ABSTRACT
COVID-19 has now been sweeping the whole world, and fundamentally affecting our daily life. An effective mechanism to further fight against COVID-19 and prevent the spread of this pandemic is to alert people when they are in the vicinity of areas with a high infection risk, yielding them to adjust their routes and consequently, leave these areas. Inspired by the fact that mobile communication networks are capable of precise positioning, data processing and information broadcasting, as well as are available for almost every person, in this paper, we propose a mobile network assisted Risk arEa ALerting scheme, named REAL, which exploits heterogeneous mobile networks to alert users who are in/near to the areas with high risks of COVID- 19 infection. Specifically, in REAL scheme, all base stations (BSs) periodically estimate their serving users' locations, which are then analyzed by macro BSs (MBSs) to identify risk areas. Next, each MBS transmits the information about risk areas to small BSs (SBSs), which in their turn adjust the beamforming direction to cover these areas and send alerts to users located therein. Simulation results validate the effectiveness of the proposed REAL scheme. In addition, some key challenges associated with implementing REAL are discussed at the end. IEEE
ABSTRACT
Smart building technologies transform buildings into agile, sustainable, and health-conscious ecosystems by leveraging IoT platforms. In this regard, we have developed a Persuasive Energy Conscious Network (PECN) at the University of Glasgow to understand the user-centric energy consumption patterns in an agile workspace. PECN consists of desk-level energy monitoring sensors that enable us to develop user-centric models that can be exploited to characterize the normal energy usage behavior of an office occupant. In this study, we make use of staked long short-term memory (LSTM) to forecast future energy demands. Moreover, we employed statistical techniques to automate the detection of anomalous power consumption patterns. Our experimental results indicate that post-anomaly resolution leads to 6.37% improvement in the forecasting accuracy. © 2022 IEEE.