Summary of Maintenance Required: Updating and Extending Bootstrapped Human Activity Recognition Systems For Smart Homes, by Shruthi K. Hiremath and Thomas Ploetz
Maintenance Required: Updating and Extending Bootstrapped Human Activity Recognition Systems for Smart Homes
by Shruthi K. Hiremath, Thomas Ploetz
First submitted to arxiv on: 20 Jun 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A novel approach to developing human activity recognition (HAR) systems for smart homes is presented, addressing the challenges posed by varied layouts and personalized settings. By introducing an effective updating and extension procedure, bootstrapped HAR systems can be continuously improved to keep pace with changing life circumstances. This method utilizes seed points identified during the initial bootstrapping phase, and a contrastive learning framework trained on these points and labels is used to improve segmentation accuracy for prominent activities. The resulting system effectively models routine activities in smart homes, as demonstrated through experiments on the CASAS datasets. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Smart homes can be tricky places to keep track of what’s going on! Researchers have been trying to figure out how to make systems that recognize human activities work well, but it’s hard because every home is different and people have their own habits. A team came up with a new way to improve these systems by using “seed points” from the start. They then used a special kind of learning framework to get even better at recognizing what people are doing. This helped them understand how people live in their homes, which can be really useful! |
Keywords
» Artificial intelligence » Activity recognition » Bootstrapping
