Fluid Intake Monitoring System Using a Wearable Inertial Sensor for Fluid Intake Management

iEat: automatic wearable dietary monitoring with bio-impedance sensing

Diet is an inseparable part of good health, from maintaining a healthy lifestyle for the general population to supporting the treatment of patients suffering from specific diseases. Therefore it is of great significance to be able to monitor people's dietary activity in their daily life remotely. While the traditional practices of self-reporting and retrospective analysis are often unreliable and prone to errors; sensor-based remote diet monitoring is therefore an appealing approach. In this work, we explore an atypical use of bio-impedance by leveraging its unique temporal signal patterns, which are caused by the dynamic close-loop circuit variation between a pair of electrodes due to the body-food interactions during dining activities. Specifically, we introduce iEat, a wearable impedance-sensing device for automatic dietary activity monitoring without the need for external instrumented devices such as smart utensils. By deploying a single impedance sensing channel with one electrode on each wrist, iEat can recognize food intake activities (e.g., cutting, putting food in the mouth with or without utensils, drinking, etc.) and food types from a defined category. The principle is that, at idle, iEat measures only the normal body impedance between the wrist-worn electrodes; while the subject is doing the food-intake activities, new paralleled circuits will be formed through the hand, mouth, utensils, and food, leading to consequential impedance variation. To quantitatively evaluate iEat in real-life settings, a food intake experiment was conducted in an everyday table-dining environment, including 40 meals performed by ten volunteers. With a lightweight, user-independent neural network model, iEat could detect four food intake-related activities with a macro F1 score of 86.4% and classify seven types of foods with a macro F1 score of 64.2%.

Every sip counts: Understanding hydration behaviors and user-acceptability of digital tools to promote adequate intake during early and late pregnancy

Maintaining adequate hydration over the course of pregnancy is critical for maternal and fetal health and reducing risks for adverse pregnancy outcomes (e.g., preeclampsia, low placental and amniotic fluid volume). Recent evidence suggests that women may be at risk for under-hydration in the second and third trimesters when water needs begin to increase. Scant research has examined pregnant women's knowledge of hydration recommendations, water intake behaviors, and willingness to use digital tools to promote water intake. This study aimed to: 1) describe hydration recommendation knowledge and behaviors by the overall sample and early vs late pregnancy, and 2) identify habits and barriers of using digital tools. Pregnant women (N = 137; M age = 30.9 years; M gestational age = 20.9) completed a one-time, 45-minute online survey. Descriptive statistics quantified women's knowledge of hydration recommendations, behaviors, and attitudes about utilizing digital tools to promote adequate intake, and Mann-Whitney U and chi-squared tests were used to determine group differences. Most women lacked knowledge of and were not meeting hydration recommendations (63%, 67%, respectively) and were not tracking their fluid consumption (59%). Knowledge of hydration recommendations differed by time of pregnancy, such that women in later pregnancy reported 82 ounces compared to women in early pregnancy (49 ounces). Common barriers included: forgetting to drink (47%), not feeling thirsty (47%), and increased urination (33%). Most were willing to use digital tools (69%) and believed a smart water bottle would help them achieve daily fluid recommendations (67%). These initial findings suggest that pregnant women may benefit from useful strategies to increase knowledge, decrease barriers, and maintain adequate hydration, specifically earlier in pregnancy. These findings will inform the design of a behavioral intervention incorporating smart connected water bottles, wearables for gesture detection, and behavior modification strategies to overcome barriers, promote proper hydration and examine its impact on maternal and infant health outcomes.

An Analysis of Fluid Intake Assessment Approaches for Fluid Intake Monitoring System

Monitoring fluid intake is essential to help people manage their individual fluid intake behaviors and achieve adequate hydration. Previous studies of fluid intake assessment approaches based on inertial sensors can be categorized into wrist-worn-based and smart-container-based approaches. This study aims to analyze wrist-worn-based and smart-container-based fluid intake assessment approaches using inertial sensors. The comparison of these two approaches should be analyzed according to gesture recognition and volume estimation. In addition, the influence of the fill level and sip size information on the performance is explored in this study. The accuracy of gesture recognition with postprocessing is 92.89% and 91.8% for the wrist-worn-based approach and smart-container-based approach, respectively. For volume estimation, sip-size-dependent models can achieve better performance than general SVR models for both wrist-worn-based and smart-container-based approaches. The improvement of MAPE, MAD, and RMSE can reach over 50% except MAPE for small sip sizes. The results demonstrate that the sip size information and recognition performance are important for fluid intake assessment approaches.

