Integrating Nearest Neighbors with Neural Network Models for Treatment Effect Estimation.

Treatment effect estimation is of high-importance for both researchers and practitioners across many scientific and industrial domains. The abundance of observational data makes them increasingly used by researchers for the estimation of causal effects. However, these data suffer from several weaknesses, leading to inaccurate causal effect estimations, if not handled properly. Therefore, several machine learning techniques have been proposed, most of them focusing on leveraging the predictive power of neural network models to attain more precise estimation of causal effects. In this work, we propose a new methodology, named Nearest Neighboring Information for Causal Inference (NNCI), for integrating valuable nearest neighboring information on neural network-based models for estimating treatment effects. The proposed NNCI methodology is applied to some of the most well established neural network-based models for treatment effect estimation with the use of observational data. Numerical experiments and analysis provide empirical and statistical evidence that the integration of NNCI with state-of-the-art neural network models leads to considerably improved treatment effect estimations on a variety of well-known challenging benchmarks.

Ultra-Processed Food vs. Fruit and Vegetable Consumption before and during the COVID-19 Pandemic among Greek and Swedish Students.

BACKGROUND: The COVID-19 pandemic has impacted children's lifestyles, including dietary behaviors. Of particular concern among these behaviors is the heightened prevalence of ultra-processed food (UPF) consumption, which has been linked to the development of obesity and related non-communicable diseases. The present study examines the changes in (1) UPF and (2) vegetable and/or fruit consumption among school-aged children in Greece and Sweden before and during the COVID-19 pandemic. METHODS: The analyzed dataset consisted of main meal pictures (breakfast, lunch, and dinner) captured by 226 Greek students (94 before the pandemic and 132 during the pandemic) and 421 Swedish students (293 before and 128 during the pandemic), aged 9-18, who voluntarily reported their meals using a mobile application. The meal pictures were collected over four-month periods over two consecutive years; namely, between the 20th of August and the 20th of December in 2019 (before the COVID-19 outbreak) and the same period in 2020 (during the COVID-19 outbreak). The collected pictures were annotated manually by a trained nutritionist. A chi-square test was performed to evaluate the differences in proportions before versus during the pandemic. RESULTS: In total, 10,770 pictures were collected, including 6474 pictures from before the pandemic and 4296 pictures collected during the pandemic. Out of those, 86 pictures were excluded due to poor image quality, and 10,684 pictures were included in the final analyses (4267 pictures from Greece and 6417 pictures from Sweden). The proportion of UPF significantly decreased during vs. before the pandemic in both populations (50% vs. 46%, p = 0.010 in Greece, and 71% vs. 66%, p < 0.001 in Sweden), while the proportion of vegetables and/or fruits significantly increased in both cases (28% vs. 35%, p < 0.001 in Greece, and 38% vs. 42%, p = 0.019 in Sweden). There was a proportional increase in meal pictures containing UPF among boys in both countries. In Greece, both genders showed an increase in vegetables and/or fruits, whereas, in Sweden, the increase in fruit and/or vegetable consumption was solely observed among boys. CONCLUSIONS: The proportion of UPF in the Greek and Swedish students' main meals decreased during the COVID-19 pandemic vs. before the pandemic, while the proportion of main meals with vegetables and/or fruits increased.

Toward Systems Models for Obesity Prevention: A Big Role for Big Data.

The relation among the various causal factors of obesity is not well understood, and there remains a lack of viable data to advance integrated, systems models of its etiology. The collection of big data has begun to allow the exploration of causal associations between behavior, built environment, and obesity-relevant health outcomes. Here, the traditional epidemiologic and emerging big data approaches used in obesity research are compared, describing the research questions, needs, and outcomes of 3 broad research domains: eating behavior, social food environments, and the built environment. Taking tangible steps at the intersection of these domains, the recent European Union project "BigO: Big data against childhood obesity" used a mobile health tool to link objective measurements of health, physical activity, and the built environment. BigO provided learning on the limitations of big data, such as privacy concerns, study sampling, and the balancing of epidemiologic domain expertise with the required technical expertise. Adopting big data approaches will facilitate the exploitation of data concerning obesity-relevant behaviors of a greater variety, which are also processed at speed, facilitated by mobile-based data collection and monitoring systems, citizen science, and artificial intelligence. These approaches will allow the field to expand from causal inference to more complex, systems-level predictive models, stimulating ambitious and effective policy interventions.

