Time Series Annotation is the process of labeling temporal data sequences with semantic or structural information to identify events, patterns, or states over time. It involves assigning timestamps, segment boundaries, or categorical tags to data such as sensor readings, financial signals, or physiological measurements. This process supports supervised learning, model evaluation, and interpretability in machine learning applications, and is widely used in domains such as forecasting, anomaly detection, and cross-domain data analysis.

Posts

Decoding Time Series with LLMs: A Multi-Agent Framework for Cross-Domain Annotation

/in /by

Time series data is ubiquitous across various domains, including manufacturing, finance, and healthcare. High-quality annotations are essential for effectively understanding time series and facilitating downstream tasks. However, obtaining such annotations is challenging, particularly in mission-critical domains. In this paper, we propose TESSA, a multi-agent system designed to automatically generate both general and domain-specific annotations for time series data. TESSA introduces two agents: a general annotation agent and a domain-specific annotation agent. The general agent captures common patterns and knowledge across multiple source domains, leveraging both time-series-wise and text-wise features to generate general annotations. Meanwhile, the domain-specific agent utilizes limited annotations from the target domain to learn domain-specific terminology and generate targeted annotations. Extensive experiments on multiple synthetic and real-world datasets demonstrate that TESSA effectively generates high-quality annotations, outperforming existing methods.

Read more