Liquid Sensing Using WiFi Signals

TL;DR

LiquidSense is a low-cost WiFi-based system that accurately detects liquid levels in containers using resonance-induced WiFi signal phase changes, suitable for smart home and healthcare applications.

Contribution

This work introduces LiquidSense, a novel liquid-level sensing system leveraging WiFi signals and a low-cost transducer for high accuracy and broad applicability.

Findings

Achieves 97% accuracy in continuous liquid level prediction

Attains an F-score of 0.968 for discrete liquid level classification

Works effectively in non-line-of-sight scenarios within home environments

Abstract

The popularity of Internet-of-Things (IoT) has provided us with unprecedented opportunities to enable a variety of emerging services in a smart home environment. Among those services, sensing the liquid level in a container is critical to building many smart home and mobile healthcare applications that improve the quality of life. This paper presents LiquidSense, a liquid-level sensing system that is low-cost, high accuracy, widely applicable to different daily liquids and containers, and can be easily integrated with existing smart home networks. LiquidSense uses an existing home WiFi network and a low-cost transducer that attached to the container to sense the resonance of the container for liquid level detection. In particular, our system mounts a low-cost transducer on the surface of the container and emits a well-designed chirp signal to make the container resonant, which introduces subtle changes to the home WiFi signals. By analyzing the subtle phase changes of the WiFi signals, LiquidSense extracts the resonance frequency as a feature for liquid level detection. Our system constructs prediction models for both continuous and discrete predictions using curve fitting and SVM respectively. We evaluate LiquidSense in home environments with containers of three different materials and six types of liquids. Results show that LiquidSense achieves an overall accuracy of 97% for continuous prediction and an overall F-score of 0.968 for discrete prediction. Results also show that our system has a large coverage in a home environment and works well under non-line-of-sight (NLOS) scenarios.