A Fuzzy C-Means Clustering-Based Hybrid Multivariate Time Series Prediction Framework With Feature Selection

Multivariate time series prediction (MTSP) stands as a significant and challenging frontier in the data science domain, garnering considerable interest among researchers. Extreme learning machine (ELM) has emerged as a popular machine learning algorithm capable of effectively addressing MTSP challen...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:IEEE transactions on fuzzy systems Ročník 32; číslo 8; s. 4270 - 4284
Hlavní autoři: Zhan, Jianming, Huang, Xianfeng, Qian, Yuhua, Ding, Weiping
Médium: Journal Article
Jazyk:angličtina
Vydáno: IEEE 01.08.2024
Témata:
Clustering algorithms
Data models
Extreme learning machine (ELM)
Feature extraction
feature selection
fuzzy C-means (FCM) clustering
multivariate time series prediction (MTSP)
Possibility theory
Prediction algorithms
Predictive models
Time series analysis
ISSN:1063-6706, 1941-0034
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Multivariate time series prediction (MTSP) stands as a significant and challenging frontier in the data science domain, garnering considerable interest among researchers. Extreme learning machine (ELM) has emerged as a popular machine learning algorithm capable of effectively addressing MTSP challenges. However, the high-dimensional and nonlinear nature of prediction information within Big Data contexts exposes certain limitations in ELM's prediction performance. To address this issue, this article proposes a hybrid MTSP framework based on fuzzy C-means (FCM) clustering coupled with feature selection. The framework begins with a possibility distribution (PD)-based feature selection algorithm designed to evaluate information quality and describe information uncertainty via multisource information fusion. Subsequently, a robust FCM algorithm is developed, optimizing the clustering process by incorporating feature differences and neighbor information of samples while employing a multimetric hybrid strategy to determine cluster numbers. Additionally, an enhanced dual-kernel ELM (EDKELM) network is established to enhance prediction capabilities. The resulting hybrid MTSP framework with feature selection excels in autonomously discovering intrinsic feature-model connections, exhibiting superior prediction performance, and demonstrating excellent generalization ability. Experimental results using real-world datasets showcase the competitiveness of the proposed framework over existing machine learning prediction models in resolving multivariate prediction challenges.
ISSN:1063-6706
1941-0034
DOI:10.1109/TFUZZ.2024.3393622