Game of LLMs: Discovering Structural Constructs in Activities using Large Language Models
Fuente:
arXiv
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916295485685760 |
|---|---|
| author | Hiremath, Shruthi K. Ploetz, Thomas |
| author_facet | Hiremath, Shruthi K. Ploetz, Thomas |
| contents | Human Activity Recognition is a time-series analysis problem. A popular analysis procedure used by the community assumes an optimal window length to design recognition pipelines. However, in the scenario of smart homes, where activities are of varying duration and frequency, the assumption of a constant sized window does not hold. Additionally, previous works have shown these activities to be made up of building blocks. We focus on identifying these underlying building blocks--structural constructs, with the use of large language models. Identifying these constructs can be beneficial especially in recognizing short-duration and infrequent activities. We also propose the development of an activity recognition procedure that uses these building blocks to model activities, thus helping the downstream task of activity monitoring in smart homes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_13777 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Game of LLMs: Discovering Structural Constructs in Activities using Large Language Models Hiremath, Shruthi K. Ploetz, Thomas Machine Learning Computation and Language Human Activity Recognition is a time-series analysis problem. A popular analysis procedure used by the community assumes an optimal window length to design recognition pipelines. However, in the scenario of smart homes, where activities are of varying duration and frequency, the assumption of a constant sized window does not hold. Additionally, previous works have shown these activities to be made up of building blocks. We focus on identifying these underlying building blocks--structural constructs, with the use of large language models. Identifying these constructs can be beneficial especially in recognizing short-duration and infrequent activities. We also propose the development of an activity recognition procedure that uses these building blocks to model activities, thus helping the downstream task of activity monitoring in smart homes. |
| title | Game of LLMs: Discovering Structural Constructs in Activities using Large Language Models |
| topic | Machine Learning Computation and Language |
| url | https://arxiv.org/abs/2406.13777 |