Semi-Supervised Learning Using Sparsely Labelled Sip Events for Online Hydration Tracking Systems

This paper presents a lightweight on-device liquid consumption tracking system based on a semi-supervised learning paradigm. The online learning framework caters to scenarios where a hydration tracking bottle/device has no prior knowledge of a user's consumption gesture patterns. The proposed iterative semi-supervised learning (ISSL) framework uses sparsely labelled user gesture events acquired from the IMU sensors installed on a bottle, such that it can learn to differentiate between sip and non-sip gestures by specific individuals. Two different strategies, namely, population-based, and distance-based, are employed to achieve the desired clustering performance. A comparative study between these strategies has been presented in terms of clustering accuracies for classifying sip and non-sip gestures. The proposed architecture is shown to be lightweight in terms of computation complexity and memory usage of the bottle-embedded hardware. The trade-off between classification accuracy and computation complexity is analyzed for different algorithmic hyper-parameters and it is shown how to manage this trade-off. Extensive experimentation and simulation study has been conducted for multiple users' drinking patterns to validate the proposed learning paradigm.

I. Introduction

Inadequate hydration can lead to many health conditions including kidney malfunction, headaches, dizziness, urinary tract infection, etc. An automated system of hydration estimation via sip detection by a smart bottle can be of enormous help for such populations with hydration deficiencies.