Learning and classification with prime implicants applied to medical data diagnosis
Zekie Shevked, Ludmil Dakovski · 2007
This paper investigates in applying an algorithm for learning from examples to medical data diagnosis. The goal is to find a more compact representation of the target classification function and use it for classification of unknown cases. The algorithm represents sets of positive and negative training instances as logical functions and applies an innovatory strategy for logical function minimization in order to find the target function's prime implicants. They actually represent the model of the data which can be used successfully for classification of unseen cases and for diagnosis in the field of medicine.