Energy-aware data collection from the Internet of Things for building emotional profiles

In the field of affective computing, a major goal has been the development of models to recognize the affective state of individuals. Data related to people such as physiological signals, facial expressions and speech enable the analysis and recognition of affective states. Currently, sensors integrated in smart devices (e.g., smartphone and smartwatch) allow the collection of this type of data. In this work, we present a platform composed of RESTful web services to collect data related to user emotions and its context through smart devices. Due to potential energy-constrained sensors, the platform is provided with an energy-aware data collection mechanism. Four series of experiments were conducted to evaluate both the energy efficiency and the scalability of the platform. The experimental results indicate that the platform is scalable and helps to save energy of data-collection sensors compared with a system unaware of energy consumption.