Multi-attention network with redundant information filtering for multi-horizon in multivariate time series

被引:2
作者
Geng, Xiulin [1 ]
He, Xiaoyu [1 ,2 ]
Hu, Miao
Bi, Meihua [1 ]
Teng, Xuyang [1 ]
Wu, Chao [1 ]
机构
[1] Hangzhou Dianzi Univ, Sch Commun Engn, Hangzhou 310018, Peoples R China
[2] Zhejiang Sci Tech Univ, Sch Comp Sci & Technol, Hangzhou 310018, Peoples R China
关键词
Multivariate time series; Multi-horizon forecasting; Redundancy filtering; Feature fusion; Attention mechanism; MODELS; LSTM;
D O I
10.1016/j.eswa.2024.125062
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Multi-horizon forecasting of multivariate time series has always been a prominent research topic in domains such as finance and transportation. While prediction models that integrate attention mechanisms and Seq2Seq frameworks effectively capture the temporal dependencies between sequences, there might exist distinctions in the contributions of different input variables to the predictions. RNN-based encoders often overlook these distinctions. Hence, we propose a Multi-attention Network with Redundant Information Filtering (MNRIF) for Multi-horizon Forecasting in Multivariate Time Series, comprising the underlying component Two-stage Feature Fusion Network (TSFFN) and the upper-level structure Temporal Attention Network(TAN). TSFFN first designs a variable-level attention to screen the spatial semantics of explanatory variables during multi-step recursive iterations, effectively reducing noisy information, then builds a feature gate fusion module to adaptively weigh the degree of association between prediction targets and spatial semantics as well as target variables, thereby accomplishing secondary filtering of redundant information. TAN is a task-oriented learner that combines the Encoder-Decoder framework with attention mechanism. By means of dual information filtering based on attention mechanism and recurrent gate, it enhances effective mining of long-term temporal dependency features in sequences. Extensive experiments conducted on three real-world benchmark datasets demonstrate MNRIF's superior performance compared to various state-of-the-art methods of different types.
引用
收藏
页数:12
相关论文
共 50 条
  • [41] Gated Multi-Attention Feedback Network for Medical Image Super-Resolution
    Shang, Jianrun
    Zhang, Xue
    Zhang, Guisheng
    Song, Wenhao
    Chen, Jinyong
    Li, Qilei
    Gao, Mingliang
    ELECTRONICS, 2022, 11 (21)
  • [42] Electromyographic hand gesture recognition using convolutional neural network with multi-attention
    Zhang, Zhen
    Shen, Quming
    Wang, Yanyu
    BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2024, 91
  • [43] Unsupervised Multi-head Attention Autoencoder for Multivariate Time-Series Anomaly Detection
    Kim, Minseok
    Park, Sanghyun
    2024 IEEE INTERNATIONAL CONFERENCE ON BIG DATA AND SMART COMPUTING, IEEE BIGCOMP 2024, 2024, : 1 - 7
  • [44] A novel multi-attention, multi-scale 3D deep network for coronary artery segmentation
    Dong, Caixia
    Xu, Songhua
    Dai, Duwei
    Zhang, Yizhi
    Zhang, Chunyan
    Li, Zongfang
    MEDICAL IMAGE ANALYSIS, 2023, 85
  • [45] A generative adversarial neural network with multi-attention feature extraction for fundus lesion segmentation
    Haiying Yuan
    Mengfan Dai
    Cheng Shi
    Minghao Li
    Haihang Li
    International Ophthalmology, 2023, 43 : 5079 - 5090
  • [46] A small object detection model for drone images based on multi-attention fusion network
    Hu, Jie
    Pang, Ting
    Peng, Bo
    Shi, Yongguo
    Li, Tianrui
    IMAGE AND VISION COMPUTING, 2025, 155
  • [47] Multi-attention semantic segmentation method for forest information extraction in hilly and mountainous areas
    Xu, Zikun
    Li, Hengkai
    Long, Beiping
    Huang, Duan
    Zou, Weigang
    JOURNAL OF APPLIED REMOTE SENSING, 2024, 18 (02) : 24518
  • [48] A generative adversarial neural network with multi-attention feature extraction for fundus lesion segmentation
    Yuan, Haiying
    Dai, Mengfan
    Shi, Cheng
    Li, Minghao
    Li, Haihang
    INTERNATIONAL OPHTHALMOLOGY, 2023, 43 (12) : 5079 - 5090
  • [49] Bearing Fault Diagnosis Using Convolutional Neural Network Based on a Multi-Attention Mechanism
    Kang T.
    Duan R.
    Yang L.
    Xue J.
    Liao Y.
    Hsi-An Chiao Tung Ta Hsueh/Journal of Xi'an Jiaotong University, 2022, 56 (12): : 68 - 77
  • [50] A dual-stage attention-based Bi-LSTM network for multivariate time series prediction
    Cheng, Qi
    Chen, Yixin
    Xiao, Yuteng
    Yin, Hongsheng
    Liu, Weidong
    JOURNAL OF SUPERCOMPUTING, 2022, 78 (14) : 16214 - 16235