Large Language Models are Zero-Shot Recognizers for Activities of Daily Living

TL;DR

This paper introduces ADL-LLM, a novel system that uses large language models to recognize daily activities from sensor data in smart homes, enabling zero-shot and few-shot recognition without extensive training.

Contribution

The paper presents ADL-LLM, the first LLM-based ADL recognition system that transforms sensor data into text for zero-shot and few-shot activity recognition in smart environments.

Findings

Effective zero-shot recognition of ADLs using LLMs

Improved performance with few-shot prompting when small datasets are available

Validated on two public datasets showing promising results

Abstract

The sensor-based recognition of Activities of Daily Living (ADLs) in smart home environments enables several applications in the areas of energy management, safety, well-being, and healthcare. ADLs recognition is typically based on deep learning methods requiring large datasets to be trained. Recently, several studies proved that Large Language Models (LLMs) effectively capture common-sense knowledge about human activities. However, the effectiveness of LLMs for ADLs recognition in smart home environments still deserves to be investigated. In this work, we propose ADL-LLM, a novel LLM-based ADLs recognition system. ADLLLM transforms raw sensor data into textual representations, that are processed by an LLM to perform zero-shot ADLs recognition. Moreover, in the scenario where a small labeled dataset is available, ADL-LLM can also be empowered with few-shot prompting. We evaluated ADL-LLM on two public datasets, showing its effectiveness in this domain.