arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2510.23261cs.LG
收藏

迈向可解释的时间序列分割评估度量

Toward Interpretable Evaluation Measures for Time Series Segmentation

Inria(法国国家信息与自动化技术研究所);ENS(巴黎高等师范学校);CNRS(法国国家科学研究中心);PSL Paris(巴黎政治学院)

Félix Chavelli, Paul Boniol, Michaël Thomazo

AI总结:

针对现有时间序列分割评估度量忽视分割质量且可解释性差的问题,本文提出WARI和SMS两种新度量,分别考虑误差位置和细粒度误差类型,并在合成及真实基准上验证其更准确且能揭示误差来源。

摘要:

时间序列分割是分析各领域时序数据的一项基础任务,涵盖从人类活动识别到能源监测等众多应用。尽管已有大量最先进的方法被开发出来解决这一问题,但其性能评估仍然受到严重限制。现有度量主要侧重于变点准确性,或依赖于诸如调整兰德指数(ARI)等基于点的度量,这些度量无法捕捉所检测分割的质量,忽视了误差的性质,并且可解释性有限。在本文中,我们通过引入两种新颖的评估度量来解决这些不足:WARI(加权调整兰德指数),它考虑了分割误差的位置;以及SMS(状态匹配得分),这是一种细粒度度量,能够识别并对四种基本类型的分割误差进行评分,同时允许针对特定误差进行加权。我们在合成基准和真实世界基准上对WARI和SMS进行了实证验证,结果表明它们不仅提供了对分割质量更准确的评估,还揭示了传统度量无法获得的见解,例如误差来源和误差类型。

英文摘要:

Time series segmentation is a fundamental task in analyzing temporal data across various domains, from human activity recognition to energy monitoring. While numerous state-of-the-art methods have been developed to tackle this problem, the evaluation of their performance remains critically limited. Existing measures predominantly focus on change point accuracy or rely on point-based measures such as Adjusted Rand Index (ARI), which fail to capture the quality of the detected segments, ignore the nature of errors, and offer limited interpretability. In this paper, we address these shortcomings by introducing two novel evaluation measures: WARI (Weighted Adjusted Rand Index), that accounts for the position of segmentation errors, and SMS (State Matching Score), a fine-grained measure that identifies and scores four fundamental types of segmentation errors while allowing error-specific weighting. We empirically validate WARI and SMS on synthetic and real-world benchmarks, showing that they not only provide a more accurate assessment of segmentation quality but also uncover insights, such as error provenance and type, that are inaccessible with traditional measures.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