The Modeling of Artificial Neural Network of Early Diagnosis for Malnutrition with Backpropagation Method

摘要

The negative effects of malnutrition can be minimized by developing medical technology through combining expert experience and knowledge to produce an early diagnosis. The development of ANN architectural model is conducted to identify the types of malnutrition. This research consisted of 2 phases, which were training phase in which it generated ANN weight by using feed-forward of activation function, and testing phase in which the result of the previous stage was tested to obtain output. The resulting architectural model has a 96% accuracy rate with MSE of 0.000997 during 5 seconds training period. Regression results show that the resulting model has a high degree of accuracy to produce output of malnutrition types such as marasmus, kwashiorkor, and marasmus-kwashiorkor.