Calibrating wavelet neural networks by distance orientation similarity fuzzy C-means for approximation problems
Improperly tuned wavelet neural network (WNN) has been shown to exhibit unsatisfactory generaliza-tion performance. In this study, the tuning is done by an improved fuzzy C-means algorithm, that utilizesa novel similarity measure. This similarity measure takes the orientation as well as the distance...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Published: |
Elsevier
2016
|
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1016/j.asoc.2016.01.042 http://dx.doi.org/10.1016/j.asoc.2016.01.042 http://eprints.uthm.edu.my/8005/1/ong_pauline_U.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Improperly tuned wavelet neural network (WNN) has been shown to exhibit unsatisfactory generaliza-tion performance. In this study, the tuning is done by an improved fuzzy C-means algorithm, that utilizesa novel similarity measure. This similarity measure takes the orientation as well as the distance intoaccount. The modified WNN was first applied to a benchmark problem. Performance assessments withother approaches were made subsequently. Next, the feasibility of the proposed WNN in forecasting thechaotic Mackey–Glass time series and a real world application problem, i.e., blood glucose level predic-tion, were studied. An assessment analysis demonstrated that this presented WNN was superior in termsof prediction accuracy. |
|---|