Energy Modeling and Architecture Exploration for Emotion Detection Systems

Description

Energy consumption is one of the main constraints which are faced by designers of communicating objects. Indeed, we are seeing a real increase in the number of communicating objects ranging from customer applications (video games, health care objects) to industrial applications (M2M, automatic car parking, drones). This paper presents a new high level model of autonomy estimation for wearable communicating objects, and more particularly for emotion detection systems and a design space exploration. The innovation in this methodology is to meet the autonomy constraint of health objects while maintaining a reasonable performance which is defined by the emotion recognition rate. The influence of the architecture (RF protocol, kind and number of sensors, ...) and its configuration of the system autonomy and emotion recognition rate is studied in order to propose the most suitable system. The different results show that we can get a high recognition rate and a sufficient autonomy for users.

Abstract

International audience

Additional details