LLM-Guided Exemplar Selection for Few-Shot Wearable-Sensor Human Activity Recognition
Fuente:
arXiv
Salvato in:
| Autori principali: | , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915703073800192 |
|---|---|
| author | Ronando, Elsen Inoue, Sozo |
| author_facet | Ronando, Elsen Inoue, Sozo |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2512_22385 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | LLM-Guided Exemplar Selection for Few-Shot Wearable-Sensor Human Activity Recognition Ronando, Elsen Inoue, Sozo Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition I.2.6; I.5.4 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. |
| title | LLM-Guided Exemplar Selection for Few-Shot Wearable-Sensor Human Activity Recognition |
| topic | Computation and Language Artificial Intelligence Computer Vision and Pattern Recognition I.2.6; I.5.4 |
| url | https://arxiv.org/abs/2512.22385 |