S. Kielienyu, B. Kantarci, D. Turgut, and S. Khan. Bridging Predictive Analytics and Mobile Crowdsensing for Future Risk Maps of Communities against COVID-19. In Proc. of the 18th ACM International Symposium on Mobility Management and Wireless Access (MobiWAC'20), pp. 37–45, November 2020.
Crowd monitoring and management is an important application of Mobile Crowdsensing (MCS). The emergence of COVID-19 pandemic has made the modeling and simulation of community infection spread a vital activity in the battle against the disease. This paper provides insights for the utility of MCS to inform the decision support systems combating the pandemic. We present an MCS-driven community risk modeling solution against COVID-19 pandemic with the support of smart mobile device users (i.e., MCS participants), who opt-in to crowdsensing campaigns and grant access to their mobile device’s built-in sensors (including GPS). Each community is defined by the spatio-temporal instances of MCS participants that are clustered based on the projected future movements of these participants. The MCS platform keeps track of the mobility patterns of the participants and utilizes unsupervised machine learning (ML) algorithms, more specifically k-means, Hidden Markov Model (HMM), and Expectation Maximization (EM) to predict a risk score of COVID-19 community spread for each community ahead of time. Through numerical results from simulating a metropolitan area (e.g., Paris), it is shown that communities’ COVID-19 risk scores at the end of a set of MCS campaign can be predicted 20\% ahead of time (i.e., upon completion of 80\% of the MCS time commitments) with a dependability score up to 0.96 and an average of 0.93. Further tests with a larger population of participants show that community risk scores can be predicted 20\% ahead of time with a dependability score up to 0.99 and an average of 0.98.
@inproceedings{Kielienyu-2020-MobiWAC,
author = "S. Kielienyu and B. Kantarci and D. Turgut and S. Khan",
title = "Bridging Predictive Analytics and Mobile Crowdsensing for Future Risk Maps of Communities against COVID-19",
booktitle = "Proc. of the 18th ACM International Symposium on Mobility Management and Wireless Access (MobiWAC'20)",
year = "2020",
month = "November",
pages = "37-45",
location = "Alicante, Spain",
xxxacceptance = "??%",
abstract = {Crowd monitoring and management is an important application of Mobile Crowdsensing (MCS). The emergence of COVID-19 pandemic has made the modeling and simulation of community infection spread a vital activity in the battle against the disease. This paper provides insights for the utility of MCS to inform the decision support systems combating the pandemic. We present an MCS-driven community risk modeling solution against COVID-19 pandemic with the support of smart mobile device users (i.e., MCS participants), who opt-in to crowdsensing campaigns and grant access to their mobile device’s built-in sensors (including GPS). Each community is defined by the spatio-temporal instances of MCS participants that are clustered based on the projected future movements of these participants. The MCS platform keeps track of the mobility patterns of the participants and utilizes unsupervised machine learning (ML) algorithms, more specifically k-means, Hidden Markov Model (HMM), and Expectation Maximization (EM) to predict a risk score of COVID-19 community spread for each community ahead of time. Through numerical results from simulating a metropolitan area (e.g., Paris), it is shown that communities’ COVID-19 risk scores at the end of a set of MCS campaign can be predicted 20\% ahead of time (i.e., upon completion of 80\% of the MCS time commitments) with a dependability score up to 0.96 and an average of 0.93. Further tests with a larger population of participants show that community risk scores can be predicted 20\% ahead of time with a dependability score up to 0.99 and an average of 0.98. },
}
Generated by bib2html.pl (written by Patrick Riley, Lotzi Boloni ) on Sun Mar 03, 2024 18:41:16