Time series forecasting based on improved multilinear trend fuzzy information granules for convolutional neural networks
Yükleniyor...
Tarih
2025
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Institute of electrical and electronics engineers inc.
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
Although 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.
Açıklama
Anahtar Kelimeler
Convolutional Neural Network (CNN), l1-Trend Filtering, Multilinear Trend Fuzzy Information Granule (FIG), Time Series Periodicity
Kaynak
IEEE transactions on fuzzy systems
WoS Q DeÄŸeri
Q1
Scopus Q DeÄŸeri
Q1
Cilt
33
Sayı
3
Künye
Zhang, 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.
