DiffNator: Generating Structured Explanations of Time-Series Differences
This work addresses the need for automated, interpretable explanations of time-series differences in IoT domains, offering a practical tool for non-experts.
The paper tackles the problem of interpreting differences between time series in IoT applications, which typically requires expert knowledge, by proposing DiffNator, a framework that generates structured explanations in JSON format. Experimental results show that DiffNator generates accurate explanations and substantially outperforms visual question answering and retrieval baselines.
In many IoT applications, the central interest lies not in individual sensor signals but in their differences, yet interpreting such differences requires expert knowledge. We propose DiffNator, a framework for structured explanations of differences between two time series. We first design a JSON schema that captures the essential properties of such differences. Using the Time-series Observations of Real-world IoT (TORI) dataset, we generate paired sequences and train a model that combine a time-series encoder with a frozen LLM to output JSON-formatted explanations. Experimental results show that DiffNator generates accurate difference explanations and substantially outperforms both a visual question answering (VQA) baseline and a retrieval method using a pre-trained time-series encoder.