Recognition of Nutrition Intake Using Time-Frequency Decomposition in a Wearable Necklace Using a Piezoelectric Sensor

Abstract

Food intake levels, hydration, ingestion rate, and dietary choices are all factors known to impact the risk of obesity. This paper presents a novel wearable system in the form of a necklace, which aggregates data from an embedded piezoelectric sensor capable of detecting skin motion in the lower trachea during ingestion. The skin motion produces an output voltage with varying frequencies over time. As a result we propose an algorithm based on time-frequency decomposition, spectrogram analysis of piezoelectric sensor signals, to accurately distinguish between food types such as liquid and solid, hot and cold drinks and hard and soft foods. The necklace transmits data to a smartphone, which performs the processing of the signals, classifies the food type, and provides visual feedback to the user to assist the user in monitoring their eating habits over time. We compare our spectrogram analysis with other time-frequency features such as Matching Pursuit (MP) and Wavelets. Experimental results demonstrate promise in using time-frequency features, with high accuracy of distinguishing between food categories using spectrogram analysis and extracting key features representative of the unique swallow patterns of various foods.

Food Intake Detection and Classification Using a Necklace-Type Piezoelectric Wearable Sensor System

“…Second, we have achieved a classification accuracy of 80.3% in real-life settings over 17 food categories. Our system outperforms the state-of-the-art piezoelectric sensor based method [13]. Third, we have developed a smartphone application that sends real-time feedback to the user about the number of swallows detected by the necklace for each food category, and suggests time for the next meal and exercise.…”

Segmentation and Characterization of Chewing Bouts by Monitoring Temporalis Muscle Using Smart Glasses With Piezoelectric Sensor

“…The classifier achieved an average F-score of 96.28% for leave-one-out cross-validation (participant level). Several sensor systems have been presented where the accuracy of food intake detection varies from 80% to 96% [18], [19], [24], [25], [34]. For most of these sensor systems, their ability to detect food intake was tested when the participants were sedentary.…”

“…Another common limitation of the current techniques for food intake monitoring is the use of the epoch-based classification to detect chewing ([16], [18], [19], [23]–[25]) and to compute the number of chews. With this approach, the sensor signal is split into short segments (epochs) which then are classified either as chewing or no chewing.…”

Sensor technology implementation for research, treatment, and assessment of eating disorders

“…Use of such technology is beneficial for supporting healthy behavior and may have long‐term health benefits (for a review, please see Fritz, Huang, Murphy, and Zimmerman []). In addition to measuring physical activity, wearable sensors (e.g., wrist or necklace sensor) and nonwearable sensors (e.g., fork and tray) have been designed to accurately and objectively measure quantity and rate of food intake in an everyday environment (e.g., Alshurafa et al, ; Dong, Scisco, Wilson, Muth, & Hoover, ). However, these devices have not yet been tested with individuals with EDs.…”

“…For example, the ability for both wearable and nonwearable sensors to detect patterns and deviations in motion has allowed caregivers to predict and prevent dangerous situations (e.g., falling) in elderly patients with Parkinson's disease and Dementia (e.g., Yu, 2008 Fritz, Huang, Murphy, and Zimmerman [2014]). In addition to measuring physical activity, wearable sensors (e.g., wrist or necklace sensor) and nonwearable sensors (e.g., fork and tray) have been designed to accurately and objectively measure quantity and rate of food intake in an everyday environment (e.g., Alshurafa et al, 2015;Dong, Scisco, Wilson, Muth, & Hoover, 2014). However, these devices have not yet been tested with individuals with EDs.…”