Evolutionary Fuzzy Relational Modeling for Fuzzy Time Series Forecasting

Shu Ching Kuo, Chih Chuan Chen, Sheng-Tun Li

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

The use of fuzzy time series has attracted considerable attention in studies that aim to make forecasts using uncertain information. However, most of the related studies do not use a learning mechanism to extract valuable information from historical data. In this study, we propose an evolutionary fuzzy forecasting model, in which a learning technique for a fuzzy relation matrix is designed to fit the historical data. Taking into consideration the causal relationships among the linguistic terms that are missing in many existing fuzzy time series forecasting models, this method can naturally smooth the defuzzification process, thus obtaining better results than many other fuzzy time series forecasting models, which tend to produce stepwise outcomes. The experimental results with two real datasets and four indicators show that the proposed model achieves a significant improvement in forecasting accuracy compared to earlier models.

Original languageEnglish
Article number43
Pages (from-to)444-456
Number of pages13
JournalInternational Journal of Fuzzy Systems
Volume17
Issue number3
DOIs
Publication statusPublished - 2015 Sep 1

Fingerprint

Fuzzy Time Series
Time Series Forecasting
Time series
Modeling
Historical Data
Forecasting
Defuzzification
Model
Fuzzy Relation
Linguistics
Forecast
Tend
Experimental Results
Term

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Software
  • Computational Theory and Mathematics
  • Theoretical Computer Science

Cite this

@article{2bbc185ba2434623857239f1f5dba41e,
title = "Evolutionary Fuzzy Relational Modeling for Fuzzy Time Series Forecasting",
abstract = "The use of fuzzy time series has attracted considerable attention in studies that aim to make forecasts using uncertain information. However, most of the related studies do not use a learning mechanism to extract valuable information from historical data. In this study, we propose an evolutionary fuzzy forecasting model, in which a learning technique for a fuzzy relation matrix is designed to fit the historical data. Taking into consideration the causal relationships among the linguistic terms that are missing in many existing fuzzy time series forecasting models, this method can naturally smooth the defuzzification process, thus obtaining better results than many other fuzzy time series forecasting models, which tend to produce stepwise outcomes. The experimental results with two real datasets and four indicators show that the proposed model achieves a significant improvement in forecasting accuracy compared to earlier models.",
author = "Kuo, {Shu Ching} and Chen, {Chih Chuan} and Sheng-Tun Li",
year = "2015",
month = "9",
day = "1",
doi = "10.1007/s40815-015-0043-2",
language = "English",
volume = "17",
pages = "444--456",
journal = "International Journal of Fuzzy Systems",
issn = "1562-2479",
publisher = "Chinese Fuzzy Systems Association",
number = "3",

}

Evolutionary Fuzzy Relational Modeling for Fuzzy Time Series Forecasting. / Kuo, Shu Ching; Chen, Chih Chuan; Li, Sheng-Tun.

In: International Journal of Fuzzy Systems, Vol. 17, No. 3, 43, 01.09.2015, p. 444-456.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Evolutionary Fuzzy Relational Modeling for Fuzzy Time Series Forecasting

AU - Kuo, Shu Ching

AU - Chen, Chih Chuan

AU - Li, Sheng-Tun

PY - 2015/9/1

Y1 - 2015/9/1

N2 - The use of fuzzy time series has attracted considerable attention in studies that aim to make forecasts using uncertain information. However, most of the related studies do not use a learning mechanism to extract valuable information from historical data. In this study, we propose an evolutionary fuzzy forecasting model, in which a learning technique for a fuzzy relation matrix is designed to fit the historical data. Taking into consideration the causal relationships among the linguistic terms that are missing in many existing fuzzy time series forecasting models, this method can naturally smooth the defuzzification process, thus obtaining better results than many other fuzzy time series forecasting models, which tend to produce stepwise outcomes. The experimental results with two real datasets and four indicators show that the proposed model achieves a significant improvement in forecasting accuracy compared to earlier models.

AB - The use of fuzzy time series has attracted considerable attention in studies that aim to make forecasts using uncertain information. However, most of the related studies do not use a learning mechanism to extract valuable information from historical data. In this study, we propose an evolutionary fuzzy forecasting model, in which a learning technique for a fuzzy relation matrix is designed to fit the historical data. Taking into consideration the causal relationships among the linguistic terms that are missing in many existing fuzzy time series forecasting models, this method can naturally smooth the defuzzification process, thus obtaining better results than many other fuzzy time series forecasting models, which tend to produce stepwise outcomes. The experimental results with two real datasets and four indicators show that the proposed model achieves a significant improvement in forecasting accuracy compared to earlier models.

UR - http://www.scopus.com/inward/record.url?scp=84940996868&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84940996868&partnerID=8YFLogxK

U2 - 10.1007/s40815-015-0043-2

DO - 10.1007/s40815-015-0043-2

M3 - Article

AN - SCOPUS:84940996868

VL - 17

SP - 444

EP - 456

JO - International Journal of Fuzzy Systems

JF - International Journal of Fuzzy Systems

SN - 1562-2479

IS - 3

M1 - 43

ER -