Forward thinking ways to apply Machine Learning in a Pandemic
Note from the editors: Towards Data Science is a Medium publication primarily based on the study of data science and machine learning. We are not health professionals or epidemiologists, and the opinions of this article should not be interpreted as professional advice. To learn more about the coronavirus pandemic, you can click here.
The pandemic has changed our lives: a lot. From all sides, the lives we lived before are no longer the same as they once were. Our workplaces are different; our families are different, our expectations are different too.
Given that most of us are working from home, I’ve put together 54interesting machine learning COVID based projects below, they’re all worth checking out! Each of these have their own place and some are more practical than others. However in terms of the raw application of knowledge, these are all great!
Let’s get right to it!
Face Mask Facial Recognition
Facial recognition is a huge field and it’s only set to grow in the coming months and years. Computer Vision is developing rapidly as technology in this space, including autonomous driving and identification, become more and more widespread.
At scale, Coronavirus has resulted in a demographic and societal change whereby people have to physically change their actions. Given that, masks are becoming compulsory in a huge number of countries and as such, the ability to identify whether people are wearing masks is also growing in demand.
Building a system that can determine if you’re wearing a mask or not is awfully similar to the problem of Facial Recognition, so the solution to this problem isn’t that difficult to create. Given that, the following sources are those that I’ve found quite useful in researching into it:
I really appreciated the work by PyImageSource and even implemented the framework on my own home computer. It worked so well as two scripts are provided meaning that you can do less of the fiddly stuff, and more of the playing around:
- Face mask recognition in images
- Face mask recognition in videos
Definitely worth a play around at home!
Social Distance Recognition
Following on from the mask recognition project: social distancing is one of the key themes of 2020. In the UK for example, you have to remain at a distance of more than 2 metres from people outside of your ‘bubble’, not to mention this distance varies between regions in Europe.
The trouble with this is to implement it in a way that doesn’t require new hardware. Existing camera’s don’t really have an innate concept of distance, so two markers are usually set to inform the program what approximately constitutes a safe distance.
Given that, the following sources will help you to develop your own Social Distance Recognition tool!
Say you’re coming down with a cold, getting a fever and generally feeling a bit run over. Should you worry?
Yes. Get a COVID test.
But if you can muster some energy, you can always use machine learning to aid in the determination of how likely you are to have COVID (or so the theory goes).
Using a sample data set from as generated here, you can quite easily throw it into a Random Forest and understand (a) how likely you are to have coronavirus and (b) how much you should be worried about each symptom.
Blog by Tanveer Hurra: source
Also If you do have symptoms, go get checked and isolate!
However, the trick with this project is getting the symptom data. It’s not easy, but the more symptom data you get, the better your predictions!
Social distancing is a big deal in the pandemic because the virus can transfer from person to person quite quickly over short distances. Given that, if an individual is tested positive, then it’s important to understand (a) who is in their network of people (which is actually easy to identify), but how likely each person is to have been infected. This allows policy makers to easily trace who may be infected and to isolate such people.
Given that, Nebula Graph is an open source project that allows users to generate graphs and determine connections between people based on arbitrary settings, in this case: people and places. A graph is loaded with data on both sick and healthy people, along with the addresses that people were travelling to: hoping to answer how people get sick when no one they came in contact was sick at the time of contact.
The blog by Min Wu is really insightful here, and despite it not coming with code, it’s not a difficult project to translate into Python.
- Blog by Min Wu: source
My recommendation would be to first build a model working with randomly generated data, then, to find a real data set or, generate your own within your network!
Despite us all being in lock down, there’s a surge in creativity in the space of machine learning as lots of new problems are being posed. New problems require smart solutions, and thankfully Machine Learning is able to play its part.
Hopefully, you’ve looked into the above and tried to take a stab at some of the projects. Some are easier than the others, but any forward steps you do make can surely make a huge difference!
Thanks for reading again!! Let me know if you have any questions and I’ll be happy to help.
Keep up to date with my latest work here!