Implementation of Emotion Recognition Using Edge-Cloud Computing

Abstract

Emotion recognition systems has been in demand due to its aid in several applications such as health monitoring, workload and drowsiness detection. For these applications, emotion recognition systems require to be deployed on an edge device. For deployment on an edge device, numerous limitations and bottlenecks such as implementation cost, deployment capabilities, and system efficiency affects the performance of the emotion recognition system. That is, emotion recognition on the edge suffers from either low accuracy or high inference time due to the hardware constraints. Hence, several previous studies focus on the deployment of emotion recognition on the edge. Despite that, low accuracy and high inference time still remains an issue. To resolve this, a platform with higher computation capacity must be employed. In this study, we implement an enhanced emotion recognition system by integrating cloud computing platform to the emotion recognition system process, whereby all emotion recognition tasks are performed on the cloud server, can overcome conventional edge device bottlenecks and provide cost-effectiveness, efficient power consumption, and enhanced computing process. Based on the results shown in this study, the proposed system is successful in predicting the emotion of the users in real-time.