Towards wearable sensing-based assessment of fluid intake

Abstract

Fluid intake is an important information for many health and assisted living applications. At the same time it is inherently difficult to monitor. Existing reliable solutions require augmented drinking containers, which severely limits the applicability of such systems. In this paper we investigate two key components of an unobtrusive, wearable solution that is independent of a particular drinking container or environment.We first describe a system for spotting individual instances of drinking (lifting a container to the mouth and taking a single sip) in a continuous stream of data from a wrist-worn acceleration sensor. We show that drinking motion can be detected across different drinking containers (glass, cup, large beer mug, bottle) on a large dataset (560 drinking motion instances from six users, embedded in 5.84 hours of complex natural activities). An average performance of 84% recall at 94% precision was achieved for the drinking motion spotting.Based on the events derived from drinking event spotting, we show how additional information can be obtained. Specifically, we demonstrate the recognition of container types and fluid level from upper body postures during drinking events. Nine containers and three container fluid levels were evaluated to recognize container type and fluid amounts with three users.Recognition rate for container type was 75%, and for fluid level 72%.

A practical approach for recognizing eating moments with wrist-mounted inertial sensing

“…Based on a study with six users that resulted in 560 drinking instances, the system performed remarkably well, with average of 84% recall and 94% precision [1]. In this work, the authors also attempted to recognize container type and fluid level, and achieved recognition rates over 70% in both cases.…”

A self-monitoring water bottle for tracking liquid intake

“…Therefore, an instrumented system that is able to detect each instance of water intake and use that information for tracking a user's hydration level can have enormous health significance. Amft et al [2] developed a wristband based fluid intake monitoring system. It was demonstrated that the proposed method was able to detect "Fetch" events with 84% recall and 90% precision, and "Sip" events with 84% recall and 94% precision.…”

Adaptive Activity Spotting Based on Event Rates

“…The sensors were attached to the user's wrist to monitor drinking motions using different containers. Scenario and analysis using a static spotting algorithm had been previously reported for this dataset in [7]. Here, the dataset properties are briefly summarised.…”

“…A general set of time-domain features (for dataset 1) and frequency-domain features (for dataset 2) was computed to model event data patterns, as described in [7] and [23] respectively.…”

“…Often, an averaged event rate can be estimated if the considered timeframe to sample this rate is sufficiently large. As an example, consider spotting of drinking motions in everyday activities during average days, which is relevant to prevent dehydration [7]: it is unlikely that a system user takes more than 30 sips per hour from a container. Similarly, not drinking for 3-4 hours may be unusual as well.…”