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

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Fiori, Michele, Civitarese, Gabriele, Colussi, Marco, Bettini, Claudio
Format: Preprint
Veröffentlicht: 2026
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911371454578688
author Fiori, Michele
Civitarese, Gabriele
Colussi, Marco
Bettini, Claudio
author_facet Fiori, Michele
Civitarese, Gabriele
Colussi, Marco
Bettini, Claudio
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2601_08241
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Improving Zero-shot ADL Recognition with Large Language Models through Event-based Context and Confidence
Fiori, Michele
Civitarese, Gabriele
Colussi, Marco
Bettini, Claudio
Computer Vision and Pattern Recognition
Distributed, Parallel, and Cluster Computing
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.
title Improving Zero-shot ADL Recognition with Large Language Models through Event-based Context and Confidence
topic Computer Vision and Pattern Recognition
Distributed, Parallel, and Cluster Computing
url https://arxiv.org/abs/2601.08241