Prediction of Significant Wave Height Using Neural Network in the Java Sea (North of Surabaya)
| Autor: | P. Juniarko, R.A. Atmoko, Ridho Akbar, Wimala L. Dhanistha |
|---|---|
| Rok vydání: | 2017 |
| Předmět: |
geography
geography.geographical_feature_category Mean squared error Meteorology Artificial neural network Java General Medicine 010501 environmental sciences 01 natural sciences Wind speed 010305 fluids & plasmas 0103 physical sciences Archipelago Significant wave height computer 0105 earth and related environmental sciences computer.programming_language Mathematics |
| Zdroj: | Applied Mechanics and Materials. 862:72-77 |
| ISSN: | 1662-7482 |
| DOI: | 10.4028/www.scientific.net/amm.862.72 |
| Popis: | Indonesia is an archipelago, Surabaya is the second crowded city in Indonesia. So the shipping lane and the city is comparable. Neural network is models inspired by biological neural networks and used to estimate or approximate functions that can depend on a large number of inputs and are generally unknown. Neural network is used to predict the wave height in Java Sea (The North of Surabaya). The Root Mean Square Error average for the next one hour is 0.03 and the Root Mean Square Error average for the next six hours is 0.09. That’s mean the longest the prediction, the biggest Root Mean Square error. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|