用大模型指导选样，让少样本穿戴设备动作识别更准。
LLM-Guided Exemplar Selection for Few-Shot Wearable-Sensor Human Activity Recognition
- 用大模型生成语义先验，结合几何特征优化选样
- 在少样本下达到88.78%的宏平均F1分数
- 适合需要精准区分相似动作的应用场景
本文提出一种基于大语言模型（LLM）引导的示例选择框架，以解决当前人体活动识别（HAR）方法依赖大规模标注数据、且仅靠几何方式选样难以区分相似动作（如走路、上楼、下楼）的问题。该方法通过大模型生成包含特征重要性、类间混淆度和示例预算倍数的语义先验，指导示例评分与选择。这些先验与基于间隔的验证信号、PageRank中心性、枢纽性惩罚及设施选址优化相结合，选出紧凑且信息量高的示例集。在严格少样本条件下于UCI-HAR数据集上评估，该框架实现88.78%的宏平均F1分数，优于随机采样、聚集法和k-center等经典方法。结果表明，融合大模型语义先验与结构几何线索，能为少样本可穿戴传感器活动识别提供更强的代表性示例选择基础。
原文摘要 · Abstract (English)
In this paper, we propose an LLM-Guided Exemplar Selection framework to address a key limitation in state-of-the-art Human Activity Recognition (HAR) methods: their reliance on large labeled datasets and purely geometric exemplar selection, which often fail to distinguish similar wearable sensor activities such as walking, walking upstairs, and walking downstairs. Our method incorporates semantic reasoning via an LLM-generated knowledge prior that captures feature importance, inter-class confusability, and exemplar budget multipliers, and uses it to guide exemplar scoring and selection. These priors are combined with margin-based validation cues, PageRank centrality, hubness penalization, and facility-location optimization to obtain a compact and informative set of exemplars. Evaluated on the UCI-HAR dataset under strict few-shot conditions, the framework achieves a macro F1-score of 88.78%, outperforming classical approaches such as random sampling, herding, and k-center. The results show that LLM-derived semantic priors, when integrated with structural and geometric cues, provide a stronger foundation for selecting representative sensor exemplars in few-shot wearable-sensor HAR.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。