The wavelet multilayer perceptron for the prediction of earthquake time series data
Forecasting a time series is a common problem in many domains of science, and this has been addressed for a long time by scientists. There exist many techniques to pre-process time series, and chief among them is wavelet approach. The use of wavelet technique to pre-process time series data has bee...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Conference or Workshop Item |
| Published: |
2011
|
| Subjects: | |
| Online Access: | http://eprints.uthm.edu.my/2983/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Forecasting a time series is a common problem in many domains of science, and this has been addressed for a long time by scientists. There exist many techniques to pre-process time series, and chief among them is wavelet approach. The use of wavelet technique to pre-process time series data has been proven to overcome the problems in numerous application where the data are imbalanced due to the outliers and noise that discriminates the data. In this work, we proposed a new model which makes use the wavelet technique to pre-process the time series data before feeding to the MLP, and it is called a wavelet multilayer perceptron (W-MLP). The model has been trained and tested for the prediction of California earthquake data. Simulation results on the prediction of earthquake time series show that W-MLP performs considerably better results when compared to Multilayer perceptron (MLP) in terms of the prediction error. |
|---|