Kombinasi Algoritma Backpropagation Neural Network dengan Gravitational Search Algorithm Dalam Meningkatkan Akurasi

Predicting disease is usually done based on the experience and knowledge of doctor. Diagnosis such a traditionally less effective. The development medical diagnosis machine learning in terms prediction provides more accurate than traditional way. In predicting can use artificial neural networks. network consists various algorithms, one which Backpropagation Algorithm. this paper it proposed that systems algorithm. algorithms are often used prediction, but algorithm has slight drawback tends to take long time obtaining optimum accuracy values. Therefore, combination overcome shortcomings by using success Gravitational Search Algorithm (GSA) algorithm, slow convergence local minimum problems contained So authors propose combine hopes improving results better only resulted higher level with same number iterations only. Can be seen first trial breast cancer data parameters namely hidden layer 5, rate 2 iteration as much 5000 resulting 99.3 % error 0.7% Algorithm, while BP & GSA got 99.68 0.32%.