With increasing microbial resistance, quickly determining antibiotic resistance is important. For automating this task, detailled knowledge about a is is known primarily by the lab technician (domain expert). In this research an automatic optimization system which can be trained by an end-user is used. Collecting an accurate ground-truth is often challenging in trainable systems. Surprise-explain-reward is used as a design methodology for the ground-truth collection software.Optimized results using the ground-truth collected by end-users show excellent performance.
Klaas Dijkstra
Published at the Nationaal Informatica Onderwijs Congres, NIOC 2013