Intake monitoring in free-living conditions: Overview and lessons we have learned.

The progress in artificial intelligence and machine learning algorithms over the past decade has enabled the development of new methods for the objective measurement of eating, including both the measurement of eating episodes as well as the measurement of in-meal eating behavior. These allow the study of eating behavior outside the laboratory in free-living conditions, without the need for video recordings and laborious manual annotations. In this paper, we present a high-level overview of our recent work on intake monitoring using a smartwatch, as well as methods using an in-ear microphone. We also present evaluation results of these methods in challenging, real-world datasets. Furthermore, we discuss use-cases of such intake monitoring tools for advancing research in eating behavior, for improving dietary monitoring, as well as for developing evidence-based health policies. Our goal is to inform researchers and users of intake monitoring methods regarding (i) the development of new methods based on commercially available devices, (ii) what to expect in terms of effectiveness, and (iii) how these methods can be used in research as well as in practical applications.

Self-Supervised Feature Learning of 1D Convolutional Neural Networks with Contrastive Loss for Eating Detection Using an In-Ear Microphone.

The importance of automated and objective monitoring of dietary behavior is becoming increasingly accepted. The advancements in sensor technology along with recent achievements in machine-learning-based signal-processing algorithms have enabled the development of dietary monitoring solutions that yield highly accurate results. A common bottleneck for developing and training machine learning algorithms is obtaining labeled data for training supervised algorithms, and in particular ground truth annotations. Manual ground truth annotation is laborious, cumbersome, can sometimes introduce errors, and is sometimes impossible in free-living data collection. As a result, there is a need to decrease the labeled data required for training. Additionally, unlabeled data, gathered in-the-wild from existing wearables (such as Bluetooth earbuds) can be used to train and fine-tune eating-detection models. In this work, we focus on training a feature extractor for audio signals captured by an in-ear microphone for the task of eating detection in a self-supervised way. We base our approach on the SimCLR method for image classification, proposed by Chen et al. from the domain of computer vision. Results are promising as our self-supervised method achieves similar results to supervised training alternatives, and its overall effectiveness is comparable to current state-of-the-art methods. Code is available at https://github.com/mug-auth/ssl-chewing.

Exploring Associations Between Children's Obesogenic Behaviors and the Local Environment Using Big Data: Development and Evaluation of the Obesity Prevention Dashboard.

BACKGROUND: Obesity is a major public health problem globally and in Europe. The prevalence of childhood obesity is also soaring. Several parameters of the living environment are contributing to this increase, such as the density of fast food retailers, and thus, preventive health policies against childhood obesity must focus on the environment to which children are exposed. Currently, there are no systems in place to objectively measure the effect of living environment parameters on obesogenic behaviors and obesity. The H2020 project "BigO: Big Data Against Childhood Obesity" aims to tackle childhood obesity by creating new sources of evidence based on big data. OBJECTIVE: This paper introduces the Obesity Prevention dashboard (OPdashboard), implemented in the context of BigO, which offers an interactive data platform for the exploration of objective obesity-related behaviors and local environments based on the data recorded using the BigO mHealth (mobile health) app. METHODS: The OPdashboard, which can be accessed on the web, allows for (1) the real-time monitoring of children's obesogenic behaviors in a city area, (2) the extraction of associations between these behaviors and the local environment, and (3) the evaluation of interventions over time. More than 3700 children from 33 schools and 2 clinics in 5 European cities have been monitored using a custom-made mobile app created to extract behavioral patterns by capturing accelerometer and geolocation data. Online databases were assessed in order to obtain a description of the environment. The dashboard's functionality was evaluated during a focus group discussion with public health experts. RESULTS: The preliminary association outcomes in 2 European cities, namely Thessaloniki, Greece, and Stockholm, Sweden, indicated a correlation between children's eating and physical activity behaviors and the availability of food-related places or sports facilities close to schools. In addition, the OPdashboard was used to assess changes to children's physical activity levels as a result of the health policies implemented to decelerate the COVID-19 outbreak. The preliminary outcomes of the analysis revealed that in urban areas the decrease in physical activity was statistically significant, while a slight increase was observed in the suburbs. These findings indicate the importance of the availability of open spaces for behavioral change in children. Discussions with public health experts outlined the dashboard's potential to aid in a better understanding of the interplay between children's obesogenic behaviors and the environment, and improvements were suggested. CONCLUSIONS: Our analyses serve as an initial investigation using the OPdashboard. Additional factors must be incorporated in order to optimize its use and obtain a clearer understanding of the results. The unique big data that are available through the OPdashboard can lead to the implementation of models that are able to predict population behavior. The OPdashboard can be considered as a tool that will increase our understanding of the underlying factors in childhood obesity and inform the design of regional interventions both for prevention and treatment.

