Hybrid Time-Series Prediction Method Based on Entropy Fusion Feature

被引:3
|
作者
Zhang, Jing [1 ,2 ,3 ,4 ]
Yang, Yang [1 ,3 ]
Feng, Yong [1 ,3 ]
机构
[1] Kunming Univ Sci & Technol, Fac Informat Engn & Automat, Kunming 650500, Peoples R China
[2] Yunnan Key Lab Comp Technol Applicat, Kunming 650500, Yunnan, Peoples R China
[3] Key Lab Artificial Intelligence Yunnan Prov, Kunming 650500, Peoples R China
[4] Yunnan Xiaorun Technol Serv Co Ltd, Kunming 650500, Peoples R China
关键词
Compendex;
D O I
10.1155/2023/3578867
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
High-precision time sequence forecasting is a complicated cyber-physical system (CPS) task. Due to the diversity of data scales and types, the classic time-series prediction model meets the challenge to deliver accurate prediction results for many forms of time-series data. This work proposes a hybrid model with long short-term memory (LSTM) and embedded empirical mode decomposition (EEMD) based on the entropy fusion feature. First, we apply EEMD in entropy fusion feature long short-term memory (ELSTM) to lessen pattern confusion and edge effects in traditional empirical mode decomposition (EMD). The sequence is then divided into intrinsic mode functions (IMF) by using EEMD. Then, feature vectors are constructed between IMFs and their respective information entropy for feature merging. LSTM is used to build a full connection network for each entropy fusion feature IMF subsequence for prediction and each type of IMF subsequence as the feature dimension to obtain its prediction results. Finally, the output results of all IMF subsequences are reconstructed to obtain the final prediction result. Compared with the LSTM method, the performance of the proposed method has been improved 64.33% on the evaluation metric MAPE. The proposed model has also delivered the best prediction outcomes across four different time-series datasets. The experimental results conclusively show that the proposed method outperforms other models compared.
引用
收藏
页数:18
相关论文
共 50 条
  • [1] Time-Series Prediction Based on Double Pyramid Bidirectional Feature Fusion Mechanism
    Wang, Na
    Zhao, Xianglian
    IEICE TRANSACTIONS ON FUNDAMENTALS OF ELECTRONICS COMMUNICATIONS AND COMPUTER SCIENCES, 2023, E106A (06) : 886 - 895
  • [2] A Time-series Prediction Algorithm Based on a Hybrid Model
    Cao D.
    Ma J.
    Sun L.
    Ma N.
    Recent Advances in Computer Science and Communications, 2023, 16 (01) : 3 - 17
  • [3] Research on Ensemble Learning-Based Feature Selection Method for Time-Series Prediction
    Huang, Da
    Liu, Zhaoguo
    Wu, Dan
    APPLIED SCIENCES-BASEL, 2024, 14 (01):
  • [4] Deep Fusion Prediction Method for Nonstationary Time Series Based on Feature Augmentation and Extraction
    Zhang, Yu-Lei
    Bai, Yu-Ting
    Jin, Xue-Bo
    Su, Ting-Li
    Kong, Jian-Lei
    Zheng, Wei-Zhen
    APPLIED SCIENCES-BASEL, 2023, 13 (08):
  • [5] Temporal Feature Selection for Time-series Prediction
    Hido, Shohei
    Morimura, Tetsuro
    2012 21ST INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR 2012), 2012, : 3557 - 3560
  • [6] A planetary gearbox fault diagnosis method based on time-series imaging feature fusion and a transformer model
    Wu, Rui
    Liu, Chao
    Han, Te
    Yao, Jiachi
    Jiang, Dongxiang
    MEASUREMENT SCIENCE AND TECHNOLOGY, 2023, 34 (02)
  • [7] A New Hybrid Model for Time-series Prediction
    Pan, Feng
    Xia, Min
    Bai, En'jian
    PROCEEDINGS OF THE 8TH IEEE INTERNATIONAL CONFERENCE ON COGNITIVE INFORMATICS, 2009, : 281 - 286
  • [8] Semi-supervised prediction method for time series based on Monte Carlo and time fusion feature attention
    Yang, Yang
    Zhang, Jing
    Wang, Lulu
    APPLIED SOFT COMPUTING, 2024, 167
  • [9] Feature Selection for Time-Series Prediction in Case of Undetermined Estimation
    Sergii, Khmilovyi
    Yurii, Skobtsov
    Tatyana, Vasyaeva
    Natalia, Andrievskaya
    BIOLOGICALLY INSPIRED COGNITIVE ARCHITECTURES (BICA) FOR YOUNG SCIENTISTS, 2016, 449 : 85 - 97
  • [10] A New Method of Time-Series Event Prediction Based on Sequence Labeling
    Zhong, Zihan
    Lv, Shu
    Shi, Kaibo
    APPLIED SCIENCES-BASEL, 2023, 13 (09):