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: 23-27
Ramli Adnan , Faculty of Electrical Engineering, Universiti Teknologi MARA, 40450 Shah Alam, Selangor, Malaysia
Abd Manan Samad , Centre of Surveying Science and Geomatics, Faculty of Arc., Planning and Surveying, Universiti Teknologi MARA, 40450 Shah Alam, Selangor, Malaysia
Fazlina Ahmat Ruslan , Faculty of Electrical Engineering, Universiti Teknologi MARA, 40450 Shah Alam, Selangor, Malaysia
ABSTRACT
Predicting flood disasters are good potential research areas due to its impact to publics and economics of the affected country. With rapid economic growth and urbanization, flash floods in cities are frequent and annoying to publics. Thus, accurate and reliable prediction model of respective rivers that causing flood to highly dense populated area is needed so that the public can be warn of the possible in coming flood disaster. This paper proposed a 3-hours river water level prediction model using NNARX with improves modelling strategy. This work made used of black-box model where only inputs and output data are required to develop the flood prediction model. The model was developed using 18 steps ahead of time flood water level values as targeted output with respect to current time inputs data to obtain the prediction model with Klang River at Petaling Bridge, Kuala Lumpur as flood location of studies. Prediction result of the proposed method shows significant prediction performance.
INDEX TERMS
Improved NNARX, Flood Water Level Prediction, Artificial Neural Network (ANN), Neural Network Autoregressive with Exogenous Input (NNARX)
CITATION
Ramli Adnan, Abd Manan Samad, Fazlina Ahmat Ruslan, "A 3-hours river water level flood prediction model using NNARX with improves modelling strategy", 2016 International Conference on Frontiers of Information Technology (FIT), vol. 00, no. , pp. 23-27, 2016, doi:10.1109/FIT.2016.7857512
1446 ms
(Ver 3.3 (11022016))