Fast Eating Is Associated with Increased BMI among High-School Students.

Fast self-reported eating rate (SRER) has been associated with increased adiposity in children and adults. No studies have been conducted among high-school students, and SRER has not been validated vs. objective eating rate (OBER) in such populations. The objectives were to investigate (among high-school student populations) the association between OBER and BMI z-scores (BMIz), the validity of SRER vs. OBER, and potential differences in BMIz between SRER categories. Three studies were conducted. Study 1 included 116 Swedish students (mean ± SD age: 16.5 ± 0.8, 59% females) who were eating school lunch. Food intake and meal duration were objectively recorded, and OBER was calculated. Additionally, students provided SRER. Study 2 included students (n = 50, mean ± SD age: 16.7 ± 0.6, 58% females) from Study 1 who ate another objectively recorded school lunch. Study 3 included 1832 high-school students (mean ± SD age: 15.8 ± 0.9, 51% females) from Sweden (n = 748) and Greece (n = 1084) who provided SRER. In Study 1, students with BMIz ≥ 0 had faster OBER vs. students with BMIz < 0 (mean difference: +7.7 g/min or +27%, p = 0.012), while students with fast SRER had higher OBER vs. students with slow SRER (mean difference: +13.7 g/min or +56%, p = 0.001). However, there was "minimal" agreement between SRER and OBER categories (κ = 0.31, p < 0.001). In Study 2, OBER during lunch 1 had a "large" correlation with OBER during lunch 2 (r = 0.75, p < 0.001). In Study 3, fast SRER students had higher BMIz vs. slow SRER students (mean difference: 0.37, p < 0.001). Similar observations were found among both Swedish and Greek students. For the first time in high-school students, we confirm the association between fast eating and increased adiposity. Our validation analysis suggests that SRER could be used as a proxy for OBER in studies with large sample sizes on a group level. With smaller samples, OBER should be used instead. To assess eating rate on an individual level, OBER can be used while SRER should be avoided.

A Data Driven End-to-End Approach for In-the-Wild Monitoring of Eating Behavior Using Smartwatches.

The increased worldwide prevalence of obesity has sparked the interest of the scientific community towards tools that objectively and automatically monitor eating behavior. Despite the study of obesity being in the spotlight, such tools can also be used to study eating disorders (e.g. anorexia nervosa) or provide a personalized monitoring platform for patients or athletes. This paper presents a complete framework towards the automated i) modeling of in-meal eating behavior and ii) temporal localization of meals, from raw inertial data collected in-the-wild using commercially available smartwatches. Initially, we present an end-to-end Neural Network which detects food intake events (i.e. bites). The proposed network uses both convolutional and recurrent layers that are trained simultaneously. Subsequently, we show how the distribution of the detected bites throughout the day can be used to estimate the start and end points of meals, using signal processing algorithms. We perform extensive evaluation on each framework part individually. Leave-one-subject-out (LOSO) evaluation shows that our bite detection approach outperforms four state-of-the-art algorithms towards the detection of bites during the course of a meal (0.923 F1 score). Furthermore, LOSO and held-out set experiments regarding the estimation of meal start/end points reveal that the proposed approach outperforms a relevant approach found in the literature (Jaccard Index of 0.820 and 0.821 for the LOSO and held-out experiments, respectively). Experiments are performed using our publicly available FIC and the newly introduced FreeFIC datasets.

Collecting big behavioral data for measuring behavior against obesity.

Obesity is currently affecting very large portions of the global population. Effective prevention and treatment starts at the early age and requires objective knowledge of population-level behavior on the region/neighborhood scale. To this end, we present a system for extracting and collecting behavioral information on the individual-level objectively and automatically. The behavioral information is related to physical activity, types of visited places, and transportation mode used between them. The system employs indicator-extraction algorithms from the literature which we evaluate on publicly available datasets. The system has been developed and integrated in the context of the EU-funded BigO project that aims at preventing obesity in young populations.

BigO: A public health decision support system for measuring obesogenic behaviors of children in relation to their local environment.

