Summary of A Phone-based Distributed Ambient Temperature Measurement System with An Efficient Label-free Automated Training Strategy, by Dayin Chen et al.
A Phone-based Distributed Ambient Temperature Measurement System with An Efficient Label-free Automated Training Strategy
by Dayin Chen, Xiaodan Shi, Haoran Zhang, Xuan Song, Dongxiao Zhang, Yuntian Chen, Jinyue Yan
First submitted to arxiv on: 16 Apr 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 distributed phone-based ambient temperature estimation system is proposed for enhancing energy efficiency in buildings. The system leverages multiple phones to measure temperature in different areas, overcoming limitations of existing methods. It integrates a few-shot meta-learning module and automated label generation module, allowing adaptation to new phones with just 5 training data points. The system also incorporates crowdsourcing for accurate labeling, reducing costs. Additionally, the potential for federated learning is highlighted for enhanced privacy protection. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary A new way to measure temperature inside buildings using smartphones is being developed. Currently, phone-based methods have some problems like not protecting people’s privacy and not working well on different phones. The researchers created a system where many phones work together to take accurate temperature readings in different areas of the building. This system uses only a few pieces of training data to adapt to new phones, making it efficient and cost-effective. It also uses crowdsourcing to get more accurate labels, which helps reduce costs. Overall, this study can help make phone-based temperature measurement more practical and useful for saving energy in buildings. |
Keywords
» Artificial intelligence » Federated learning » Few shot » Meta learning » Temperature
