Appsilon at Hack4Environment Hackathon - Solving Illegal Waste Disposal Problems with Machine Learning

Estimated time:

<h2><span data-preserver-spaces="true">Appsilon at Hack4Environment</span></h2> <span data-preserver-spaces="true">Appsilon has recently taken part in the </span><a class="editor-rtfLink" href="" target="_blank" rel="noopener noreferrer"><span data-preserver-spaces="true">Hack4Environment</span></a><span data-preserver-spaces="true"> - a 24-hour hackathon focusing on dealing with the critical problem of illegal waste disposal (known as </span><em><span data-preserver-spaces="true">fly-tipping</span></em><span data-preserver-spaces="true">). </span> <blockquote><span data-preserver-spaces="true">Read about our AI4Good initiative - </span><a class="editor-rtfLink" href="" target="_blank" rel="noopener noreferrer"><span data-preserver-spaces="true">Here's how Machine Learning can be used to analyze wildlife camera trap datasets</span></a><span data-preserver-spaces="true">.</span></blockquote> <span data-preserver-spaces="true">Long story short - in 24 hours, we proposed a solution that granted us an honorable mention in the competition!</span> <span data-preserver-spaces="true">Navigate to a section:</span> <ul><li><a href="#about">About the Hackathon</a></li><li><a href="#solution">Our Solution</a></li><li><a href="#lessons">Lessons Learned</a></li><li><a href="#conclusion">Conclusion</a></li></ul> <h2 id="about"><span data-preserver-spaces="true">About the Hackathon</span></h2> <span data-preserver-spaces="true">As said previously, the hackathon's goal was to somehow deal with the problem of illegal waste disposal. Our solution was based on two parts:</span> <ol><li><strong><span data-preserver-spaces="true">Application portion</span></strong><span data-preserver-spaces="true"> - managed by Dominik Krzemiński</span></li><li><strong><span data-preserver-spaces="true">Machine learning portion</span></strong><span data-preserver-spaces="true"> - managed by Jędrzej Świeżewski</span></li></ol> <span data-preserver-spaces="true">We ended up proposing a solution from three different perspectives, which are discussed in the following section.</span> <h2 id="conclusion"><span data-preserver-spaces="true">Our Solution</span></h2> <span data-preserver-spaces="true">Our idea was to build an app addressing the issue from the following perspectives:</span> <ul><li><strong><span data-preserver-spaces="true">Citizen perspective</span></strong><span data-preserver-spaces="true"> - citizens could localize sites in their neighborhood with disposed waste and earn recognition for reporting on cleaning it up.</span></li><li><strong><span data-preserver-spaces="true">Local authority's perspective</span></strong><span data-preserver-spaces="true"> - we provide them with insights about the waste's location on a larger scale, allowing them to direct cleaning efforts.</span></li><li><strong><span data-preserver-spaces="true">Manufacturer perspective</span></strong><span data-preserver-spaces="true"> - we build a mechanism for incentivizing the manufacturers of goods that get thrown out as the waste to act on the information that their products are perceived as littering the local communities.</span></li></ul> <span data-preserver-spaces="true">As icing on the cake, we have built and deployed a Shiny application called </span><a class="editor-rtfLink" href="" target="_blank" rel="noopener noreferrer"><span data-preserver-spaces="true">Kropla</span></a><span data-preserver-spaces="true">. It aims to display the data provided by the hackathon organizers clustered into localized groups of waste items. We have added a mechanism for claiming waste removal and receiving recognition for it. </span> <span data-preserver-spaces="true">In addition, we've also trained a computer vision model to detect the brand of a given waste item. The model's validation accuracy reached 75% on a dataset with 46 classes.</span> <h2 id="lessons"><span data-preserver-spaces="true">Lessons Learned</span></h2> <span data-preserver-spaces="true">At the end of the day, there are four main takeaways for us from this hackathon:</span> <ol><li><span data-preserver-spaces="true">Hackathons are a great occasion to bond within the team. Somehow, a chat late at night serves this purpose best.