Toward supporting food journaling using air quality data mining and a social robot

Unhealthy diet is a leading cause of health issues. A powerful means for monitoring and improving nutrition is keeping a food diary. Unfortunately, frail people such as the elderly have a hard time filling food diaries on a continuous basis due to forgetfulness or physical issues. For this reason, in this paper we investigate the integration of nutrition monitoring in a robotic platform. A machine learning module detects cooking activities based on air quality sensor data. When cooking is detected, a social robot interacts with the user to fill the food diary through a conversational interface. We report our experience on the development of a partial prototype of our system. Moreover, we illustrate the results of preliminary experiments with annotated sensor data gathered over one month from a real-world apartment