Obesity is a complex disease and its prevalence depends on multiple factors related to the local socioeconomic, cultural and urban context of individuals. Many obesity prevention strategies and policies, however, are horizontal measures that do not depend on context-specific evidence. In this paper we present an overview of BigO (http://bigoprogram.eu), a system designed to collect objective behavioral data from children and adolescent populations as well as their environment in order to support public health authorities in formulating effective, context-specific policies and interventions addressing childhood obesity. We present an overview of the data acquisition, indicator extraction, data exploration and analysis components of the BigO system, as well as an account of its preliminary pilot application in 33 schools and 2 clinics in four European countries, involving over 4,200 participants.

Inferring the Spatial Distribution of Physical Activity in Children Population from Characteristics of the Environment.

Obesity affects a rising percentage of the children and adolescent population, contributing to decreased quality of life and increased risk for comorbidities. Although the major causes of obesity are known, the obesogenic behaviors manifest as a result of complex interactions of the individual with the living environment. For this reason, addressing childhood obesity remains a challenging problem for public health authorities. The BigO project (https://bigoprogram.eu) relies on large-scale behavioral and environmental data collection to create tools that support policy making and intervention design. In this work, we propose a novel analysis approach for modeling the expected population behavior as a function of the local environment. We experimentally evaluate this approach in predicting the expected physical activity level in small geographic regions using urban environment characteristics. Experiments on data collected from 156 children and adolescents verify the potential of the proposed approach. Specifically, we train models that predict the physical activity level in a region, achieving 81% leave-one-out accuracy. In addition, we exploit the model predictions to automatically visualize heatmaps of the expected population behavior in areas of interest, from which we draw useful insights. Overall, the predictive models and the automatic heatmaps are promising tools in gaining direct perception for the spatial distribution of the population's behavior, with potential uses by public health authorities.

Formative Evaluation of a Smartphone App for Monitoring Daily Meal Distribution and Food Selection in Adolescents: Acceptability and Usability Study.

BACKGROUND: Obesity interventions face the problem of weight regain after treatment as a result of low compliance. Mobile health (mHealth) technologies could potentially increase compliance and aid both health care providers and patients. OBJECTIVE: This study aimed to evaluate the acceptability and usability and define system constraints of an mHealth system used to monitor dietary habits of adolescents in real life, as a first step in the development of a self-monitoring and lifestyle management system against adolescent obesity. METHODS: We recruited 26 students from a high school in Stockholm, Sweden. After a 30-minute information meeting and 5-minute individual instruction on how to use an mHealth system (smartphone with app and two external sensors), participants used it for 2-3 weeks to objectively collect dietary habits. The app and sensors were used by the participants, without supervision, to record as many main meals and snacks as possible in real life. Feasibility was assessed following the "mHealth evidence reporting and assessment checklist," and usability was assessed by questionnaires. Compliance was estimated based on system use, where a registration frequency of 3 main meals (breakfast, lunch, and dinner) per day for the period of the experiment, constituted 100% compliance. RESULTS: Participants included in the analysis had a mean age of 16.8 years (SD 0.7 years) and BMI of 21.9 kg/m2 (SD 4.1 kg/m2). Due to deviations from study instructions, 2 participants were excluded from the analysis. During the study, 6 participants required additional information on system use. The system received a 'Good' grade (77.1 of 100 points) on the System Usability Scale, with most participants reporting that they were comfortable using the smartphone app. Participants expressed a willingness to use the app mostly at home, but also at school; most of their improvement suggestions concerned design choices for the app. Of all main meals, the registration frequency increased from 70% the first week to 76% the second week. Participants reported that 40% of the registered meals were home-prepared, while 34% of the reported drinks contained sugar. On average, breakfasts took place at 8:30 AM (from 5:00 AM to 2:00 PM), lunches took place at 12:15 PM (from 10:15 AM to 6:15 PM), and dinners took place at 7:30 PM (from 3:00 PM to 11:45 PM). When comparing meal occurrence during weekdays vs weekends, breakfasts and lunches were eaten 3 hours later during weekends, while dinner timing was unaffected. CONCLUSIONS: From an infrastructural and functional perspective, system use was feasible in the current context. The smartphone app appears to have high acceptability and usability in high school students, which are the intended end-users. The system appears promising as a relatively low-effort method to provide real-life dietary habit measurements associated with overweight and obesity risk.

Novel e-Health Applications for the Management of Cardiometabolic Risk Factors in Children and Adolescents in Greece.

