论文标题
Wi-Fi和蓝牙触点跟踪无需用户干预
Wi-Fi and Bluetooth Contact Tracing Without User Intervention
论文作者
论文摘要
以前的联系跟踪系统要求用户执行许多手动操作，例如安装智能手机应用程序，连接无线网络或携带自定义用户设备。这增加了进入的障碍并降低了用户的采用率。结果，接触追踪效率降低了。与上面的系统不同，我们提出了一个新的隐私保护Wi-Fi和蓝牙（BLE）触点跟踪系统，该系统不需要智能手机应用程序，连接无线网络或自定义用户设备。我们的专门构建的路由器无缝跟踪智能手机，笔记本电脑，智能手表，BLE耳机和平板电脑，而无需任何用户操作，但不会追踪用户身份。设备和用户之间的映射仅用于确认的案例和可疑联系人。此外，由于使用双向长期记忆神经网络，我们可以在1.0 m内跟踪用户设备的绝对位置，这些短期记忆神经网络经过由自主机器人预先收集的数据进行训练。这使公共卫生当局可以跟踪其他接触跟踪系统经常忽略的间接液滴和表面传输。
Previous contact tracing systems required the users to perform many manual actions, such as installing smartphone applications, joining wireless networks, or carrying custom user devices. This increases the barrier to entry and lowers the user adoption rate. As a result, the contact tracing effectiveness is reduced. Unlike the systems above, we propose a new privacy preserving Wi-Fi and Bluetooth (BLE) contact tracing system that does not require smartphone applications, joining wireless networks, or custom user devices. Our specially built routers seamlessly track smartphones, laptops, smartwatches, BLE headphones, and tablets without any user action, but do not trace user identity. Mapping between devices and users is only carried out for confirmed cases and suspected contacts. Moreover, we can track the absolute positions of user devices within 1.0 m due to using bidirectional long short-term memory neural networks that are trained with data pre-collected by an autonomous robot. This allows public health authorities to track indirect droplet and surface transmissions that other contact tracing systems often overlook.
