Concept Development and Use of an Automated Food Intake and Eating Behavior Assessment Method

Nutrition researchers and dieticians use indirect measures to measure food intake, such as food recalls. With a meter, we can measure actual food intake during the meal and also people's eating behavior. The main advantage of the meter is that we can measure more precise how much people eat with little effort from consumers or patients.

This technique can be used to get better insight in what an individual eats. This can be especially important for those who suffer from diabetes or those who are malnourished, such as the elderly. The procedure will be demonstrated by Els Siebelink, who is head of the Dietician Department and a trained research dietician.

Participants are Femke de Gooijer and Michele Tufano, both PhD students, and all work at the Human Nutrition and Health Department of Wageningen University. Begin by preparing a juice, fruit yogurt, and fruit pieces. Recruit volunteers who agree to participate in the study.

Exclude participants wearing glasses who cannot wear lenses or those who have facial hair to avoid measurement errors. Inform the participants about the study and data collection, and obtain their signature on the informed consent before collecting data. After ensuring that the light in the room is evenly distributed and that there is no background noise on the video recordings, seat the participant before the table with the tabletop located just below their chest.

The entire torso should be visible, including the arms. Connect the wireless receiver of the tray and the webcam to a laptop. Switch on the tray, and start the laptop, making sure that the tray is charged, which is indicated by a green light.

Open the connector program, the receiver, and the processor software program together with the dashboard, respectively. Make sure the image frame is correct to prevent poor image quality and that the participant's head and chest, including arms and shoulders, are clearly visible. Keep the tray dry, including a 50-millimeter thin base panel with a central circuit board below the tray.

Transfer the weighing data at a one-second interval via a short-range radio signal of about one-meter distance. Connect the receiver to a personal computer via a USB port. Make sure that the plate, the cup, and the bowl are not resting on the platform or the surrounding tray.

Use the center ring to avoid this. Place the meter in front of the participant, and instruct the participant to eat as much or as little as he or she wants while looking straight into the webcam. Remind them not to put their hands in front of their face while eating.

Start a new observation in the receiver software. Log the date, participant number, participant's gender, age, and anthropometric data, such as weight and height. Include additional information such as the study condition and the study visit in the observation name.

Press record in the receiver software to record the observation and activate the dashboard in order to check the video recordings and the incoming data during data collection. Prior to the recording, ask the participant to raise the card with the participant number and raise their hand at the start and end of the meal. End the observation when the participant finishes eating.

It takes two minutes to transfer all the data to a spreadsheet. Disconnect the webcam and the tray receiver from the laptop, and clean it with a cleaning tissue or cleaning spray. Automated measures of eating behavior are stored under the heading Data.

Click on Export Data to extract the raw data. The output file contains data on the participant number, real time, relative starting time, and timestamped eating behavior variables, such as number of bites, number of chews, and chewing duration. Summarize and visualize the results in different bar charts within the program.

Export the log files to a spreadsheet, and perform the data analysis using the statistical program of preference. The meter tray measured lower intake of the salad compared to the yogurt and juice. The participants ate 17%less of the fruit salad compared to the fruit juice, a slower ingestion rate, smaller sip or bite sizes, and more chews led to lower intake of the salad compared to the yogurt and juice, as measured by the meter tray.

The participants chewed significantly more on the fruit salad compared to the yogurt and juice. The observed number of chews differed by a factor of three between the yogurt and fruit salad. The bite size was smallest for the salad, 6.5 grams per bite compared to eight grams per sip of juice.

Overall, the number of chews, the bite size, and the eating rate seemed to affect the amount that was eaten during the meal in an eating lab setting. In future versions of the meter, we would like to build in a camera that comes from the side or from the lower corner level, such that it is less intrusive for people than a camera that comes straight in front of them. Future versions of the system will allow us to study food intake behavior in real life.

This also allows us to give feedback to the consumer directly on how much they consume, what they consume, and also how fast they are eating.