Fuzzy time series forecasting model based on various types of similarity measure approach / Nik Muhammad Farhan Hakim Nik Badrul Alam and Nazirah Ramli
Fuzzy time series(FTS) is a well-known method for forecasting the time series data in linguistic values. Recently, a few studies have used the similarity measure approach in determining the performance of the FTS forecasting model. In this paper, an FTS forecasting model based on seven intervals of...
I tiakina i:
| Ngā kaituhi matua: | , |
|---|---|
| Hōputu: | Pukapuka |
| I whakaputaina: |
Universiti Teknologi MARA Cawangan Pahang,
2019.
|
| Ngā marau: | |
| Urunga tuihono: | Link Metadata |
| Ngā Tūtohu: |
Tāpirihia he Tūtohu
Kāore He Tūtohu, Me noho koe te mea tuatahi ki te tūtohu i tēnei pūkete!
|
| Whakarāpopototanga: | Fuzzy time series(FTS) is a well-known method for forecasting the time series data in linguistic values. Recently, a few studies have used the similarity measure approach in determining the performance of the FTS forecasting model. In this paper, an FTS forecasting model based on seven intervals of equal length and trapezoidal fuzzy numbers is presented. Then, the performance of FTS forecasting model using various types of similarity measure is compared. The FTS model is implemented in the case of students' enrollment in the University of Alabama and the unemployment rate in Malaysia. The hybrid similarity measure of geometric distance, center of gravity, area, perimeter and height gives the best performance |
|---|---|
| Whakaahutanga tūemi: | https://ir.uitm.edu.my/id/eprint/31176/1/31176.pdf |