发表机构
University of Sydney; Curtin University; Colorado State University（悉尼大学; 科廷大学; 科罗拉多州立大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
RAG-HAR+是面向边缘部署的成本高效型LLM辅助HAR方案，通过检索设计智能体优化特征、对确定样本用多数投票、仅不确定样本用LLM，在六基准上性能相当或更优且降低了LLM相关开销。
AI 中文摘要
可穿戴传感器的人类活动识别（HAR）支持医疗、康复、健身追踪及智能环境等应用，但现有深度学习方法需针对特定数据集训练、依赖大量标注语料，且需反复适配新传感器设置或活动分类体系。针对人类活动识别的检索增强生成（RAG-HAR）将HAR视为无需训练的检索增强任务，通过传感器窗口的统计描述检索相似标注示例，以指导基于LLM的分类。本文提出RAG-HAR+，这是一种以检索为优先、成本优化的扩展方案，在强化检索的同时降低对LLM推理的依赖。RAG-HAR+使用离线的检索设计智能体（Retrieval Designer Agent），从多样的运动描述符池中设计针对特定数据集的特征组，使传感器窗口可通过更契合数据集特定活动模式的特征进行比较。推理阶段，RAG-HAR+对具有强检索证据的样本采用检索近邻的多数投票，仅将不确定样本交由基于LLM的歧义解决智能体（Ambiguity Resolver Agent）处理。在六个HAR基准测试中，RAG-HAR+保持了具有竞争力或更优的性能，同时减少了LLM使用量、令牌消耗及推理时间。本文还扩展了RAG-HAR移动原型，以展示以检索为优先、LLM辅助的HAR在移动感知场景中的实际可行性。
英文摘要
Human Activity Recognition (HAR) from wearable sensors supports applications in healthcare, rehabilitation, fitness tracking, and smart environments. Yet, existing deep learning approaches require dataset-specific training, large labeled corpora, and repeated adaptation to new sensor settings or activity taxonomies. Retrieval-Augmented Generation for Human Activity Recognition (RAG-HAR) addresses this by framing HAR as a training-free, retrieval-augmented task, in which statistical descriptions of sensor windows are used to retrieve similar labeled examples that guide LLM-based classification. We introduce RAG-HAR+, a retrieval-first and cost-optimized extension that strengthens retrieval while reducing dependence on LLM-based inference. RAG-HAR+ uses an offline Retrieval Designer Agent to design dataset-specific feature groups from a diverse pool of motion descriptors, enabling sensor windows to be compared using features better aligned with dataset-specific activity patterns. During inference, RAG-HAR+ uses majority voting over retrieved neighbors for samples with strong retrieval evidence and defers only uncertain cases to an LLM-based Ambiguity Resolver Agent. Across six HAR benchmarks, RAG-HAR+ maintains competitive or improved performance while reducing LLM usage, token consumption, and inference time. We further extend the RAG-HAR mobile prototype to demonstrate the practical feasibility of retrieval-first, LLM-assisted HAR in mobile sensing scenarios.
CommentsSubmitted to IEEE Transactions on Mobile Computing. Extended version of the IEEE PerCom 2026 paper "RAG-HAR: Retrieval Augmented Generation-based Human Activity Recognition." (https://doi.org/10.1109/PerCom67906.2026.11524560)
