<![CDATA[Sea wave height prediction is difficult thing to do. One factors become wave generator is wind that influenced by wind direction and wind speed. These factors are difficult to calculate and predict manually, because wind conditions change any time. Wave height prediction is important because useful for shipping safety. Many prediction methods can used to make predictions, one of them is ANN Backpropagation used in this study to predict wave height in the next hour. Time-series data used in this study is wave height, wind direction, and wind speed data every one hour in East Java Sea from 2013 to 2014. The application of ANN Backpropagation in prediction of wave height is through by several phases, there are data normalization, weight initialization using Nguyen-Widrow, training, testing, and forecasting. The training data used is wave height, wind direction, and wind speed data every one hour from January to December 2013 and the test data used is data from January to June 2014. The training process used learning rate 0.5 ,4 neurons input layer,3 neurons hidden layer,1 neuron output layer, error limit MAPE training of 13,2% and maximum of 30000 iterations.The combination of these parameters produces average MAPE test value of 17.53182%.]]>
Copyrights © 2019
