发表机构
Jilin University; Hong Kong Polytechnic University; Pengcheng Laboratory; Changchun Normal University（吉林大学; 香港理工大学; 鹏城实验室; 长春师范大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
FreSH是一种频率分段分层多专家框架，通过自适应多尺度分析等技术解决MTSC的类别不平衡等挑战，在30个UEA基准数据集和真实振动数据上，其分类准确率优于SOTA且模型规模更小、效率更高。
AI 中文摘要
多变量时间序列分类（MTSC）需要模型能够有效捕获跨多个尺度的复杂时间模式，同时保持计算效率。然而，现有方法通常难以协调细粒度表示学习，尤其是在类别不平衡和现实约束下。在本文中，我们提出了FreSH，一种频率分段分层多专家框架，旨在应对这些挑战。FreSH为MTSC引入了新视角，通过对时间信号进行自适应多尺度分析，使数据的不同方面能够以互补和协调的方式建模。通过结合局部专业化与整体上下文建模，FreSH实现了强大的表示能力，同时不会产生过多的计算开销。自适应融合策略进一步增强了灵活性，使模型能够动态强调输入中信息最丰富的组件。此外，我们纳入了更鲁棒的优化目标，以提高不同样本难度和类别分布下的学习稳定性。在30个UEA基准数据集和真实世界振动数据上的广泛评估表明，FreSH在分类准确率上始终优于最先进的方法，同时大幅减小了模型规模并提升了效率。
英文摘要
Multivariate Time Series Classification (MTSC) demands models that can effectively capture complex temporal patterns across multiple scales while remaining computationally efficient. However, existing approaches generally struggle to reconcile fine-grained representation learning, especially under class imbalance and real-world constraints. In this paper, we present FreSH, a Frequency-Segmented Hierarchical Multi-Expert Framework designed to address these challenges. FreSH introduces a new perspective for MTSC by enabling adaptive, multi-scale analysis of temporal signals, allowing different aspects of the data to be modeled in a complementary and coordinated manner. By combining localized specialization with holistic context modeling, FreSH achieves strong representational capacity without incurring excessive computational overhead. An adaptive fusion strategy further enhances flexibility, enabling the model to dynamically emphasize the most informative components of the input. In addition, we incorporate a more robust optimization objective that improves learning stability across varying sample difficulties and class distributions. Extensive evaluations on 30 UEA benchmark datasets and real-world vibration data demonstrate that FreSH consistently outperforms state-of-the-art methods in classification accuracy, while substantially reducing model size and efficiency.
