Title :
Prediction of significant wave height in The Java Sea using Artificial Neural Network
Author :
Rizianiza, Illa ; Aisjah, Aulia Siti
Author_Institution :
Dept. of Eng. Phys., Inst. Teknol. Sepuluh Nopember, Surabaya, Indonesia
Abstract :
The Java Sea is one of the busiest ship traffic both of domestic and international shipping and potential marine accident is quite high. It is about 43.6% of marine accidents is caused by natural factor. There are two point in this research. Point 1 at latitude 5° 55\´29.03" S longitude 110°51\´42.88" E and point 2 at latitude 4°39\´41.99" S longitude 109°10\´7.15" E. Design predictor of significant wave height is using Artificial Neural Network with backpropagation algorithm. The predictor consists of three inputs. They are significant wave height (m); wind speed (m/s) and wind direction (degree). Architecture of Artificial Neural Network is point 1 [3, 6, 1] dan point 2 [3, 3, 1]. The result RMSE in this prediction are point 1 0.006 m; point 2 0.075 m.
Keywords :
backpropagation; geophysics computing; neural nets; ocean waves; Java Sea; RMSE; artificial neural network; backpropagation algorithm; domestic shipping; international shipping; marine accident; significant wave height prediction; Artificial neural networks; Java; Neurons; Oceans; Training; Wind speed; backpropagation; significant wave height; wind direction; wind speed;
Conference_Titel :
Intelligent Technology and Its Applications (ISITIA), 2015 International Seminar on
Conference_Location :
Surabaya
Print_ISBN :
978-1-4799-7710-9
DOI :
10.1109/ISITIA.2015.7219944