Improving Zero-shot ADL Recognition with Large Language Models through Event-based Context and Confidence
This work addresses the challenge of unobtrusive ADL recognition for applications in healthcare, safety, and energy management, representing an incremental improvement over existing zero-shot methods.
The paper tackles the problem of zero-shot recognition of Activities of Daily Living (ADLs) in smart homes by proposing event-based segmentation and a confidence estimation method, resulting in consistent outperformance over time-based LLM approaches and surpassing supervised methods on complex datasets, even with smaller LLMs like Gemma 3 27B.
Unobtrusive sensor-based recognition of Activities of Daily Living (ADLs) in smart homes by processing data collected from IoT sensing devices supports applications such as healthcare, safety, and energy management. Recent zero-shot methods based on Large Language Models (LLMs) have the advantage of removing the reliance on labeled ADL sensor data. However, existing approaches rely on time-based segmentation, which is poorly aligned with the contextual reasoning capabilities of LLMs. Moreover, existing approaches lack methods for estimating prediction confidence. This paper proposes to improve zero-shot ADL recognition with event-based segmentation and a novel method for estimating prediction confidence. Our experimental evaluation shows that event-based segmentation consistently outperforms time-based LLM approaches on complex, realistic datasets and surpasses supervised data-driven methods, even with relatively small LLMs (e.g., Gemma 3 27B). The proposed confidence measure effectively distinguishes correct from incorrect predictions.