BLEDoorGuard: A Device-Free Person Identification Framework Using Bluetooth Signals for Door Access

Abstract

Recently, door access control with Internet of Things has become increasingly popular in the field of security. However, conventional approaches such as video-based or biological information-based cannot satisfy the requirements of personal privacy protection in the modern society. Hence, a wireless signal-based technique which does not need users to carry any devices, called device-free have been introduced in recent years to detect and identify persons. In this paper, we present BLEDoorGuard, a wireless, invisible, and robust door access system which leverages received signal strength indicator from Bluetooth low energy (BLE) beacons to recognize a person who accesses a door. We evaluated BLEDoorGuard in two real-world scenarios: the first is an office with a key lock, and the second is a meeting room with swipe card access. We exploit the characteristics of use of BLE for person identification and propose a two-step algorithm with multiple classifiers. We demonstrate that BLEDoorGuard is capable of identifying the actual user during door access with an accuracy of 69% and 62% among groups of 6 and 10 people, respectively.