Obesity in childhood and adolescence represents a major health problem. Novel e-Health technologies have been developed in order to provide a comprehensive and personalized plan of action for the prevention and management of overweight and obesity in childhood and adolescence. We used information and communication technologies to develop a "National Registry for the Prevention and Management of Overweight and Obesity" in order to register online children and adolescents nationwide, and to guide pediatricians and general practitioners regarding the management of overweight or obese subjects. Furthermore, intelligent multi-level information systems and specialized artificial intelligence algorithms are being developed with a view to offering precision and personalized medical management to obese or overweight subjects. Moreover, the Big Data against Childhood Obesity platform records behavioral data objectively by using inertial sensors and Global Positioning System (GPS) and combines them with data of the environment, in order to assess the full contextual framework that is associated with increased body mass index (BMI). Finally, a computerized decision-support tool was developed to assist pediatric health care professionals in delivering personalized nutrition and lifestyle optimization advice to overweight or obese children and their families. These e-Health applications are expected to play an important role in the management of overweight and obesity in childhood and adolescence.

Predicting Real-Life Eating Behaviours Using Single School Lunches in Adolescents.

Large portion sizes and a high eating rate are associated with high energy intake and obesity. Most individuals maintain their food intake weight (g) and eating rate (g/min) rank in relation to their peers, despite food and environmental manipulations. Single meal measures may enable identification of "large portion eaters" and "fast eaters," finding individuals at risk of developing obesity. The aim of this study was to predict real-life food intake weight and eating rate based on one school lunch. Twenty-four high-school students with a mean (±SD) age of 16.8 yr (±0.7) and body mass index of 21.9 (±4.1) were recruited, using no exclusion criteria. Food intake weight and eating rate was first self-rated ("Less," "Average" or "More than peers"), then objectively recorded during one school lunch (absolute weight of consumed food in grams). Afterwards, subjects recorded as many main meals (breakfasts, lunches and dinners) as possible in real-life for a period of at least two weeks, using a Bluetooth connected weight scale and a smartphone application. On average participants recorded 18.9 (7.3) meals during the study. Real-life food intake weight was 327.4 g (±110.6), which was significantly lower (p = 0.027) than the single school lunch, at 367.4 g (±167.2). When the intra-class correlation of food weight intake between the objectively recorded real-life and school lunch meals was compared, the correlation was excellent (R = 0.91). Real-life eating rate was 33.5 g/min (±14.8), which was significantly higher (p = 0.010) than the single school lunch, at 27.7 g/min (±13.3). The intra-class correlation of the recorded eating rate between real-life and school lunch meals was very large (R = 0.74). The participants' recorded food intake weights and eating rates were divided into terciles and compared between school lunches and real-life, with moderate or higher agreement (κ = 0.75 and κ = 0.54, respectively). In contrast, almost no agreement was observed between self-rated and real-life recorded rankings of food intake weight and eating rate (κ = 0.09 and κ = 0.08, respectively). The current study provides evidence that both food intake weight and eating rates per meal vary considerably in real-life per individual. However, based on these behaviours, most students can be correctly classified in regard to their peers based on single school lunches. In contrast, self-reported food intake weight and eating rate are poor predictors of real-life measures. Finally, based on the recorded individual variability of real-life food intake weight and eating rate, it is not advised to rank individuals based on single recordings collected in real-life settings.

Modeling Wrist Micromovements to Measure In-Meal Eating Behavior From Inertial Sensor Data.

Overweight and obesity are both associated with in-meal eating parameters such as eating speed. Recently, the plethora of available wearable devices in the market ignited the interest of both the scientific community and the industry toward unobtrusive solutions for eating behavior monitoring. In this paper, we present an algorithm for automatically detecting the in-meal food intake cycles using the inertial signals (acceleration and orientation velocity) from an off-the-shelf smartwatch. We use five specific wrist micromovements to model the series of actions leading to and following an intake event (i.e., bite). Food intake detection is performed in two steps. In the first step, we process windows of raw sensor streams and estimate their micromovement probability distributions by means of a convolutional neural network. In the second step, we use a long short-term memory network to capture the temporal evolution and classify sequences of windows as food intake cycles. Evaluation is performed using a challenging dataset of 21 meals from 12 subjects. In our experiments, we compare the performance of our algorithm against three state-of-the-art approaches, where our approach achieves the highest F1 detection score (0.913 in the leave-one-subject-out experiment). The dataset used in the experiments is available at https://mug.ee.auth.gr/intake-cycle-detection/.

