Game of LLMs: Discovering Structural Constructs in Activities using Large Language Models
This work addresses the challenge of varying activity durations in smart homes, offering a potential improvement for activity monitoring systems, though it appears incremental as it builds on prior findings about activity building blocks.
The paper tackles the problem of human activity recognition in smart homes by identifying underlying structural constructs (building blocks) using large language models, which helps recognize short-duration and infrequent activities and proposes a new activity recognition procedure for improved monitoring.
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.