A Cross-Day Analysis of EMG Features, Classifiers, and Regressors for Swallowing Events Detection and Fluid Intake Volume Estimation

Dehydration is a common problem among older adults. It can seriously affect their health and wellbeing and sometimes leads to death, given the diminution of thirst sensation as we age. It is, therefore, essential to keep older adults properly hydrated by monitoring their fluid intake and estimating how much they drink. This paper aims to investigate the effect of surface electromyography (sEMG) features on the detection of drinking events and estimation of the amount of water swallowed per sip. Eleven individuals took part in the study, with data collected over two days. We investigated the best combination of a pool of twenty-six time and frequency domain sEMG features using five classifiers and seven regressors. Results revealed an average F-score over two days of 77.5±1.35% in distinguishing the drinking events from non-drinking events using three global features and 85.5±1.00% using three subject-specific features. The average volume estimation RMSE was 6.83±0.14 mL using one single global feature and 6.34±0.12 mL using a single subject-specific feature. These promising results validate and encourage the potential use of sEMG as an essential factor for monitoring and estimating the amount of fluid intake.

Drinking Gesture Detection Using Wrist-Worn IMU Sensors with Multi-Stage Temporal Convolutional Network in Free-Living Environments

Maintaining adequate hydration is important for health. Inadequate liquid intake can cause dehydration problems. Despite the increasing development of liquid intake monitoring, there are still open challenges in drinking detection under free-living conditions. This paper proposes an automatic liquid intake monitoring system comprised of wrist-worn Inertial Measurement Units (IMU s) to recognize drinking gesture in free-living environments. We build an end-to-end approach for drinking gesture detection by employing a novel multi-stage temporal convolutional network (MS-TCN). Two datasets are collected in this research, one contains 8.9 hours data from 13 participants in semi-controlled environments, the other one contains 45.2 hours data from 7 participants in free-living environments. The Leave-One-Subject-Out (LOSO) evaluation shows that this method achieves a segmental F1-score of 0.943 and 0.900 in the semi-controlled and free-living datasets, respectively. The results also indicate that our approach outperforms the convolutional neural network and long-short-term-memory network combined model (CNN-LSTM) on our datasets. The dataset used in this paper is available at https://github.com/Pituohai/drinking-gesture-dataset/. Clinical Relevance- This automatic liquid intake monitoring system can detect drinking gesture in daily life. It has the potential to be used to record the frequency of drinking water for at-risk elderly or patients in the hospital.

Microwave Hydration Monitoring: System Assessment Using Fasting Volunteers

Hydration is an important aspect of human health, as water is a critical nutrient used in many physiological processes. However, there is currently no clinical gold standard for non-invasively assessing hydration status. Recent work has suggested that permittivity in the microwave frequency range provides a physiologically meaningful metric for hydration monitoring. Using a simple time of flight technique for estimating permittivity, this study investigates microwave-based hydration assessment using a population of volunteers fasting during Ramadan. Volunteers are measured throughout the day while fasting during Ramadan and while not fasting after Ramadan. Comparing the estimated changes in permittivity to changes in weight and the time s fails to establish a clear relationship between permittivity and hydration. Assessing the subtle changes in hydration found in a population of sedentary, healthy adults proves difficult and more work is required to determine approaches suitable for tracking subtle changes in hydration over time with microwave-based hydration assessment techniques.

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

Fluid intake monitoring is an essential component in preventing dehydration and overhydration, especially for the senior population. Numerous critical health problems are associated with poor or excessive drinking such as swelling of the brain and heart failure. Real-time systems for monitoring fluid intake will not only measure the exact amount consumed by the users, but could also motivate people to maintain a healthy lifestyle by providing feedback to encourage them to hydrate regularly throughout the day. This paper reviews the most recent solutions to automatic fluid intake monitoring both commercially and in the literature. The available technologies are divided into four categories: wearables, surfaces with embedded sensors, vision- and environmental-based solutions, and smart containers. A detailed performance evaluation was carried out considering detection accuracy, usability and availability. It was observed that the most promising results came from studies that used data fusion from multiple technologies, compared to using an individual technology. The areas that need further research and the challenges for each category are discussed in detail.

Multiphase Identification Algorithm for Fall Recording Systems Using a Single Wearable Inertial Sensor

Fall-related information can help clinical professionals make diagnoses and plan fall prevention strategies. The information includes various characteristics of different fall phases, such as falling time and landing responses. To provide the information of different phases, this pilot study proposes an automatic multiphase identification algorithm for phase-aware fall recording systems. Seven young adults are recruited to perform the fall experiment. One inertial sensor is worn on the waist to collect the data of body movement, and a total of 525 trials are collected. The proposed multiphase identification algorithm combines machine learning techniques and fragment modification algorithm to identify pre-fall, free-fall, impact, resting and recovery phases in a fall process. Five machine learning techniques, including support vector machine, k-nearest neighbor (kNN), naïve Bayesian, decision tree and adaptive boosting, are applied to identify five phases. Fragment modification algorithm uses the rules to detect the fragment whose results are different from the neighbors. The proposed multiphase identification algorithm using the kNN technique achieves the best performance in 82.17% sensitivity, 85.74% precision, 73.51% Jaccard coefficient, and 90.28% accuracy. The results show that the proposed algorithm has the potential to provide automatic fine-grained fall information for clinical measurement and assessment.