A Container-Attachable Inertial Sensor for Real-Time Hydration Tracking

Abstract

Various sensors have been proposed to address the negative health ramifications of inadequate fluid consumption. Amongst these solutions, motion-based sensors estimate fluid intake using the characteristics of drinking kinematics. This sensing approach is complicated due to the mutual influence of both the drink volume and the current fill level on the resulting motion pattern, along with differences in biomechanics across individuals. While motion-based strategies are a promising approach due to the proliferation of inertial sensors, previous studies have been characterized by limited accuracy and substantial variability in performance across subjects. This research seeks to address these limitations for a container-attachable triaxial accelerometer sensor. Drink volume is computed using support vector machine regression models with hand-engineered features describing the container’s estimated inclination. Results are presented for a large-scale data collection consisting of 1908 drinks consumed from a refillable bottle by 84 individuals. Per-drink mean absolute percentage error is reduced by 11.05% versus previous state-of-the-art results for a single wrist-wearable inertial measurement unit (IMU) sensor assessed using a similar experimental protocol. Estimates of aggregate consumption are also improved versus previously reported results for an attachable sensor architecture. An alternative tracking approach using the fill level from which a drink is consumed is also explored herein. Fill level regression models are shown to exhibit improved accuracy and reduced inter-subject variability versus volume estimators. A technique for segmenting the entire drink motion sequence into transport and sip phases is also assessed, along with a multi-target framework for addressing the known interdependence of volume and fill level on the resulting drink motion signature.

Responses to external repeated perturbations vary with time intervals

“…The unit was attached at 5% of the total height below the knee joint. Acceleration values were used to calculate the angle of the lower body with regard to the vertical line, which was regarded as an estimate of the ankle angle, using the following equation (Griffith et al, 2019;Kim & Hwang, 2018):…”

Responses to external repeated perturbations vary with time intervals

“…The unit was attached at 5% of the total height below the knee joint. Acceleration values were used to calculate the angle of the lower body with regard to the vertical line, which was regarded as an estimate of the ankle angle, using the following equation [14], [27]:…”

Fluid Intake Monitoring Systems for the Elderly: A Review of the Literature

“…They found that using kNN to classify drink events achieved F1-score of 89.92% for detecting a drink event within a window and 85.88% to detect the exact frame in 11 participants. Dong et al and Griffith et al placed an elastic band with an accelerometer around a water bottle to estimate volume intake and fill ratio (fill level as a percentage of the height of the container), shown in the schematic in Figure 4 a [ 120 , 121 , 122 , 123 , 124 ]. They obtained an overall MAPE of greater than 7.64% for the fill ratio and 19.49% per sip using machine learning [ 120 , 121 , 122 ].…”

“… Schematic diagram of various sensor layouts for each smart container category, namely ( a ) inertial [ 120 , 121 , 122 , 123 , 124 ], ( b ) load and pressure [ 125 ], ( c ) capacitive [ 126 ], ( d ) conductive [ 127 ], ( e ) Wi-Fi [ 128 ], ( f ) vibration [ 129 ], ( g ) acoustic [ 130 ], ( h ) and other level sensor [ 131 ]. …”