This is graphical representation of the workflow for the AI4COVID project. There are three Working Packages (WPs) and each WP is divided to tasks (Ts). WP1 is about data collection for the project by means of websites, surveys, and questionnaires. The collected data are analyzed under WP2 using artificial intelligence (AI) techniques to generate useful information for disease containment and policy making. The outcomes of the research will be communicated to the relevant officials in WP3 to map the AI models to actionable policies. Besides, the project will engage in additional research for COVID-19 threat assessment.
AI4COVID Sri Lanka project will develop AI to conduct contact tracing and socioeconomic impact mitigation actions in a more informed, socially conscious and responsible manner in the case of the next wave of COVID-19 infections or a different future infectious disease. The project will develop a set of recommendations that policymakers and medical practitioners can access. This video includes milestones of the project.
A video introducing the AI4COVID project in Sri Lanka.
Overview of research by Prof. Janaka Ekanayake (at FITI 2020 keynote).
In this research, we try to understand the relationship between the population age demography and COVID-19 cases and deaths per million of countries and its application to other mortality causes.
Artificial Intelligence to model and forecast the spread of COVID-19: We are developing algorithms to predict the COVID-19 case counts, outbreaks and severity on different scenarios. We also attemp to quantify the differential impact of COVID-19 on different communities and individuals.
We are developing computer vision pipelines to asses the risk and suggest preventive measures for COVID-19 transmission in different scenarios
We propose a simulator that is capable of simulating a population with realistic movements where unique daily routines were assigned for each person. The users can efficiently build the environment of the simulation and robustly adjust the daily routines of each population group. We consider detailed factors that affect the transmission of the disease when people are in contact with each other and allows the user to tune these hyperparameters so that the simulator reflects a different variant of the disease.
We are developing a simulator to simulate the mobility of a population in a predefined virtual environment. This simulator resembles the behavior of a real-world pandemic. Thus, enabling us to identify the dissimilarities between observed vs true infection cases. Also, we can simulate different containment strategies and reopening strategies to find the optimal method that minimizes risks.
The spread of the global Covid-19 pandemic affected Sri Lanka similar to how it affected other countries across the globe. The Sri Lankan government took many preventive measures to suppress the pandemic spread. To aid policy makers in taking these preventive measures, we propose a novel district-wise clustering based approach. Using freely available data from the Epidemiological Department of Sri Lanka, a cluster analysis was carried out based on the Covid-19 data and the demographic data of districts. K-Means clustering and spectral clustering models were the selected clustering techniques in this study. From the many district-wise socio-economic factors, population, population density, monthly expenditure and the education level were identified as the demographic variables that exhibit a high similarity with Covid-19 clusters. This approach will positively impact the preventive measures suggested by the relevant policy making parties of the Sri Lankan government.