Case Study: Spark GPU-Enabled Framework to Control COVID-19 Spread Using Cell-Phone Spatio-Temporal Data

Abstract

Nowadays, the world is fighting a dangerous form of Coronavirus that represents an emerging pandemic. Since its early appearance in China Wuhan city, many countries undertook several strict regulations including lockdowns and social distancing measures. Unfortunately, these procedures have badly impacted the world economy. Detecting and isolating positive/probable virus infected cases using a tree tracking mechanism constitutes a backbone for containing and resisting such fast spreading disease. For helping this hard effort, this research presents an innovative case study based on big data processing techniques to build a complete tracking system able to identify the central areas of infected/suspected people, and the new suspected cases using health records integration with mobile stations spatio-temporal data logs. The main idea is to identify the positive cases historical movements by tracking their phone location for the last 14 days (i.e., the virus incubation period). Then, by acquiring the citizen's mobile phone locations for the same period, the system will be able to measure the Euclidean distances between positive case locations and other nearby people to identify the incontact suspected-cases using parallel clustering and classification techniques. Moreover, the daily change of the clusters size and its centroids will be used to predict new regions of infection, as well as, new cases. Moreover, this approach will support infection avoidance by alerting people approaching areas of high probability of infection using their mobile GPS location. This case study has been developed as a simulation system consisting of three components; positive cases/citizens movement's data generation subsystem, big data processing platform including CPU/GPU tasks, and data visualization/map geotagging subsystem. The processing of such a big data system requires intensive computing tasks. Therefore, GPU tasks carried out to achieve high performance and accelerate the data processing. According to the simulated system results, data partitioning and processing speed up measures have been examined.

A review of GIS methodologies to analyze the dynamics of COVID‐19 in the second half of 2020

“…In this review we identify those works that used it to perform clustering as part of the process of a spatial analysis. For example, Lai, Charpignon, Ebner, and Celi ( 2020 ) used it to group US counties based on sociodemographic characteristics and COVID‐19 data; and Abdallah, Khafagy, and Omara ( 2020 ) for GPS location data. SIR models can add explicit geographical variables to study epidemic dynamics (Geng et al., 2020 ; O'Sullivan, Gahegan, Exter, & Adams, 2020 ; Thomas et al., 2020 ).…”

“…In this review we identify those works that used it to perform clustering as part of the process of a spatial analysis. For example, Lai, Charpignon, Ebner, and Celi ( 2020 ) used it to group US counties based on sociodemographic characteristics and COVID‐19 data; and Abdallah, Khafagy, and Omara ( 2020 ) for GPS location data.…”

A Survey on Big Data Research in Fighting COVID-19: Contributions and Techniques

“…Various studies related to virus transmission and its influence factors have been carried out to predict (a) the spread of the virus [29,30,31,32,33]; (b) the person suspected of being infected [34]; (c) new infection areas [35]; (d) the likelihood of the second and third waves of the epidemic [36]; (e) COVID-19 contamination scenario based on people movement [37]; and (f) the increased number of cases [38]. COVID-19 task-force stakeholders can use these epidemiological predictions to prepare the necessary measures and policies.…”

“…K-means algorithms integrated with correlation techniques can be employed to cluster the countries based on their stages in facing COVID-19 and then examine the relationship between their public policy and the spread of diseases [4]. Hussien et al [35] used K-Means clustering to allocate positive case areas and classify the risk status using decision trees algorithms. The K-modes clustering algorithm, the extended version of K-means, was used to help physicians group the patients to get insight into their health and the treatments that might be needed.…”

“…Optical Character Recognition technology was applied to extract text data from PFT data for classification purposes [47]. To determine suspected cases and areas, cellphone Spatio-temporal data can be processed using a decision tree algorithm for classification [35,32]. An application of artificial intelligence was developed to determine the diagnosis and treatment of the COVID-19 disease for high-risk groups.…”