Summary of Active Learning For Wban-based Health Monitoring, by Cho-chun Chiu et al.
Active Learning for WBAN-based Health Monitoring
by Cho-Chun Chiu, Tuan Nguyen, Ting He, Shiqiang Wang, Beom-Su Kim, Ki-Il Kim
First submitted to arxiv on: 5 Aug 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Networking and Internet Architecture (cs.NI)
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 This paper proposes a novel active learning method for training machine learning models for health monitoring in wireless body area networks (WBANs). The authors address two key challenges: collecting unlabeled samples incurs non-trivial costs, and obtaining labels from healthcare professionals cannot keep pace with data collection. They introduce a two-phased approach, comprising online coreset construction and offline labeling to train the target model. The selected samples guarantee error bounds in approximating the full dataset’s loss function. Experiments on real health monitoring data demonstrate that this solution significantly reduces data curation costs without compromising model quality. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary This paper is about a new way to learn machine learning models for tracking people’s health using tiny sensors on their bodies. It’s hard to collect and label these samples because it takes time and resources. The researchers came up with a two-step plan: first, they pick the most important samples based on how well a simple model does on them; then, they use those selected samples to train the final model. This approach makes sure that the training process is accurate and efficient. |
Keywords
» Artificial intelligence » Active learning » Loss function » Machine learning » Tracking
