A Predictive Framework for Haptic Enabled VR-based Remote Phobia Treatment in Cloud/Fog Environment

The emerging Tactile Internet aims to transmit the modality of touch in addition to the conventional audiovisual signals, thus converting the content delivery networks into skill-set delivery networks. An interesting example of immersive, low-latency Tactile Internet applications is haptic-enabled virtual reality (VR), where an extremely low latency of less than 50 ms is required. In this paper, we consider a recently proposed fog-based haptic-enabled VR system for remote treatment of animal phobia. Specifically, we address the problem of excessive packet latency as well as packet loss, which may result in quality-of-experience (QoE) degradation. Toward this end, we aim to use machine learning to decouple the impact of excessive latency and extreme packet loss from the user experience by utilizing our proposed edge tactile learner (ETL), which is responsible for predicting the zones touched by the therapist and then delivering it to the patient fog domain immediately, if needed. The simulation results indicate that our proposed predictive method outperforms two benchmark algorithms in terms of accuracy and prediction time.