DEVELOPMENT OF HEART DETECTION DETECTION SYSTEM USING IRIDOLOGY WITH NETWORK METHODS OF CURRENT EDUCATION
Iridology is the study of the iris structure as a reflection of the condition of organs and systems in the body. In this study, the detected organ is the liver. To determine the condition of the liver through the iris, texture analysis and classification process to distinguish iris eyes that have normal and abnormal conditions. Application to detect the condition of the heart is made using Matlab version 18.104.22.1684 (R2013a). Inserts used in the processing of this digital image are eyes that have normal and abnormal liver conditions, based on the iridological map of Bernard Jensen. The image is then performed image processing, and extraction of GLCM features. These characteristic extraction results are used as input data (training data and test data) for back-propagation neural networks, then used to diagnose liver organ conditions. In the test results obtained the effect of the number of hidden layer units showed by the increase in the number of units in the hidden layer to eat the value of MSE will decrease. This makes network performance better. It is based on the test results of 35 test data with 4 variations of the number of units in the hidden layer ie, the variation of the number of hidden layer units [40 (layer 1), 20 (layer 2)], [50 (layer 1), 20 (layer 2) ], [70 (layer 1), 30 (layer 2)], and [80 (layer 1), 30 (layer 2)]. Sequentially indicate the percentage of success rate of 77.14%, 80%, 88.57%, and 91.42%.
Kata kunci: Iris mata, GLCM, Jaringan Saraf Tiruan, Perambatan Balik, 2015
Download full abstract: 10022-19349-1-SM