Multi-period interaction networks for time series forecasting

doi:10.1016/j.patrec.2025.09.007

Multi-period interaction networks for time series forecasting

2025-09-22

0

PRE

AI

DOI：10.1016/j.patrec.2025.09.007

Original

Original request for help

Save

Abstract

En 中文

• Proposes MPINet, an efficient MLP model for multi-period time series forecasting. • Designs a PFIN module to capture the local and cross-period dependencies. • Achieves state-of-the-art SOH estimation accuracy on real battery datasets. • Offers a lightweight architecture with low memory and runtime costs.

Multi-period interaction networks for time series forecasting

Abstract

Journal

Organization