On Self-Organizing Map Approaches for Data Detection of Hematopoietic Tumors

Data detection using self organizing maps is presented for hematopoietic tumor patients. The learning data for the maps is generated from the screening data. Redundant items, which have an unfavorable influence on data detection and are common to all the data, are eliminated by a genetic algorithm and an immune algorithm. It is basically judged, by observing a label of a winner neuron in a map, whether the data presented to the map belongs to the class of hematopoietic tumors. Quantitative evaluations show that the proposed methods achieve the high probability of correctly identifying examinees as hematopoietic tumor patients