A QoE Model for Digital Twin Systems in the Era of the Tactile Internet

Abstract

The idiom by Thomas Fuller fantasizes the fact that seeing is believing, but the feeling is the truth. This ideology has fired the vision and innovation of the Mulsemedia, multiple-sensorial media, and Internet of Skills (IoS) which enable the exchange of control, skills, and expertise anytime/everywhere across the Internet. With the emergence of the new generation of mobile network (5G), Tactile Internet, as well as the deployment of Industry 4.0 and Health 4.0, multimedia systems are moving towards immersed haptic enabled human-machine interaction systems such as the Digital Twin (DT). Specifically, Industry 4.0 will be using DT and robots on a large scale. This will increase human-machine and interaction to a great extent. There will be multimodal communications used to interact with digital twins and robots, specially haptics. Hence, tactile internet will replace the conventional internet today. In fact, a DT system can also be extended in Health 4.0 domain to act as a COVID-19 early warning system. Tracking a person’s temperature and other symptom data in real-time can signal if as well as when it’s time to see a doctor or take a COVID test. Link to a COVID tracing app, the digital twin might help get more information about the virus relative to the person itself. Since there are currently no well-recognized models to evaluate the performance of these systems, to address this research lacuna, we proposed a Quality-of-Experience (QoE) model for DT systems containing multi-levels of subjective, objective, and physiopsychological influencing factors. The model is itemized through a fully detailed taxonomy that deduces the perceived user’s emotional and physical states during and after consuming spatial, temporal, proximal, and abstracted multi-modality media between humans and machines. Further, the taxonomy was modelled using the best practice of machine learning methods to show how QoE for digital twin applications can be inferred and predicted from interactions and biosignals in this class of applications. Furthermore, the taxonomy was applied to two use cases. The first one addresses the objective quality optimization for transmission in a large scale immersed haptic virtual reality over the Internet while the second one aims to objectively infer an important DT QoE physiological aspect i.e, fatigue.