OVERMIND

https://github.com/DiegoCrafter/nasa-space-challenge

https://youtu.be/8GPbzSv4ayk

The OMS reported that 4.79 million people worldwide have died as of October 2021 as a result of COVID-19, which continues to infect many people who do not take the necessary precautions. The risk of contagion has a greater impact in the world because countries do not have an adequate prevention policy against COVID-19 and this generates greater vulnerability. NASA has environmental indicators such as the measurement of environmental temperature, humidity, wind speed and global solar radiation that relate to a possible contagion of COVID-19 according to the area where the individual is located. One of the influencing factors is the lack of technology that provides information in real time through intelligent devices to reduce the risk of the spread of cases. Given this need, the objective is to create an intelligent mobile geolocation application with environmental variables to determine the level of risk in real time based on the K-means algorithm, which is why the KuskaSafe proposal was born. Epidemiological data such as gender, age, body mass index (BMI), diseases and temperature of the patient will be considered and analyzed with the CRISP-DM data mining methodology, which will help determine the level of risk of contagion against COVID-19.

KuskaSafe will provide geolocation with heat maps, QR code and Bluetooth which will allow visualization of risk level, risk factor and risk category. The application will benefit healthcare organizations, contributing to the reduction of contagions and the adequate management of resources.

The NASA data that served in the project is the Global Ground Data Assimilation System Version 2 (GLDAS-2) which has three components: GLDAS-2.0, GLDAS-2.1 and GLDAS-2.2. The GLDAS-2.0 component is forced entirely with Princeton meteorological forcing input data and provides a consistent time series from 1948 to 2014. GLDAS-2.1 is forced with a combination of model and observational data from 2000 to the present. The GLDAS-2.2 product sets use data assimilation (DA), while the GLDAS-2.0 and GLDAS-2.1 products are "open loop". The choice of forced data, as well as the observation source, variable and DA scheme, vary for the different GLDAS-2.2 products.

These meteorological data were used to use the environmental indicators as input variables of the intelligent device in which temperature, wind speed, dew and solar radiation made it possible to locate with the use of geolocation the most affected areas of covid 19 allowing to determine the level of risk of the areas with high contagion using the Kmeans algorithm to make a classification of the areas with more contagion located with heat maps. There is research that shows that there is an association between environmental variables and covid infection, which is why it inspired to know the level of risk of COVID 19 worldwide.

Thanks to the hackathon as a team we learned to propose solutions to problems that affect the world as COVID-19 and also encouraged each member to be more aware that as a team we can add knowledge and solve different problems. 

Tools: Data mining, Jamovil Software, Matlab, Figma, Tableau, Python programming language, Canvas, Discord, Google meet, Google Drive, Camtasia, Zoom, Office. 

NASA global ground data (GLDAS-2.0, GLDAS-2.1 and GLDAS-2.2), WHO case data. 

COVID-19, IA, Data mining, Matlab

This project has been submitted for consideration during the Judging process.