Univariate Channel Fusion for Multivariate Time Series Classification

TL;DR

This paper introduces Univariate Channel Fusion (UCF), a lightweight method transforming multivariate time series into univariate form, enabling efficient classification with often better accuracy and lower computational cost across diverse applications.

Contribution

The paper proposes UCF, a novel univariate transformation approach for multivariate time series classification that improves efficiency and often enhances accuracy over existing methods.

Findings

UCF often outperforms baseline and state-of-the-art methods.

UCF achieves substantial computational efficiency gains.

UCF is particularly effective with highly correlated channels.

Abstract

Multivariate time series classification (MTSC) plays a crucial role in various domains, including biomedical signal analysis and motion monitoring. However, existing approaches, particularly deep learning models, often require high computational resources, making them unsuitable for real-time applications or deployment on low-cost hardware, such as IoT devices and wearable systems. In this paper, we propose the Univariate Channel Fusion (UCF) method to deal with MTSC efficiently. UCF transforms multivariate time series into a univariate representation through simple channel fusion strategies such as the mean, median, or dynamic time warping barycenter. This transformation enables the use of any classifier originally designed for univariate time series, providing a flexible and computationally lightweight alternative to complex models. We evaluate UCF in five case studies covering diverse application domains, including chemical monitoring, brain-computer interfaces, and human activity analysis. The results demonstrate that UCF often outperforms baseline methods and state-of-the-art algorithms tailored for MTSC, while achieving substantial gains in computational efficiency, being particularly effective in problems with high inter-channel correlation.