Creative Coders

https://drive.google.com/file/d/1OFADieWMinry7DwgH7l8S31E7yzg7QxT/view

https://drive.google.com/drive/folders/1Ivj5D60gTBKmuFCc8W4BUsoAdgmsl3ub

We chose this "COVID19: Calculating Risk" challenge because it discusses how Cov19 has become a global problem, or how pandemics and vaccination efforts can control its spread, but we should reduce this risk until we see a Vaccination, and it will depend on my joy and protect us... so what do we do?            

So first our application collects data from users, such as (age, country, city, length, health status, processing) With COV19 (like wearing a mask, etc.) Then this application tries to find out how many cases there may be in his city by using GPS and determining his location. Because it accesses data from certified websites such as who.int, the user may be Encountering danger is like the status of his city. Our app showed him the latest news about Cov19 to learn about it. By using GPS, we made it into an application that will remind users to wear a mask, drink alcohol and pay attention to hygiene after about 6 meters from home. There is a reminder in our app, he is used to reminding him every time he goes out and reminds him to wear a mask before then. Finally, we analyzed factors that may affect Cov19 cases, such as temperature, population growth, and special events. By using machine learning engineering, algorithms, and data structures, we have warned him about these factors and tried to warn him to make him aware.

To create our app, we first Analyzed Factors that may Affect the Spread of Coronavirus. While there are other methods that can also shed insights on the relationship between factors, the correlation matrix is one of the simplest tools for shortlisting the highly correlated factors for analysis and we used it to analyze the factors. there are several factors mapped that we hypothesized may affect the coronavirus data points as follows:

• Pop. Density (per km²)

• Avg. Wind Speed (m/s)

• Avg. Annual Temp. (C.)

• Avg. Annual Precipitation (mm/yr.)

• %Pop. High Income

• %Pop. Upper-Middle Income

• %Pop. Middle Income

• %Pop. Lower Income

• %Pop. Poor

• %Pop. Age ≤ 14

• %Pop. Age 15–64

• %Pop. Age ≥ 65

• Current Lockdown Status (Y/N)

 we started analyzing the correlation matrix in Python. We found Correlation ≠ Causation. Correlation does not imply causation even if there is a high correlation between the two factors. Therefore, it is imperative for us to research more on the relationships between the factors before establishing the causal links. After we found relations between factors and covid-19. These are usually what we can assume to further prove causality. Some assumptions are as follows:

a) ‘Average wind speed’ vs. ‘Infected Cases’: The correlation between these two factors is very deep. Although there is no direct information pointing to a direct relationship between the two factors. According to reports, viral droplets from infected patients can infect other nearby pathogens.

b) ‘%Pop. High income’ & ‘%Pop. Upper-middle income’ vs. Infection data: These two correlations are marked in red. In fact, high- and upper-middle-income segments are mostly colored red compared to the infection data. Low-income and poor-income segments appear to be more positively correlated with active and active cases than middle-income and upper-income segments (albeit slightly positively).

c) If the wind speed does have a causal link with the infection rates, then the social distance of 6 ft. (1.83 m.) may not be enough

In addition, a simple prediction model can be trained for a specific area based on the factors mentioned. An example of a linear regression model to predict the number of tomorrow's cases in each area can be written as follows:

 Infected cases (Day N+1) ~ Avg. Wind Speed (in the past 1 week — or incubation period) + Population density + Current Active Cases.

 In this way, we can also test the hypotheses of these factors, whether they are true or not. If the test set predictions are imprecise, we may need to change the factors in the regression models (or find new ones). To understand how these applications work, the first thing that should be kept in mind is that not all of them work in the same way. In general, the 'apps' rolled out to date in Spain and in other western countries focus on self-diagnosing the disease, symptom monitoring, and notifying cases to health authorities. the app will collect data from you, and let you know if you have been near another app user who has tested positive for coronavirus. In short, the more sensitive the data is from a privacy protection standpoint, the more useful it is from an epidemiological point of view. This implies that citizens may be faced with having to choose between anonymity and convenience, so this app collects information like health status, behavior, and location by using GPS. This app is made it by Using Flutter, Dart, and Java as Finishing the Front-end Part of the App & Start with the back-end. This app tells you:

• Regional risk score alerts: Based on the postal region you submit during registration, the app tells you the level of risk in your area as how many cases were recovered and then notifies you when it changes.

