A Phone-based Distributed Ambient Temperature Measurement System with An Efficient Label-free Automated Training Strategy
arxiv(2024)
摘要
Enhancing the energy efficiency of buildings significantly relies on
monitoring indoor ambient temperature. The potential limitations of
conventional temperature measurement techniques, together with the omnipresence
of smartphones, have redirected researchers' attention towards the exploration
of phone-based ambient temperature estimation technology. Nevertheless,
numerous obstacles remain to be addressed in order to achieve a practical
implementation of this technology. This study proposes a distributed
phone-based ambient temperature estimation system which enables collaboration
between multiple phones to accurately measure the ambient temperature in each
small area of an indoor space. Besides, it offers a secure, efficient, and
cost-effective training strategy to train a new estimation model for each newly
added phone, eliminating the need for manual collection of labeled data. This
innovative training strategy can yield a high-performing estimation model for a
new phone with just 5 data points, requiring only a few iterations. Meanwhile,
by crowdsourcing, our system automatically provides accurate inferred labels
for all newly collected data. We also highlight the potential of integrating
federated learning into our system to ensure privacy protection at the end of
this study. We believe this study has the potential to advance the practical
application of phone-based ambient temperature measurement, facilitating
energy-saving efforts in buildings.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要