Abstract
This study presents fuzzy time series based on the concept of long-term predictive significance level. Fuzzy time series theory and structural analysis are used to develop a long-term predictive significance level for evaluating the suitability of historical data. New triangular fuzzy numbers by S are subsequently obtained using the graded mean integration representation method. Finally, △S can strengthen fuzzy time series data for a series and yield additional information. The Shanghai Containerized Freight Index is used to illustrate the forecasting process. The results indicate that the proposed definition can generate forecast levels that provide more information for analysis.
Recommended Citation
Chou, Ming-Tao
(2017)
"AN IMPROVED FUZZY TIME SERIES THEORY WITH APPLICATIONS IN THE SHANGHAI CONTAINERIZED FREIGHT INDEX,"
Journal of Marine Science and Technology: Vol. 25:
Iss.
4, Article 4.
DOI: 10.6119/JMST-017-0313-1
Available at:
https://jmstt.ntou.edu.tw/journal/vol25/iss4/4