Clustering Indoor Location Data for Social Distancing and Human Mobility to Combat COVID-19

The world is experiencing the unprecedented time of a pandemic caused by the coronavirus disease(i.e.,COVID-19).As a countermeasure,contact tracing and social distancing are essential to prevent the transmission of the virus,which can be achieved using indoor location analytics.Based on the indoor location analytics,the human mobility on a site can be monitored and planned to minimize human’s contact and enforce social distancing to contain the transmission of COVID-19.Given the indoor location data,the clustering can be applied to cluster spatial data,spatio-temporal data and movement behavior features for proximity detection or contact tracing applications.More specifically,we propose the Coherent Moving Cluster(CMC)algorithm for contact tracing,the density-based clustering(DBScan)algorithm for identification of hotspots and the trajectory clustering(TRACLUS)algorithm for clustering indoor trajectories.The feature extraction mechanism is then developed to extract useful and valuable features that can assist the proposed system to construct the network of users based on the similarity of the movement behaviors of the users.The network of users is used to model an optimization problem to manage the human mobility on a site.The objective function is formulated to minimize the probability of contact between the users and the optimization problem is solved using the proposed effective scheduling solution based on OR-Tools.The simulation results show that the proposed indoor location analytics system outperforms the existing clustering methods by about 30%in terms of accuracy of clustering trajectories.By adopting this system for human mobility management,the count of close contacts among the users within a confined area can be reduced by 80%in the scenario where all users are allowed to access the site.

An Efficient Stacked-LSTM Based User Clustering for 5G NOMA Systems

Non-orthogonal multiple access(NOMA)has been a key enabling technology for the fifth generation(5G)cellular networks.Based on the NOMA principle,a traditional neural network has been implemented for user clustering(UC)to maximize the NOMA system’s throughput performance by considering that each sample is independent of the prior and the subsequent ones.Consequently,the prediction of UC for the future ones is based on the current clustering information,which is never used again due to the lack of memory of the network.Therefore,to relate the input features of NOMA users and capture the dependency in the clustering information,time-series methods can assist us in gaining a helpful insight into the future.Despite its mathematical complexity,the essence of time series comes down to examining past behavior and extending that information into the future.Hence,in this paper,we propose a novel and effective stacked long short term memory(S-LSTM)to predict the UC formation of NOMA users to enhance the throughput performance of the 5G-based NOMA systems.In the proposed strategy,the S-LSTM is modelled to handle the time-series input data to improve the predicting accuracy of UC of the NOMA users by implementing multiple LSTM layers with hidden cells.The implemented LSTM layers have feedback connections that help to capture the dependency in the clustering information as it propagates between the layers.Specifically,we develop,train,validate and test the proposed model to predict the UC formation for the futures ones by capturing the dependency in the clustering information based on the time-series data.Simulation results demonstrate that the proposed scheme effectively predicts UC and thereby attaining near-optimal throughput performance of 98.94%compared to the exhaustive search method.

Robust Fingerprint Construction Based on Multiple Path Loss Model (M-PLM) for Indoor Localization

A robust radio map is essential in implementing a fingerprint-based indoor positioning system(IPS).However,the offline site survey to manually construct the radio map is time-consuming and labour-intensive.Various interpolation techniques have been proposed to infer the virtual fingerprints to reduce the time and effort required for offline site surveys.This paper presents a novel fingerprint interpolator using a multi-path loss model(MPLM)to create the virtual fingerprints from the collected sample data based on different signal paths from different access points(APs).Based on the historical signal data,the poor signal paths are identified using their standard deviations.The proposed method reduces the positioning errors by smoothing out the wireless signal fluctuations and stabilizing the signals for those poor signal paths.By consideringmultipath signal propagations from different APs,the inherent noise from these signal paths can be alleviated.Firstly,locations of the signal data with standard deviations higher than the threshold are identified.The new fingerprints are then generated at these locations based on the proposed M-PLM interpolation function to replace the old fingerprints.The proposed technique interpolates virtual fingerprints based on good signal paths with more stable signals to improve the positioning performance.Experimental results show that the proposed scheme enhances the positioning accuracy by up to 44%compared to the conventional interpolation techniques such as the Inverse DistanceWeighting,Kriging,and single Path LossModel.As a result,we can overcome the site survey problems for IPS by building an accurate radio map with more reliable signals to improve indoor positioning performance.