COVID-19 has impacted all of our lives in a wide range of ways. A new collection of papers shows that the applications of AI in the management of this pandemic are equally wide-reaching.
Since the COVID-19 pandemic began our understanding of how contagious diseases spread has been called into question in an unprecedented way. Many researchers have reached the conclusion, supported by a robust body of scientific studies, that if we are to better understand how COVID-19 spreads and how this spread can be stymied we must turn to artificial intelligence (AI) and other recent computing breakthroughs.
The powerful combination of AI, machine learning, big data, cloud computing, mobile devices and much more could provide the key to filling gaps in our knowledge of infectious disease spread and combating the pandemic that impacted all of our lives.
Beyond this, however, advanced modeling methods can be applied to a surprising range of aspects of our lives, such as the transmission of medical data, and the eventual recovery of the global economy by the simulation of consumer buying habits.
A new collection of papers¹ published in a special edition of the journal Personal and Ubiquitous Computing lays out some of the ways these platforms can be employed both during this pandemic and beyond.
In a guest editorial introducing these sixteen studies, Fadi Al-Turjman, Near East University, Nicosia, Mersin 10, Turkey, explains the importance of some of these papers and how they stand poised to use AI to change our understanding of infectious diseases.
The first paper in the collection, also authored by Al-Turjman, examines one of the most prominent and influential aspects of the COVID-19 pandemic in limiting the spread of the virus, lockdowns and isolation.
Looking at Lockdowns
There has been no greater impact on our collective and individual lifestyles over the past 18 months and the levying of lockdown measures in an attempt to restrict the spread of COVID-19.
Al-Turjman and the team² applied a system called the Susceptible-Infectious-Recovered model to calculate the role population plays in the spread of disease. They attempted to isolate and study the ‘lockdown effect’, particularly in India, assessing in the process the numbers of infected and recovered individuals.
The resultant models were then set against lockdown policies to determine the role these played in India. This resulted in a solution-based analysis for use in limiting the pandemic spread and flattening of the infection curve.
While this paper modeled the effects of policy as the pandemic raged, another study³ in the collection used up-to-date deep learning techniques like Long Short Term Memory networks (LSTM), Recurrent Neural Network (RNN), and Gated Recurrent Units (GRU) to estimate the intensity of the pandemic in the near future.
The model helped the authors, including Hafiz Tayyab Rauf, a Research Scholar at the Faculty of Engineering & Informatics, University of Bradford, United Kingdom, predict the number of COVID-19 cases for the coming 10 days. The forecasting developed by the researchers proved 90% accurate in comparison to real-world numbers collected on July 1st, 2020, thus demonstrating its reliability.
Modeling of COVID-19 spread in a populated area was also the focus of the authors of the paper ‘Thermodynamic imaging calculation model on COVID-19 transmission and epidemic cities risk level assessment — data from Hubei in China’ ⁴, including Sulin Pang, School of Emergency Management/Institute of Finance Engineering, Jinan University, Guangzhou, 510632 China.
The team took the unique approach of using thermodynamics to model the density of infection in the 17 prefectures or cities in the landlocked province. The team found the higher the superimposed density of urban epidemic, the more infected people.
The transmission situation they found in Hubei Province showed that transmission was the highest possible risk, especially in Xiaogan and 10 other cities, with a slightly lower risk in the remaining six cities.
The Cost of COVID and Beyond
One of the most impressive aspects of the collection is that it brings together solutions to the many different problems that have arisen as a result of the COVID-19 pandemic. These include the impact on patients with pre-existing conditions like diabetes and neuromuscular diseases.
In addition to this, the papers also looked at some of the wider impacts of the pandemic and the modeling of the spread of a virus through a large population. This includes how health information should be effectively and ethically shared and how quantum cryptography could be employed to protect data being streamed from wearable medical devices.
One of the collection’s papers looks at what will undoubtedly be one of the major ongoing concerns as we emerge from the COVID-19 pandemic. The serious effect it has had on the global economy.
The article ‘Research on mobile impulse purchase intention in the perspective of system users during COVID-19’⁵ aimed to explore how consumers made impulse purchases during the COVID-19 outbreak. The team found three positive mobile situation factors influencing this behavior and having a positive impact on purchase intention; personalized recommendation, visual appeal and system usability.
Using these findings, the researchers put forward management strategies for vendors who rely on mobile purchases to improve shopping experiences and expand marketing.
1. Al-Turjman. F., , ‘AI-powered cloud for COVID-19 and other infectious disease diagnosis,’ Pers Ubiquit Comput, [https://doi.org/10.1007/s00779-021-01625-1]
2. Srivastava, V., Srivastava, S., Chaudhary, G. et al, , ‘A systematic approach for COVID-19 predictions and parameter estimation. Pers Ubiquit Comput, [https://doi.org/10.1007/s00779-020-01462-8]
3. Rauf. HT., Lali. MIU., Khan. MA., Kadry S, et al, , ‘Time series forecasting of COVID-19 transmission in Asia Pacific countries using deep neural networks,’ Pers Ubiquit Comput, [doi: 10.1007/s00779–020–01494–0.]
4. Pang. S., Wu. J., Lu. Y., , ‘Thermodynamic imaging calculation model on COVID-19 transmission and epidemic cities risk level assessment — data from Hubei in China,’ Pers Ubiquit Comput, [doi: 10.1007/s00779–020–01478–0]
5. Zhang, W., Leng, X., Liu, S., , ‘Research on mobile impulse purchase intention in the perspective of system users during COVID-19,’ Pers Ubiquit Comput, [https://doi.org/10.1007/s00779-020-01460-w]
Disclaimer: The views expressed here are those of the author expressed in their private capacity and do not necessarily represent the views of AZoM.com Limited T/A AZoNetwork the owner and operator of this website. This disclaimer forms part of the Terms and conditions of use of this website.