-)classification and searchability of large amounts of experimental data using artificial intelligence methods. The FTZ CyberSec at HAW is researching the recognition of persons and objects using intrinsic identity features. In the case of measured values, such unique identifiers can be, for example, the relevant research results or characteristics that are being searched for. However, due to the diversity of potential features, it is difficult to predict the exact scope and characteristics of the features. It therefore makes sense for systems to use AI methods to learn through feedback mechanisms when objects differ in order to learn other features in addition to those that have been consciously trained.
Project website: KI-Methoden am Beispiel von GISAXS-Streudaten (in German)
