Improving Zero-shot ADL Recognition with Large Language Models through Event-based Context and Confidence

TL;DR

This paper enhances zero-shot ADL recognition in smart homes by using event-based segmentation and confidence estimation with large language models, leading to improved accuracy and reliability over existing methods.

Contribution

It introduces event-based segmentation and a confidence estimation method for LLMs, significantly improving zero-shot ADL recognition performance.

Findings

Event-based segmentation outperforms time-based methods.

The approach surpasses supervised methods on complex datasets.

Confidence measure effectively identifies correct predictions.

Abstract

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.