Thanakotn NaennaMark J. EmbrechtsBolek SzymanskiKarsten SternickelMahidol UniversityRensselaer Polytechnic InstituteCardioMag Imaging, Inc.2018-07-242018-07-242004-12-01IEEE Region 10 Annual International Conference, Proceedings/TENCON. Vol.B, (2004)2-s2.0-27944508328https://repository.li.mahidol.ac.th/handle/20.500.14594/21291The main goal of this paper is to apply the Self-Organizing Maps (SOM), a novel learning and visualization technique, for abnormal and normal magnetocardiography (MCG) classification. MCG is the measurement of magnetic fields emitted by the electrophysiological activity of the human heart The interpretation of MCG recordings remains a challenge since there are no databases available from which precise rules could be educed. Hence, there is a need to automate interpretation of MCG measurements to minimize human input for the analysis. In this particular case SOMs are applied in detecting ischemia, which is a loss of conductivity because of damaged cell tissue in the heart and the main cause of heart attacks. © 2004 IEEE.Mahidol UniversityComputer ScienceEngineeringConference PaperSCOPUS