A Sustainable Multi-Modal Multi-Layer Emotion-Aware Service at the Edge

Limited by the computational capabilities and battery energy of terminal devices network bandwidth, emotion recognition tasks fail to achieve good interactive experience for users. The intolerable latency users also seriously restricts popularization applications in edge environments such as fatigue detection auto-driving. development computing provides a more sustainable solution this problem. Based on computing, article proposes multi-modal multi-layer emotion-aware service (MULTI-EASE) architecture that considers user’s facial expression voice data source recognition, employs intelligent terminal, server cloud execution environment. By analyzing average delay each task consumption at mobile device, we formulate delay-constrained minimization problem perform scheduling policy between multiple layers reduce end-to-end using an edge-based approach, further improve users’ saving computing. Finally, prototype system is implemented validate MULTI-EASE, experimental results show MULTI-EASE efficient platform analysis applications, provide valuable reference dynamic under architecture.