• Symptom recorder: You can record your symptoms, and (if appropriate) the app will invite you to book a coronavirus test and access the latest medical advice and guidance. Your symptom record is not shared with anyone.

• It tells you advice about how to protect yourself from covid-19.

• It makes analysis by using covid-19’s factors to tell you the risk of the day.

• Signup with some information to rate the user’s health and knowing if he is infected with covid-19 or not.

So, what permissions does the app require? Just notifications and GPS. We made this app to achieve this:

Calculate the risk of covid-19, but the benefits in our app are:

1-Easy to use as we make great UI /UX design for users

2-Tell you whether you can go to this city or not based on covid-19 infection risk in it

3-Covid-19 and vaccination news

4-Tells you covid-19 prevention ways

5-Tells you whether you have covid-19 symptoms or not

6-Real-time data on cases in your country

7-Tells you case fatality risk and infection risk in your location and country.

The tools were used to develop our app:

Hardware:

• Smartphone to try the app on it.

• PC for coding.

Software:

• Visual studio code.

• jupyter notebook.

• Flutter

• Gd design

Programming Language:

• Python in Data analysis and machine learning (Seaborn, Pandas, requests).

• Dart

• Gd Script

We used this Data:

-https://covid.cdc.gov/covid-data-tracker/#vaccinations_vacc-total-admin-rate-total

-https://earthdata.nasa.gov/learn/articles/sedac-covid-19-viewer

-https://eodashboard.org/?poi=W6-NASAPopulation&indicator=NASAPopulation

-https://sedac.ciesin.columbia.edu/data/set/gpw-v4-basic-demographic-characteristics-rev11/metadata

-https://vaccovid.live/covid-19-tracker/africa-data

-https://nasapeople.nasa.gov/coronavirus/

-https://www.nasa.gov/office/procurement/covid19-contractor-information

When we want to analyze covid-19 spreading factors, we want to collect more and more data on covid-19. So we used these sites and data to collect from it and make an analysis.

we used data from Nasa to calculate the risk as we find wind speed, population growth, and infection risk, used it and by using python and machine learning we made it graph that can make analysis by using this data.

We followed these steps:

Connect to a database: the data that’s available or open up your private database and start digging through it to understand what information our team has been collecting.

Use APIs: Think of the APIs to all the tools our team \’s been using and the data have been collecting. we have to work on getting these all set up so we can use those email open and click stats, the information our team.

Look for open data: The Internet is full of datasets to enrich what we have with additional information. For example, census data will help us add the average revenue for the district where our users live or OpenStreetMap. A lot of countries have open data platforms.

we attend this Hackathon for these reasons:

1. Showcase our Skills

While hackathons are a great way for everyone to meet and collaborate with others in their field of expertise, there’s also a competitive side. Hackathons challenge attendees to exhibit our ability to innovate and create compelling, real-world solutions, utilizing the latest devices and technology. It’s also a chance to demonstrate specific skills that we aren’t able to showcase elsewhere.

2. Learn About Tech

One of the biggest benefits of attending This hackathon is learning new skills and attaining new knowledge. we might gain more knowledge than we would in six months, due to the learning-by-doing approach employed at hackathons. we could also soak up information from fellow attendees — including ideas we may never have gained in the classroom or from a book.

3. Share our Ideas

At its heart, this hackathon is a deeply collaborative effort. To get the most out of these events, attendees need to be willing to share their expertise with others, ensuring that everyone learns from everyone else. For example, experts in security can learn from designers about how to better implement their features and app designers can learn how to better protect personal information. Hardware and software specialists can better learn how to work with each others’ tools — everyone learns something new.

4. Challenge ourselves

It can be very easy to remain in our comfort zone, doing things we know how to do and never really challenging ourselves. At hackathons, there is no such safe space. we were constantly challenged to push ourselves and move outside our comfort zone. From working as part of a team of people who we don’t know, to doing things that we never even thought we’d try, hackathons are a great way to discover new talents, passions and skills.

5. Collaborate Under Pressure

It may not sound like a selling point, but experiencing the pressure of having to come together with people we don’t know and create something entirely new in a very short space of time can be hugely rewarding. we don’t simply get a sense of achievement from completing the task — we also learn how to work efficiently, how to work as a team, and how we can put our skills to work in a quick-turn environment.

