App. Res. of Comp. Accepted Paper
Vol. 43, 2026 No. 12

Asymmetric water consumption time series forecasting model via adaptive time-frequency decoupling and kan

Li Xiaohui
Geng Yanbing
Lian Yongjian
Cui Fangshu
School of Computer Science and Technology, North University of China, Taiyuan Shanxi 030051, China
DOI: 10.19734/j.issn.1001-3695.2026.05.0121

Abstract

This study addressed the loss of forecasting accuracy caused by the coexistence of genuine and spurious peaks in smart water management. It proposed WaveKAN-Mix, an asymmetric forecasting framework that integrates time-frequency decoupling with Kolmogorov-Arnold Networks (KAN) . The framework first used learnable wavelet decomposition and frequency-domain energy gating to perform adaptive time-frequency decoupling and reduce the early mixing of abrupt real peaks with high-frequency noise. It then applied environmental-covariate-based asymmetric modulation to calibrate low-frequency backbone features under environmental priors and suppress abnormal fluctuation propagation and pseudo-trend drift. Finally, it employed a KAN-based cross-scale nonlinear synthesis head to jointly reconstruct low-frequency trends and high-frequency details, thereby reducing peak attenuation and phase lag. Experiments showed that WaveKAN-Mix reduced the mean squared error and mean absolute error by 6.05% and 7.14% on average, respectively, over representative baselines. The results demonstrate improved stability and robustness in peak forecasting and phase alignment.

Foundation Support

山西省基础研究计划(202303021222084)

Publish Information

DOI: 10.19734/j.issn.1001-3695.2026.05.0121
Publish at: Application Research of Computers Accepted Paper, Vol. 43, 2026 No. 12

Publish History

[2026-08-21] Accepted Paper

Cite This Article

李晓辉, 耿艳兵, 廉永健, 等. 融合时频自适应解耦与KAN的非对称水务时序预测 [J]. 计算机应用研究, 2026, 43 (12). (2026-08-25). https://doi.org/10.19734/j.issn.1001-3695.2026.05.0121. (Li Xiaohui, Geng Yanbing, Lian Yongjian, et al. Asymmetric water consumption time series forecasting model via adaptive time-frequency decoupling and kan [J]. Application Research of Computers, 2026, 43 (12). (2026-08-25). https://doi.org/10.19734/j.issn.1001-3695.2026.05.0121. )

About the Journal

  • Application Research of Computers Monthly Journal
  • Journal ID ISSN 1001-3695
    CN  51-1196/TP

Application Research of Computers, founded in 1984, is an academic journal of computing technology sponsored by Sichuan Institute of Computer Sciences under the Science and Technology Department of Sichuan Province.

Aiming at the urgently needed cutting-edge technology in this discipline, Application Research of Computers reflects the mainstream technology, hot technology and the latest development trend of computer application research at home and abroad in a timely manner. The main contents of the journal include high-level academic papers in this discipline, the latest scientific research results and major application results. The contents of the columns involve new theories of computer discipline, basic computer theory, algorithm theory research, algorithm design and analysis, blockchain technology, system software and software engineering technology, pattern recognition and artificial intelligence, architecture, advanced computing, parallel processing, database technology, computer network and communication technology, information security technology, computer image graphics and its latest hot application technology.

Application Research of Computers has many high-level readers and authors, and its readers are mainly senior and middle-level researchers and engineers engaged in the field of computer science, as well as teachers and students majoring in computer science and related majors in colleges and universities. Over the years, the total citation frequency and Web download rate of Application Research of Computers have been ranked among the top of similar academic journals in this discipline, and the academic papers published are highly popular among the readers for their novelty, academics, foresight, orientation and practicality.

Indexed & Evaluation

  • The Second National Periodical Award 100 Key Journals
  • Double Effect Journal of China Journal Formation
  • the Core Journal of China (Peking University 2023 Edition)
  • the Core Journal for Science
  • Chinese Science Citation Database (CSCD) Source Journals
  • RCCSE Chinese Core Academic Journals
  • Journal of China Computer Federation
  • 2020-2022 The World Journal Clout Index (WJCI) Report of Scientific and Technological Periodicals
  • Full-text Source Journal of China Science and Technology Periodicals Database
  • Source Journal of China Academic Journals Comprehensive Evaluation Database
  • Source Journals of China Academic Journals (CD-ROM Version), China Journal Network
  • 2017-2019 China Outstanding Academic Journals with International Influence (Natural Science and Engineering Technology)
  • Source Journal of Top Academic Papers (F5000) Program of China's Excellent Science and Technology Journals
  • Source Journal of China Engineering Technology Electronic Information Network and Electronic Technology Literature Database
  • Source Journal of British Science Digest (INSPEC)
  • Japan Science and Technology Agency (JST) Source Journal
  • Russian Journal of Abstracts (AJ, VINITI) Source Journals
  • Full-text Journal of EBSCO, USA
  • Cambridge Scientific Abstracts (Natural Sciences) (CSA(NS)) core journals
  • Poland Copernicus Index (IC)
  • Ulrichsweb (USA)