Behaviour Profiles for Evidence-based Policies Against Obesity.

Obesity is a preventable disease that affects the health of a significant population percentage, reduces the life expectancy and encumbers the health care systems. The obesity epidemic is not caused by isolated factors, but it is the result of multiple behavioural patterns and complex interactions with the living environment. Therefore, in-depth understanding of the population behaviour is essential in order to create successful policies against obesity prevalence. To this end, the BigO system facilitates the collection, processing and modelling of behavioural data at population level to provide evidence for effective policy and interventions design. In this paper, we introduce the behaviour profiles mechanism of BigO that produces comprehensive models for the behavioural patterns of individuals, while maintaining high levels of privacy protection. We give examples for the proposed mechanism from real world data and we discuss usages for supporting various types of evidence-based policy design.

Detecting Meals In the Wild Using the Inertial Data of a Typical Smartwatch.

Automated and objective monitoring of eating behavior has received the attention of both the research community and the industry over the past few years. In this paper we present a method for automatically detecting meals in free living conditions, using the inertial data (acceleration and orientation velocity) from commercially available smartwatches. The proposed method operates in two steps. In the first step we process the raw inertial signals using an End-to-End Neural Network with the purpose of detecting the bite events throughout the recording. During the next step, we process the resulting bite detections using signal processing algorithms to obtain the final meal start and end timestamp estimates. Evaluation results obtained from our Leave One Subject Out experiments using our publicly available FIC and FreeFIC datasets, exhibit encouraging results by achieving an F1/Average Jaccard Index of 0.894/0.804.

Assessment of In-Meal Eating Behaviour using Fuzzy SVM.

Certain patterns of eating behaviour during meal have been identified as risk factors for long-term abnormal eating development in healthy individuals and, eventually, can affect the body weight. To detect early signs of problematic eating behaviour, this paper proposes a novel method for building behaviour assessment models. The goal of the models is to predict whether the in-meal eating behaviour resembles patterns associated with obesity, eating disorders, or low-risk behaviours. The models are trained using meals recorded with a plate scale from a reference population and labels annotated by a domain expert. In addition, the domain expert assigned scores that characterise the degree of any exhibited abnormal patterns. To improve model effectiveness, we use the domain expert's scores to create training error regularisation weights that alter the importance of each training instance for its class during model training. The behaviour assessment models are based on the SVM algorithm and the fuzzy SVM algorithm for their instance-weighted variation. Experiments conducted on meals recorded from 120 individuals show that: (a) the proposed approach can produce effective models for eating behaviour classification (for individuals), or for ranking (for populations); and (b) the instance-weighted fuzzy SVM models achieve significant performance improvements, compared to the non-weighted, standard SVM models.

Automatic Analysis of Food Intake and Meal Microstructure Based on Continuous Weight Measurements.

The structure of the cumulative food intake (CFI) curve has been associated with obesity and eating disorders. Scales that record the weight loss of a plate from which a subject eats food are used for capturing this curve; however, their measurements are contaminated by additive noise and are distorted by certain types of artifacts. This paper presents an algorithm for automatically processing continuous in-meal weight measurements in order to extract the clean CFI curve and in-meal eating indicators, such as total food intake and food intake rate. The algorithm relies on the representation of the weight-time series by a string of symbols that correspond to events such as bites or food additions. A context-free grammar is next used to model a meal as a sequence of such events. The selection of the most likely parse tree is finally used to determine the predicted eating sequence. The algorithm is evaluated on a dataset of 113 meals collected using the Mandometer, a scale that continuously samples plate weight during eating. We evaluate the effectiveness for seven indicators and for bite-instance detection. We compare our approach with three state-of-the-art algorithms, and achieve the lowest error rates for most indicators (24 g for total meal weight). The proposed algorithm extracts the parameters of the CFI curve automatically, eliminating the need for manual data processing, and thus facilitating large-scale studies of eating behavior.

End-to-end Learning for Measuring in-meal Eating Behavior from a Smartwatch.

In this paper, we propose an end-to-end neural network (NN) architecture for detecting in-meal eating events (i.e., bites), using only a commercially available smartwatch. Our method combines convolutional and recurrent networks and is able to simultaneously learn intermediate data representations related to hand movements, as well as sequences of these movements that appear during eating. A promising F-score of 0.884 is achieved for detecting bites on a publicly available dataset with 10 subjects.