6-Presentation Details and Practice Matters

It’s typical for hackathons to hold presentations and prototype demos. We’ve spent hours building a prototype, might as well give it a little kick by working on our presentation and delivery. My team collaborated on our deck and as the self-appointed designer, we made sure that the slides we’re going to show we're not boring. Issy, our designated presenter, rehearsed thoroughly until it was our turn.

7-You Need to See the Bigger Picture

As developers and hackers, we may be too deep into your code to think of business goals, or our solution’s value propositions. If we don’t care much about business angles or our users, we better have dedicated people in the team to help us make sense of our innovative solution. It’s worth a step back — do market and user research, and take our time to understand the moving pieces of our idea.

So we found these things and learned in this hackathon. We learnt how to use GODOT to make 2D/3D game and coding in it using Gd Script, how to send and receive data from websites using API and web Scraping, Go deep into Data analysis to make analysis for covid-19 spreading factors by using python and machine learning(Seaborn, Pandas and requests) and learning Back-end for users data.

We faced many problems like a deadline as we won't finish this app until the deadline, but by collaborating, we finish it.

So we learnt problem-solving skills. By sharing ideas and discuss them we learnt Critical Thinking.

As we searching a lot about Covid-19, we learnt how to make scientific research and APA. How we can find info.

Data:

▪ https://earthdata.nasa.gov/learn/articles/sedac-covid-19-viewer

▪ https://sedac.ciesin.columbia.edu/data/sets/browse

▪ https://www.worldometers.info/coronavirus/

▪ https://www.tomorrow.io/coronavirus-resource-center/

▪ https://www.ncsc.gov.uk/information/nhs-covid-19-app-explainer

▪ https://covid19.who.int/table

▪ https://www.canada.ca/en/public-health/services/diseases/2019-novelcoronavirus-infection.html?utm_campaign=hc-sc-phm-21- 22&utm_medium=sem&utm_source=ggl&utm_content=ad-texten&utm_term=coronaviruses&adv=2122- 0008&id_campaign=12663296824&id_source=125900518968&id_content=511 624188952&gclid=EAIaIQobChMI5I3wmtew8gIVa21vBB00KglVEAAYASAAEg Kl5_D_BwE&gclsrc=aw.ds#a1

References:

• Urrutia-Pereira, M., Mello-da-Silva, C. A., & Solé, D. (2020). COVID-19 and air pollution: A dangerous association?. Allergologia et immunopathologia, 48(5), 496-499.

• Osler, S. (2020). Coronavirus outbreak: All the secrets revealed about the COVID-19 pandemic. A complete rational guide of its evolution, expansion, symptoms and first defense.

• Baldwin, R. E., & Weder, B. (2020). Economics in the time of COVID-19.

• Moustafa, A. A. (2021). Mental health effects of COVID-19. Academic Press.

• RAabeda, K., & Lashinbc, M. A. (n.d.). An analytical study of the factors that influence COVID-19 spread. ScienceDirect.com | Science, health and medical journals, full text articles and books. https://www.sciencedirect.com/science/article/pii/S1319562X20306331

• Tripathi, S. (2020, May 19). Analysing factors that may affect the spread of coronavirus. Medium. https://towardsdatascience.com/identifying-factorsthat-leads-to-increased-infection-cases-with-correlation-analysise49d75eebbb5

• Worldometer. (17th April 2020). Coronavirus Reported Cases by Country. https://www.worldometers.info/coronavirus/

• Grassi, Veronesi, Schenkel, Peier, Neukom, Volkwein, Martin, and Hurni. (2015). Mapping of the global wind energy potential using open-source GIS data”

The tools were used to develop our app:

Hardware:

• Smartphone to try the app on it.

• PC for coding.

Software:

• Visual studio code.

• jupyter notebook.

• Flutter

• Gd design

Programming Language:

• Python in Data analysis and machine learning (Seaborn, Pandas, requests).

• Dart

• Gd Script

#Covid-19 #Calculate risk #Flutter & Dart #Godot #ML and Data analysis #Case Fatality risk #Covdi-19 Prevention #App development #Game development

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