文献类型：期刊文献

英文题名：Transferable Deep Slow Feature Network With Target Feature Attention for Few-Shot Time-Series Prediction

作者：Yang, Dan[1];Peng, Xin[1];Jiang, Chao[1];Wu, Xiaolong[2,3];Ding, Steven X.[4];Zhong, Weimin[1]

机构：[1]East China Univ Sci & Technol, Key Lab Smart Mfg Energy Chem Proc, Minist Educ, Shanghai 200237, Peoples R China;[2]Beijing Univ Technol, Beijing Artificial Intelligence Inst, Engn Res Ctr Digital Community, Minist Educ,Fac Informat Technol,Beijing Key Lab C, Beijing 100124, Peoples R China;[3]Beijing Univ Technol, Beijing Lab Intelligent Environm Protect, Beijing 100124, Peoples R China;[4]Univ Duisburg Essen, Inst Automat Control & Complex Syst, D-47057 Duisburg, Germany

年份：2024

卷号：20

期号：5

起止页码：7292

外文期刊名：IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS

收录：;EI(收录号：20240815571677);WOS:【SCI-EXPANDED(收录号:WOS:001174253100001)】；

基金：No Statement Available

语种：英文

外文关键词：Feature extraction; Time series analysis; Training; Probabilistic logic; Bayes methods; Probability distribution; Monitoring; Bayesian inference; gate recurrent unit; slow feature analysis (SFA); transfer learning (TL); wastewater treatment process (WWTP)

摘要：Data-driven methods for predicting quality variables in wastewater treatment processes (WWTPs) have mostly ignored the slow time-varying nature of WWTP, and they are data-consuming that need a large amount of independent and homogeneously distributed data, which makes it difficult to collect. To address this issue with few-shot and inconsistent distribution, a transfer learning method called transferable deep slow feature network (TDSFN) for time-series prediction is proposed by leveraging the knowledge of relevant datasets. TDSFN extracts nonlinear slow features of WWTP with inertia from the time series through a deep slow feature network and constructs the domain invariant features based on them. Target feature attention is designed in TDSFN to enhance the predictor adaptability to the target domain by assigning weights to the source features based on their similarity to target features. Furthermore, a variational Bayesian inference framework is introduced to learn the parameters of TDSFN. The effectiveness of TDSFN is verified through prediction experiments based on WWTP.