Fuzzy time series forecasting with a probabilistic smoothing hidden Markov model

Yi Chung Cheng, Sheng-Tun Li

Research output: Contribution to journalArticle

31 Citations (Scopus)

Abstract

Since its emergence, the study of fuzzy time series (FTS) has attracted more attention because of its ability to deal with the uncertainty and vagueness that are often inherent in real-world data resulting from inaccuracies in measurements, incomplete sets of observations, or difficulties in obtaining measurements under uncertain circumstances. The representation of fuzzy relations that are obtained from a fuzzy time series plays a key role in forecasting. Most of the works in the literature use the rule-based representation, which tends to encounter the problem of rule redundancy. A remedial forecasting model was recently proposed in which the relations were established based on the hidden Markov model (HMM). However, its forecasting performance generally deteriorates when encountering more zero probabilities owing to fewer fuzzy relationships that exist in the historical temporal data. This paper thus proposes an enhanced HMM-based forecasting model by developing a novel fuzzy smoothing method to overcome performance deterioration. To deal with uncertainty more appropriately, the roulette-wheel selection approach is applied to probabilistically determine the forecasting result. The effectiveness of the proposed model is validated through real-world forecasting experiments, and performance comparison with other benchmarks is conducted by a Monte Carlo method.

Original languageEnglish
Article number6060907
Pages (from-to)291-304
Number of pages14
JournalIEEE Transactions on Fuzzy Systems
Volume20
Issue number2
DOIs
Publication statusPublished - 2012 Apr 1

Fingerprint

Fuzzy Time Series
Time Series Forecasting
Hidden Markov models
Markov Model
Forecasting
Smoothing
Time series
Roulette
Uncertainty
Smoothing Methods
Vagueness
Fuzzy Relation
Performance Comparison
Deterioration
Wheel
Monte Carlo method
Redundancy
Wheels
Monte Carlo methods
Model

All Science Journal Classification (ASJC) codes

  • Control and Systems Engineering
  • Computational Theory and Mathematics
  • Artificial Intelligence
  • Applied Mathematics

Cite this

@article{85d7ed6a0d7a487d94e983f541bdb3b7,
title = "Fuzzy time series forecasting with a probabilistic smoothing hidden Markov model",
abstract = "Since its emergence, the study of fuzzy time series (FTS) has attracted more attention because of its ability to deal with the uncertainty and vagueness that are often inherent in real-world data resulting from inaccuracies in measurements, incomplete sets of observations, or difficulties in obtaining measurements under uncertain circumstances. The representation of fuzzy relations that are obtained from a fuzzy time series plays a key role in forecasting. Most of the works in the literature use the rule-based representation, which tends to encounter the problem of rule redundancy. A remedial forecasting model was recently proposed in which the relations were established based on the hidden Markov model (HMM). However, its forecasting performance generally deteriorates when encountering more zero probabilities owing to fewer fuzzy relationships that exist in the historical temporal data. This paper thus proposes an enhanced HMM-based forecasting model by developing a novel fuzzy smoothing method to overcome performance deterioration. To deal with uncertainty more appropriately, the roulette-wheel selection approach is applied to probabilistically determine the forecasting result. The effectiveness of the proposed model is validated through real-world forecasting experiments, and performance comparison with other benchmarks is conducted by a Monte Carlo method.",
author = "Cheng, {Yi Chung} and Sheng-Tun Li",
year = "2012",
month = "4",
day = "1",
doi = "10.1109/TFUZZ.2011.2173583",
language = "English",
volume = "20",
pages = "291--304",
journal = "IEEE Transactions on Fuzzy Systems",
issn = "1063-6706",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

Fuzzy time series forecasting with a probabilistic smoothing hidden Markov model. / Cheng, Yi Chung; Li, Sheng-Tun.

In: IEEE Transactions on Fuzzy Systems, Vol. 20, No. 2, 6060907, 01.04.2012, p. 291-304.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Fuzzy time series forecasting with a probabilistic smoothing hidden Markov model

AU - Cheng, Yi Chung

AU - Li, Sheng-Tun

PY - 2012/4/1

Y1 - 2012/4/1

N2 - Since its emergence, the study of fuzzy time series (FTS) has attracted more attention because of its ability to deal with the uncertainty and vagueness that are often inherent in real-world data resulting from inaccuracies in measurements, incomplete sets of observations, or difficulties in obtaining measurements under uncertain circumstances. The representation of fuzzy relations that are obtained from a fuzzy time series plays a key role in forecasting. Most of the works in the literature use the rule-based representation, which tends to encounter the problem of rule redundancy. A remedial forecasting model was recently proposed in which the relations were established based on the hidden Markov model (HMM). However, its forecasting performance generally deteriorates when encountering more zero probabilities owing to fewer fuzzy relationships that exist in the historical temporal data. This paper thus proposes an enhanced HMM-based forecasting model by developing a novel fuzzy smoothing method to overcome performance deterioration. To deal with uncertainty more appropriately, the roulette-wheel selection approach is applied to probabilistically determine the forecasting result. The effectiveness of the proposed model is validated through real-world forecasting experiments, and performance comparison with other benchmarks is conducted by a Monte Carlo method.

AB - Since its emergence, the study of fuzzy time series (FTS) has attracted more attention because of its ability to deal with the uncertainty and vagueness that are often inherent in real-world data resulting from inaccuracies in measurements, incomplete sets of observations, or difficulties in obtaining measurements under uncertain circumstances. The representation of fuzzy relations that are obtained from a fuzzy time series plays a key role in forecasting. Most of the works in the literature use the rule-based representation, which tends to encounter the problem of rule redundancy. A remedial forecasting model was recently proposed in which the relations were established based on the hidden Markov model (HMM). However, its forecasting performance generally deteriorates when encountering more zero probabilities owing to fewer fuzzy relationships that exist in the historical temporal data. This paper thus proposes an enhanced HMM-based forecasting model by developing a novel fuzzy smoothing method to overcome performance deterioration. To deal with uncertainty more appropriately, the roulette-wheel selection approach is applied to probabilistically determine the forecasting result. The effectiveness of the proposed model is validated through real-world forecasting experiments, and performance comparison with other benchmarks is conducted by a Monte Carlo method.

UR - http://www.scopus.com/inward/record.url?scp=84859717982&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84859717982&partnerID=8YFLogxK

U2 - 10.1109/TFUZZ.2011.2173583

DO - 10.1109/TFUZZ.2011.2173583

M3 - Article

AN - SCOPUS:84859717982

VL - 20

SP - 291

EP - 304

JO - IEEE Transactions on Fuzzy Systems

JF - IEEE Transactions on Fuzzy Systems

SN - 1063-6706

IS - 2

M1 - 6060907

ER -