The Community for Technology Leaders
2016 International Conference on Frontiers of Information Technology (FIT) (2016)
Islamabad, Pakistan
Dec. 19, 2016 to Dec. 21, 2016
ISBN: 978-1-5090-5300-1
pp: 53-56
Fazlina Ahmat Ruslan , Faculty of Electrical Engineering, Bandung Institute of Technology, Ganesha street 10 Bandung 40132, West Java - Indonesia
Abd Manan Samad , Centre of Surveying Science and Geomatics, Faculty of Arc., Planning and Surveying University Technology, MARA 40450 Shah Alam, Selangor, Malaysia
Ramli Adnan , Faculty of Electrical Engineering, Bandung Institute of Technology, Ganesha street 10 Bandung 40132, West Java - Indonesia
ABSTRACT
Nowadays flood water level predictions have become one of the most popular subject matter among researcher because this natural disaster damages people's life and property. In addition, flood is also one of the natural disasters that occur frequently around the world. However, since the dynamic of the flood itself is highly nonlinear, it is a very difficult task to predict the flood water level ahead of time. Therefore, since Multilayer Perceptron Neural Network is widely known to solve nonlinear cases, this paper proposed a 3 hours flood water level prediction for Kuala Lumpur flood prone using advance Neural Network technique. All samples used in model development and testing stage were real-time samples obtained from Department of Irrigation and Drainage Malaysia upon special request. The 3 hours NNARX flood water level prediction model have been successfully developed, analyzed and tested using MATLAB Neural Network Toolbox. Results show that the NNARX model successfully predicted flood water level 3 hours ahead of time.
INDEX TERMS
Neural Network Autoregressive Model with Exogenous Input (NNARX), Flood Prediction Model
CITATION
Fazlina Ahmat Ruslan, Abd Manan Samad, Ramli Adnan, "3 Hours flood water level prediction using NNARX structure: Case study Kuala Lumpur", 2016 International Conference on Frontiers of Information Technology (FIT), vol. 00, no. , pp. 53-56, 2016, doi:10.1109/FIT.2016.7857537
195 ms
(Ver 3.3 (11022016))