Open Science Research Excellence

M S Elbisy

Publications

1

Publications

1
9997044
The Use Support Vector Machine and Back Propagation Neural Network for Prediction of Daily Tidal Levels along the Jeddah Coast, Saudi Arabia
Abstract:

Sea level rise threatens to increase the impact of future  storms and hurricanes on coastal communities. Accurate sea level  change prediction and supplement is an important task in determining  constructions and human activities in coastal and oceanic areas. In  this study, support vector machines (SVM) is proposed to predict  daily tidal levels along the Jeddah Coast, Saudi Arabia. The optimal  parameter values of kernel function are determined using a genetic  algorithm. The SVM results are compared with the field data and  with back propagation (BP). Among the models, the SVM is superior  to BPNN and has better generalization performance.

 

Keywords:
Tides, Prediction, Support Vector Machines, Genetic Algorithm, Back-Propagation Neural Network, Risk, Hazards.