Studies indicate isolation as a psychological trigger to increased violence and stress which is reflected through protests against governments, increased cases of domestic violence and divorce, and increased substance abuse.
Our platform can be used by the government to normalize lockdown norms and allow access of public places ensuring social distancing. After relaxing prolonged lockdown measures, high population density can be expected in parks, streets, and other public places. Our interface can regulate this problem by ensuring social distancing regulations by collecting data of the maximum allowable human population at government-approved places. This will be done through a visit-request system created on the platform, which will ensure citizens will only be approved to visit non-clustered areas.
This will regulate further spread of COVID-19 or any such pandemics in future and will advance to the notion of a smart city.
We witnessed overcrowded public places in Japan when the state of emergency was removed. This violation of social distancing can inflict the second wave of COVID-19 and all these months of lockdown will be in vain. We are AbeNoMask and our idea is to create a more evolved organization in society to enforce and monitor social distancing.
A majority of the park data was obtained using a web- scraping tool. The data was then used to cross-reference data obtained from satellites to get the estimation of the land area of every respective park in the dataset. In addition, address and location data were also obtained.
Ideally, governments will use their own citizen identification numbers to populate accounts. For example, in Japan “My Number” is the unique identifier used for all citizens of Japan. Thus, for the demonstration of this proof of concept, the application requires the user to input their “My Number”. All other relevant data can be either manually inputted by the user, or auto-populated by the government organization.
This is done by following the social distancing practice of at least 2m radius per person. Once a value for the area of a park can be determined. That number is divided by 2.5m squared to estimate, a safe occupancy level for that park. However, using Landsat Surface Reflectance Data we would like to further improve the accuracy of the area of the park. Specifically, we would run a Machine Learning Model to determine the area of the bodies of water located in a park. For instance, if the park contains a body of water where humans would not normally occupy, we can subtract the surface area of the body of water from the total.
The design of the interface was done using a popular API called Flask. It was designed to be simple and barebone as possible to prove that the concept would work. There are pages for the following: 1) Registration of Account, 2) Login Page, 3) List of Available Parks, 4) Making a Request to Visit a Park, 5) List of all Active Requests, and 5) Account Settings.
The SQL database was designed using SQLite. There are three major tables: 1) Users, 2) Parks, and 3) Reservations.
Relationships:
The site is deployed for free using Heroku.
Tools:
Coding languages:
Built with:
Software: