Automatic food intake monitoring for the ageing population

Food intake monitoring can play an important role in the prevention of malnutrition among older adults. Traditional monitoring methods typically involve the use of pen-and-paper food diaries or questionnaires. While digital alternatives exist, these tools rely on manual data entry, often multiple times a day. Furthermore, the recorded data may be incomplete and contain mistakes due to human error or a deliberate misreporting of the food intake. While these methods are considered to be the gold standard for food intake, they are rarely used in the ageing population due to their time consuming nature. Nevertheless, nutrition plays an important role in the health status of older adults. Malnutrition has been linked with decreased muscle strength, poorly healing wounds, increased hospital admission time and increased hospital mortality rate. Preventing malnutrition by means of a targeted nutritional intervention can prevent these problems and increase general quality of life. A routine monitoring for early recognition and treatment of malnutrition should therefore be included in the routine care of older adults.

Technology can play an important role in the food monitoring process. Sensors may be employed to automatically measure eating activity or the amount of consumed food, which may supplement traditional methods, lowering the recording burden on the user and caregiver. Several sensor systems have been proposed in the literature to accomplish this task, from wearable devices to table embedded scales and camera based methods running on a smartphone. Research specifically investigating methodologies for use in the older population, however, remains sparse. The wearable systems proposed in the literature may not be comfortable for use over longer periods of time or be stigmatising to the older adult, table embedded scales require an extensive adaptation of the existing eating surface, while smartphone usage has proven difficult in older adults. There is an acute need for tools that are comfortable to use by older adults to aid in the daily care and prevention or treatment of malnutrition or related disease. 

Two sensor systems and corresponding algorithms are proposed in this thesis. The first is an accelerometer based wearable system, with the accelerometer mounted on the eyeglasses of the user. The eyeglasses are used in this context as a platform to mount the accelerometer in close proximity to the head. The ears of the glasses are able to transmit the vibrations and movements of mastication muscles in the skull during chewing to the accelerometer, where it can be converted into an acceleration signal and used for the detection of chewing activity. A chewing detection algorithm is proposed based on supervised machine learning techniques. Data was recorded from older adults in a nursing home to train and validate the model. The results show that an accelerometer worn this way can be used to detect chewing activity. 

Furthermore, a smart plate system is presented. For the purpose of the research, a prototype was designed and developed  consisting of a custom embedded system and sensors. The system consists of a base station and an off-the-shelf polymer plate that is mounted on top of the base. Weight sensors in the base accurately measure the weight of consumed food from the plate. The novelty of this system is the ability to measure the location of individual bites on the plate. In combination with a compartmentalised plate, the system can estimate from which compartment a bite was taken, without any sensors or electronics embedded into the plate itself or physical changes to the plate. All hardware is located into the base station and is separate from the plate. For the bite localisation to work, an accurate detection of the individual bites is required. For this, a novel bite detection algorithm is presented based on a supervised learner. Data was recorded from older adults eating a meal with the plate in a nursing home and hospital, and is used to train and validate the model. Results show that the system works as expected, with a bite detection algorithm that improves on the state of the art and the ability to measure the consumed food per compartment. With prior knowledge of which food type was served in which compartment, this can allow for an accurate estimation of the total amount of ingested calories.

Finally, an exploratory study into behavioural analysis using the smart plate is presented. We show that parameters extracted from individual bites detected with the smart plate may be used as a descriptor of behavioural traits during eating. 

The systems and algorithms presented in the thesis have the potential to lower the threshold for the adaptation of sensor based food intake monitoring in older adults. Furthermore, the tools can be employed for research in other target groups, from prevention and treatment of obesity to quantified self applications in young to middle aged adults.