A Phone-based Distributed Ambient Temperature Measurement System with An Efficient Label-free Automated Training Strategy

TL;DR

The paper tackles indoor ambient temperature monitoring by leveraging a distributed, phone-based system that crowdsources multi-phone estimates to infer accurate spatial temperature distributions. It integrates a Gaussian-uncertainty ambient estimator, CBTS truth inference for robust aggregation and automatic labeling, and a meta-learning framework (MAML) for rapid adaptation to new phones with only a few data points. A federated learning extension with CKKS-based encrypted gradients is explored to protect privacy while enabling collaborative training. Empirical results show crowdsourced MAE of 0.136°C, inferred-label MAE of 0.161°C, and sub-1°C errors with 5 data points under MAML, highlighting potential for energy-saving, fine-grained indoor temperature management. The approach demonstrates practical pathways for scalable, privacy-preserving ambient temperature sensing in large indoor spaces, with direct implications for distributed cooling strategies and occupancy-aware comfort optimization.

Abstract

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 methods. However, existing phone-based methods face challenges such as insufficient privacy protection, difficulty in adapting models to various phones, and hurdles in obtaining enough labeled training data. In this study, we propose a distributed phone-based ambient temperature estimation system which enables collaboration among multiple phones to accurately measure the ambient temperature in different areas of an indoor space. This system also provides an efficient, cost-effective approach with a few-shot meta-learning module and an automated label generation module. It shows that with just 5 new training data points, the temperature estimation model can adapt to a new phone and reach a good performance. Moreover, the system uses crowdsourcing to generate accurate labels for all newly collected training data, significantly reducing costs. Additionally, we highlight the potential of incorporating federated learning into our system to enhance privacy protection. We believe this study can advance the practical application of phone-based ambient temperature measurement, facilitating energy-saving efforts in buildings.

Figures (8)

• Figure 1: The schematic diagram of our distributed phone-based cooperative ambient temperature estimation system.
• Figure 2: The structure of the ambient temperature estimation model. This model takes 9 phone state features as input and outputs the temperature estimation result with the corresponding uncertainty value.
• Figure 3: Structure of the CBTS truth inference model.
• Figure 4: The flow diagram of how to build a training data set and fine-tune the source model for the new participant.
• Figure 5: The diagram which illustrates the partition of data sets and task sets.