Forecasting students' enrolment in fuzzy time series based on three classes of t-norm of subsethood defuzzification / Nazirah Ramli and Abu Osman Md. Tap
Traditional time series methods can predict the seasonal problem but fail to forecast the problems with linguistic values. An improvised forecasting method by using fuzzy time series can be applied to deal with this problems. This paper presents three classes oft-norm of subsethood defuzzification t...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Book |
| Published: |
Universiti Teknologi MARA Cawangan Pahang,
2009.
|
| Subjects: | |
| Online Access: | Link Metadata |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Traditional time series methods can predict the seasonal problem but fail to forecast the problems with linguistic values. An improvised forecasting method by using fuzzy time series can be applied to deal with this problems. This paper presents three classes oft-norm of subsethood defuzzification that are algebraic product, Einstein product and minimum inforecasting the students' enrolments based on fuzzy time series. The proposed method uses the historical data of students' enrolment and applies seven and ten intervals with equal length and the max-product and max-min as the composition operator in the fuzzy relations. The result shows that the t-norm of algebraic product class of subsethood defuzzijication model with (10, max-product) is the best forecasting methods in terms of accuracy. The t-norm of algebraic product class with (I 0, max-product) also achieves higher forecasting accuracy rates compared to some of the existing methods. |
|---|---|
| Item Description: | https://ir.uitm.edu.my/id/eprint/33605/1/33605.PDF |