ABSTRACT
The pandemic experienced in the last two years in the world has led people to be much more careful in their social relations, keeping their social distance and using hygienic prevention measures. However, when it is necessary to enter crowded closed environments, people feel insecure and are more afraid of contagion. This situation leads to the need for measures to control access to public places in order to prevent infection and to reinforce people’s confidence. Various devices and solutions exist to control access, ranging from card-based identification to biometric sensors. However, they have shortcomings detected during the pandemic, such as the need to touch elements or the types of computing used, which can compromise security and/or response times. The solution proposed in this article integrates the best of these by incorporating facial recognition using neural networks, the presence or absence of a mask and medical Internet of Things (IoT) devices to monitor pulse, blood oxygen and body temperature. All this technology is used to check whether the person’s access is safe for them and others. The data collection process in this system has proven to be efficient thanks to fog computing, which reduces latency times and prevents the user’s data from being accessed by third parties while maintaining their privacy. © 2022, Springer Nature Switzerland AG.