Objective monitoring of food intake and ingestive behavior in a free-living environment remains an open problem that has significant implications in study and treatment of obesity and eating disorders. In this paper, a novel wearable sensor system (automatic ingestion monitor, AIM) is presented for objective monitoring of ingestive behavior in free living. The proposed device integrates three sensor modalities that wirelessly interface to a smartphone: a jaw motion sensor, a hand gesture sensor, and an accelerometer. A novel sensor fusion and pattern recognition method was developed for subject-independent food intake recognition. The device and the methodology were validated with data collected from 12 subjects wearing AIM during the course of 24 h in which both the daily activities and the food intake of the subjects were not restricted in any way. Results showed that the system was able to detect food intake with an average accuracy of 89.8%, which suggests that AIM can potentially be used as an instrument to monitor ingestive behavior in free-living individuals.

Presence of speech and motion artifacts has been shown to impact the performance of wearable sensor systems used for automatic detection of food intake. This work presents a novel wearable device which can detect food intake even when the user is physically active and/or talking. The device consists of a piezoelectric strain sensor placed on the temporalis muscle, an accelerometer, and a data acquisition module connected to the temple of eyeglasses. Data from 10 participants was collected while they performed activities including quiet sitting, talking, eating while sitting, eating while walking, and walking. Piezoelectric strain sensor and accelerometer signals were divided into non-overlapping epochs of 3 s; four features were computed for each signal. To differentiate between eating and not eating, as well as between sedentary postures and physical activity, two multiclass classification approaches are presented. The first approach used a single classifier with sensor fusion and the second approach used two-stage classification. The best results were achieved when two separate linear support vector machine (SVM) classifiers were trained for food intake and activity detection, and their results were combined using a decision tree (two-stage classification) to determine the final class. This approach resulted in an average F1-score of 99.85% and area under the curve (AUC) of 0.99 for multiclass classification. With its ability to differentiate between food intake and activity level, this device may potentially be used for tracking both energy intake and energy expenditure.

Many methods for monitoring diet and food intake rely on subjects self-reporting their daily intake. These methods are subjective, potentially inaccurate and need to be replaced by more accurate and objective methods. This paper presents a novel approach that uses an electroglottograph (EGG) device for an objective and automatic detection of food intake. Thirty subjects participated in a four-visit experiment involving the consumption of meals with self-selected content. Variations in the electrical impedance across the larynx caused by the passage of food during swallowing were captured by the EGG device. To compare performance of the proposed method with a well-established acoustical method, a throat microphone was used for monitoring swallowing sounds. Both signals were segmented into non-overlapping epochs of 30 s and processed to extract wavelet features. Subject-independent classifiers were trained, using artificial neural networks, to identify periods of food intake from the wavelet features. Results from leave-one-out cross validation showed an average per-epoch classification accuracy of 90.1% for the EGG-based method and 83.1% for the acoustic-based method, demonstrating the feasibility of using an EGG for food intake detection.

The goal of this paper is to evaluate the feasibility of using a 3-axis accelerometer attached to the frame of eyeglasses for automatic detection of food intake. A 3-D acceleration sensor was attached to the temple of the regular eyeglasses. Ten participants wore the device in two visits (first, laboratory; second, free-living) on different days, reporting the food intake episodes using a pushbutton. Hold-one-out procedure was used to test the algorithm for food intake detection. The accelerometer signal was split into epochs of varying durations (3, 5, 10 15, 20, 25, and 30 s); 152 time and frequency domain features were computed for each epoch. A two-stage procedure was used for finding the best feature set suitable for classification. The first stage used minimum redundancy and maximum relevance to get the 30 top-ranked features and the second stage used forward feature selection along with a k-nearest neighbor classifier to get the optimum feature set for each hold-one-out set. The best average F1-score combined from laboratory and free-living experiments was 87.9 +/- 13.8% (Mean±Standard Deviation) for 20 s epochs; and 84.7 +/- 7.95% for the shortest epoch of 3 s. The results suggest that accelerometer may provide a compelling alternative to other sensor modalities, as the proposed sensor does not require direct attachment to the body and, therefore, significantly improves user comfort and social acceptability of the food intake monitoring system.

Research suggests that there might be a relationship between chew count as well as chewing rate and energy intake. Chewing has been used in wearable sensor systems for the automatic detection of food intake, but little work has been reported on the automatic measurement of chew count or chewing rate. This work presents a method for the automatic quantification of chewing episodes captured by a piezoelectric sensor system. The proposed method was tested on 120 meals from 30 participants using two approaches. In a semi-automatic approach, histogram-based peak detection was used to count the number of chews in manually annotated chewing segments, resulting in a mean absolute error of 10.40 $\%\pm$ 7.03%. In a fully automatic approach, automatic food intake recognition preceded the application of the chew counting algorithm. The sensor signal was divided into 5-s non-overlapping epochs. Leave-one-out cross-validation was used to train a artificial neural network (ANN) to classify epochs as “food intake” or “no intake” with an average F1 score of 91.09%. Chews were counted in epochs classified as food intake with a mean absolute error of 15.01% ± 11.06%. The proposed methods were compared with manual chew counts using an analysis of variance (ANOVA), which showed no statistically significant difference between the two methods. Results suggest that the proposed method can provide objective and automatic quantification of eating behavior in terms of chew counts and chewing rates.

Several methods have been proposed for automatic and objective monitoring of food intake, but their performance suffers in the presence of speech and motion artifacts. This paper presents a novel sensor system and algorithms for detection and characterization of chewing bouts from a piezoelectric strain sensor placed on the temporalis muscle. The proposed data acquisition device was incorporated into the temple of eyeglasses. The system was tested by ten participants in two part experiments, one under controlled laboratory conditions and the other in unrestricted free-living. The proposed food intake recognition method first performed an energy-based segmentation to isolate candidate chewing segments (instead of using epochs of fixed duration commonly reported in research literature), with the subsequent classification of the segments by linear support vector machine models. On participant level (combining data from both laboratory and free-living experiments), with ten-fold leave-one-out cross-validation, chewing were recognized with average F-score of 96.28% and the resultant area under the curve was 0.97, which are higher than any of the previously reported results. A multivariate regression model was used to estimate chew counts from segments classified as chewing with an average mean absolute error of 3.83% on participant level. These results suggest that the proposed system is able to identify chewing segments in the presence of speech and motion artifacts, as well as automatically and accurately quantify chewing behavior, both under controlled laboratory conditions and unrestricted free-living.