A novel high-order weighted fuzzy time series model and its application in nonlinear time series prediction

Jiang, Ping; Dong, Qingli; Li, Peizhi; Lian, Liu

doi:10.1016/j.asoc.2017.01.043

Cited by 45 publications

(14 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Further, Stefanakos et al first applied fuzzy time series forecasting in wave field predictions which supposed to be a satisfying application for nonstationary series [59]. For wind speed series forecasting, fuzzy logic also has excellent performance [32]. Fuzzy time series forecasting also performs well in air quality forecasting, and this paper is a successful application.…”

Section: Definition Of Fuzzy Time Seriesmentioning

confidence: 83%

“…Nevertheless, while the time series forecasting techniques mentioned above are widely used in the prediction of air pollutant concentrations, they also have unavoidable limitations, such as the following: a lack of knowledge of the data resources, uncertainty, vagueness, huge volatility in the data and so on. Fortunately, the fuzzy time series (FTS) forecasting technique first developed by Zadeh [31] can be successfully applied to forecasting when handling data series with imprecise and unidentifiable trends [32].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Application of a novel early warning system based on fuzzy time series in urban air quality forecasting in China

Wang

2018

Applied Soft Computing

104

View full text Add to dashboard Cite

With atmospheric environmental pollution becoming increasingly serious, developing an early warning system for air quality forecasting is vital to monitoring and controlling air quality. However, considering the large fluctuations in the concentration of pollutants, most previous studies have focused on enhancing accuracy, while few have addressed the stability and uncertainty analysis, which may lead to insufficient results. Therefore, a novel early warning system based on fuzzy time series was successfully developed that includes three modules: deterministic prediction module, uncertainty analysis module, and assessment module. In this system, a hybrid model combining the fuzzy time series forecasting technique and data reprocessing approaches was constructed to forecast the major air pollutants. Moreover, an uncertainty analysis was generated to further analyze and explore the uncertainties involved in future air quality forecasting. Finally, an assessment module proved the effectiveness of the developed model. The experimental results reveal that the proposed model outperforms the comparison models and baselines, and both the accuracy and the stability of the developed system are remarkable. Therefore, fuzzy logic is a better option in air quality forecasting and the developed system will be a useful tool for analyzing and monitoring air pollution.

show abstract

Section: Definition Of Fuzzy Time Seriesmentioning

confidence: 83%

Section: Introductionmentioning

confidence: 99%

Application of a novel early warning system based on fuzzy time series in urban air quality forecasting in China

Wang

2018

Applied Soft Computing

104

View full text Add to dashboard Cite

show abstract

“…FTS models are transferred to IFTS models (e.g., Chen [27], Cheng et al [4], and Chang and Huang [32]). Besides, the results of one recent FTS [33] and one IFTS [17] approaches are also adopted for comparison in Table 5. The direction accuracy (DA) and RMSE obtained with these models of and the forecasts obtained with the proposed model are listed in Table 5.…”

Section: Figurementioning

confidence: 99%

An Intuitionistic Fuzzy Time Series Model Based on New Data Transformation Method

Chen¹,

Chen²,

Chang³

et al. 2021

IJCIS

View full text Add to dashboard Cite

Traditional time series methods can predict seasonal problems, but not problems with transferred linguistic data. Thus, a forecasting method for such problems is required. However, existing intuitionistic fuzzy time series forecasting methods lack persuasiveness in determining the degree of hesitation and the lengths of intervals. Hence, this research is mainly to explore how to decide the degree of hesitation for each interval for intuitionistic fuzzy time series. This paper proposes the weighted intuitionistic fuzzy time series model based on the Nth quantile discretization approach (NQDA). The proposed model can decide the appropriate number, interval length, degree of hesitation, and membership and nonmembership functions of linguistic values on the basis of the training data. In the experimental section, the forecasts of several data sets are made for model validation. Results indicate that the proposed model can be used to obtain forecasts for other time-related data sets.

show abstract

“…Já os modelos de STN de Alta Ordem (STNAO) são capazes de reconhecer padrões passados mais complexos na série temporal, incluindo sazonalidades e tendências, e são discutidos em Severiano et al (2017) e Zhang et al (2018). Modelos ponderados de alta ordem são abordados em Jiang et al (2017). A determinação dos melhoresíndices de defasagem para modelos de alta ordemé discutida em Guney et al (2018), que usa ACF/PACF, veja Egrioglu (2014) e Carvalho Jr and Costa Jr (2017).…”

Section: Preliminaresunclassified

Otimização Evolutiva de Hiperparâmetros para Modelos de Séries Temporais Nebulosas

Lucas

Silva

Guimarães

2019

Anais Do 14º Simpósio Brasileiro De Automação Inteligente

View full text Add to dashboard Cite

A novel high-order weighted fuzzy time series model and its application in nonlinear time series prediction

Cited by 45 publications

References 47 publications

Application of a novel early warning system based on fuzzy time series in urban air quality forecasting in China

Application of a novel early warning system based on fuzzy time series in urban air quality forecasting in China

An Intuitionistic Fuzzy Time Series Model Based on New Data Transformation Method

Otimização Evolutiva de Hiperparâmetros para Modelos de Séries Temporais Nebulosas

Contact Info

Product

Resources

About