AI-Aided Proximity Detection and Location-Dependent Authentication on Mobile-Based Digital Twin Networks: A Case Study of Door Materials

Abstract

Nowadays, mobile–mobile interaction is becoming a fundamental methodology for human–human networking services since mobile devices are the most common interfacing equipment for recent smart services such as food delivery, e-commerce, ride-hailing, etc. Unlike legacy ways of human interaction, on-site and in-person mutual recognition between a service provider and a client in mobile–mobile interaction is not trivial. This is because of not only the avoidance of face-to-face communication due to safety and health concerns but also the difficulty of matching up the online user using mobiles with the real person in the physical world. So, a novel mutual recognition scheme for mobile–mobile interaction is highly necessary. This paper comes up with a novel cyber-physical secure communication scheme relying on the digital twin paradigm. The proposed scheme designs the digital twin networking architecture on which real-world users form digital twins as their own online abstraction, and the digital twins authenticate each other for a smart service interaction. Thus, inter-twin communication (ITC) could support secure mutual recognition in mobile–mobile interaction. Such cyber-physical authentication (CPA) with the ITC is built on the dynamic BLE beaconing scheme with accurate proximity detection and dynamic identifier (ID) allocation. To achieve high accuracy in proximity detection, the proposed scheme is conducted using a wide variety of data pre-processing algorithms, machine learning technologies, and ensemble techniques. A location-dependent ID exploited in the CPA is dynamically generated by the physical user for their own digital twin per each mobile service.

Keywords

• machine learning
• digital twin
• proximity detection
• mutual authentication