SOURCE-LINKED INTELLIGENCE

Improving Multivariate Time Series Classification with Class-Wise Training and Model Aggregation

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

In this paper, we propose a class-wise dimension (channel) selection framework for Multivariate Time Series Classification (MTSC). Rather than applying a single global dimension selection process, the proposed approach independently identifies informative dimensions for each class. A dedicated learning process is subsequently performed for each class, followed by a fusion stage for final prediction. The objective is to improve the generation of discriminative feature representations while reducing the influence of noisy or non-informative dimensions. The proposed framework is evaluated using M

Read original source ↗ Open in workspace

recordType

paper

region

Global