Implementation of The Backpropagation Method and The Kohonen Network to Predict Blood Availability: Case Study in PMI Kota Magelang

Abstract

The availability of blood stocks at the Indonesian Red Cross or Palang Merah Indonesia (PMI) is a must and absolute for institutions that organize the procurement and distribution of blood for medical purposes. The problem is that the blood stock in PMI Magelang City Branch is not ideally available in each blood type, especially blood type AB, which in recent years has been very minimal and difficult to obtain. The purpose of this study was to predict blood stock of type AB with software based on artificial neural networks backpropagation and Coherent tissues. Artificial Neural Network (JST) backpropagation is used to predict the stock supply of blood type AB. Meanwhile, Coherent is a network used to divide input patterns into groups. The application has a network structure consisting of 2 input neurons, 10 neurons in the hidden layer, and 1 and 1 neuron in the output layer. The total amount of data is 3 years (2015-2017), 2 years of data are used for training data, and 1 year of data is used for testing data. The engine predicts using a maximum iteration of 1,000 epochs, an expletive constant of 0.5, a momentum of 0.9, and a minimum error rate of 0.001. With variations in the value of the backpropagation component, a prediction of less than 140 bags per year is generated. Meanwhile, the resulting weight is predicted by the Coherent method and produces a prediction of the production of type AB blood stocks per month. Based on the results against 3 years of test data, the percentage of the system accuracy rate is 100%. The reduction of learning constants and the addition of training data systems may affect the accuracy of the system in making predictions.