RT Journal Article ID 5ab286e52620bedf A1 Dovbysh, Anatoliy S. A1 Stadnyk , Anna A. A1 Holubnychyi , Stanislav A. T1 Hierarchical Information-Extreme Learning Algorithm for a Diagnostic System with Redundant Training Matrix JF Journal of Automation and Information Sciences JO JAI(S) YR 2015 FD 2015-05-22 VO 47 IS 4 SP 54 OP 63 K1 diagnostic system K1 redundant training matrix K1 hierarchical information-extreme learning algorithm K1 machine learning AB The problem of information synthesis of decision support system for pathological process diagnosing is considered within the frames of information-extreme intellectual technology based on maximization of information capacity of the system in the process of its learning. The influence of the training matrix forming method on functional efficiency of machine learning is investigated. Implementation of the algorithm was performed with the example of diagnosis of the spontaneous pneumothorax forms differed by etiology and disease course. PB Begell House LK https://www.dl.begellhouse.com/journals/2b6239406278e43e,73dfa9ae3a8278b9,5ab286e52620bedf.html