Time series forecasting based on improved multilinear trend fuzzy information granules for convolutional neural networks

Basit Öğe Kaydı
dc.authorscopusidWitold Pedrycz / 58861905800
dc.authorwosidWitold Pedrycz / HJZ-2779-2023
dc.contributor.authorZhang, Ronghua
dc.contributor.authorZhan, Jianming
dc.contributor.authorDing, Weiping
dc.contributor.authorPedrycz, Witold
dc.date.accessioned2025-04-17T07:55:26Z
dc.date.available2025-04-17T07:55:26Z
dc.date.issued2025
dc.departmentİstinye Üniversitesi, Mühendislik ve Doğa Bilimleri Fakültesi, Bilgisayar Mühendisliği Bölümü
dc.description.abstractAlthough the construction of multilinear trend fuzzy information granules (FIG) achieves a win-win situation in terms of interpretability and trend extraction, in its second stage of segmentation, the equal-length segmentation will result in the loss of local trend. The granulation effect will further affect the forecasting performance of the time series. To this end, this article establishes a convolutional neural network (CNN) prediction method based on improved multilinear trend FIGs. First, considering the natural cycle characteristics of the time series, this article establishes a time series segmentation algorithm based on the valley points, which replaces the equal-length segmentation in the second stage of the construction of the multilinear trend FIGs, thus enhancing the interpretability of the granulation process. Later, an evaluation index of Gaussian fuzzy information granules (GLFIGs) is proposed for improving the trend extraction effect of each multilinear trend FIG. Since the multilinear trend FIGs are constructed in the natural period segment, in order to fully exploit the correlation of the corresponding positions of each granule to enhance the prediction accuracy, a GLFIG correspondence algorithm based on the segmentation and merging is introduced in this article. Finally, CNN is selected as the prediction model based on the data characteristics. We conduct experiments on six datasets and two artificial cycle datasets, and compare the constructed model with commonly used prediction models and the latest granularity model. At last, the experiments reveal that our model performs better.
dc.description.sponsorshipNational Natural Science Foundation of China
dc.identifier.citationZhang, R., Zhan, J., Ding, W., & Pedrycz, W. (2024). Time series forecasting based on improved multi-linear trend fuzzy information granules for convolutional neural networks. IEEE Transactions on Fuzzy Systems.
dc.identifier.doi10.1109/TFUZZ.2024.3504486
dc.identifier.endpage1023
dc.identifier.issn1063-6706
dc.identifier.issn1941-0034
dc.identifier.issue3
dc.identifier.scopus2-s2.0-86000426436
dc.identifier.scopusqualityQ1
dc.identifier.startpage1009
dc.identifier.urihttp://dx.doi.org/10.1109/TFUZZ.2024.3504486
dc.identifier.urihttps://hdl.handle.net/20.500.12713/6138
dc.identifier.volume33
dc.identifier.wosWOS:001435449700005
dc.identifier.wosqualityQ1
dc.indekslendigikaynakWeb of Science
dc.indekslendigikaynakScopus
dc.institutionauthorPedrycz, Witold
dc.institutionauthoridWitold Pedrycz / 0000-0002-9335-9930
dc.language.isoen
dc.publisherInstitute of electrical and electronics engineers inc.
dc.relation.ispartofIEEE transactions on fuzzy systems
dc.relation.publicationcategoryMakale - Uluslararası Hakemli Dergi - Kurum Öğretim Elemanı
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.subjectConvolutional Neural Network (CNN)
dc.subjectl1-Trend Filtering
dc.subjectMultilinear Trend Fuzzy Information Granule (FIG)
dc.subjectTime Series Periodicity
dc.titleTime series forecasting based on improved multilinear trend fuzzy information granules for convolutional neural networks
dc.typeArticle

Dosyalar

Orijinal paket
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
Ä°sim:
Time_Series_Forecasting_Based_on_Improved_Multilinear_Trend_Fuzzy_Information_Granules_for_Convolutional_Neural_Networks.pdf
Boyut:
5.19 MB
Biçim:
Adobe Portable Document Format
Ä°ndir
Lisans paketi
Listeleniyor 1 - 1 / 1
Küçük Resim Yok
Ä°sim:
license.txt
Boyut:
1.17 KB
Biçim:
Item-specific license agreed upon to submission
Açıklama:
Ä°ndir

Koleksiyon

Bilgisayar Mühendisliği Bölümü Makale Koleksiyonu