[3Yin-A] Poster 5

[3Yin-A-11] DiffNator: Generating Structured Explanations of Time-Series Differences

〇Kota Dohi¹, Tomoya Nishida¹, Harsh Purohit¹, Takashi Endo¹, Yohei Kawaguchi¹ (1. Hitachi, Ltd.)

Keywords:

Sensor data analysis,Caption generation,Time series difference

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.