</span></li><li><em><span data-preserver-spaces="true">Agglomerative clustering</span></em><span data-preserver-spaces="true"> is perfect for dealing with clustering on huge scale differences. The data we dealt with spanned the globe, while it, of course, makes no sense for a fly-tipping site to be of a size larger than a few tens of meters. Many other clustering algorithms (including the common </span><em><span data-preserver-spaces="true">HDBSCAN</span></em><span data-preserver-spaces="true">) struggle with such data leading to, e.g., entire cities becoming a cluster.</span></li><li><span data-preserver-spaces="true">The 75% accuracy reached by our machine learning model does not seem to stand out. When one considers the fact it was an accuracy over 46 classes, it starts feeling very good. However, this is misleading as the data set was heavily imbalanced, with one brand taking up around half of the data. This means a majority-class proxy would have ~50% accuracy regardless of the multitude of classes. Our model's key strength lies in the fact that it dealt well with some of the tiny classes (for some, the brand was hard to recognize even for a human eye). The takeaway here is that reporting a model's performance with a single number is typically not sufficient.</span></li><li><span data-preserver-spaces="true">Our team had two participants, while each of the three teams that ranked above us had more (3, 5, and 5) - having more people on board, especially in a limited time setting, can be a differentiating factor.</span></li></ol> <h2 id="conclusion"><span data-preserver-spaces="true">Conclusion</span></h2> <span data-preserver-spaces="true">All in all, the hackathon was a lot of fun! Moreover, it touched a globally and locally important ecological issue and helped raise the awareness of waste reduction and fly-tipping.</span> <span data-preserver-spaces="true">We would like to congratulate the other winners, thank the organizers and applaud all the participants for their effort. We regret that we could not gather in person due to the circumstances and mingle with all the people involved in the event to get to know each other beyond the chat communication.</span> <h2><span data-preserver-spaces="true">Learn More</span></h2><ul><li><a class="editor-rtfLink" href="" target="_blank" rel="noopener noreferrer"><span data-preserver-spaces="true">5 Ways to Apply Ethics to AI</span></a></li><li><a class="editor-rtfLink" href="" target="_blank" rel="noopener noreferrer"><span data-preserver-spaces="true"> in R: How to Make a Computer Vision Model within R Environment</span></a></li><li><a class="editor-rtfLink" href="" target="_blank" rel="noopener noreferrer"><span data-preserver-spaces="true">Satellite Image Analysis with For Disaster Recovery</span></a></li><li><a class="editor-rtfLink" href="" target="_blank" rel="noopener noreferrer"><span data-preserver-spaces="true">AI for Good: Fighting COVID-19 with Data Science</span></a></li><li><a class="editor-rtfLink" href="" target="_blank" rel="noopener noreferrer"><span data-preserver-spaces="true">AI for Assisting in Natural Disaster Relief Efforts: The xView2 Competition </span></a></li></ul> &nbsp; &nbsp; <p style="text-align: center;"><strong><span data-preserver-spaces="true">Appsilon is hiring for remote roles! See our </span></strong><a class="editor-rtfLink" href="" target="_blank" rel="noopener noreferrer"><strong><span data-preserver-spaces="true">Careers</span></strong></a><strong><span data-preserver-spaces="true"> page for all open positions, including </span></strong><a class="editor-rtfLink" href="" target="_blank" rel="noopener noreferrer"><strong><span data-preserver-spaces="true">R Shiny Developers</span></strong></a><strong><span data-preserver-spaces="true">, </span></strong><a class="editor-rtfLink" href="" target="_blank" rel="noopener noreferrer"><strong><span data-preserver-spaces="true">Fullstack Engineers</span></strong></a><strong><span data-preserver-spaces="true">, </span></strong><a class="editor-rtfLink" href="" target="_blank" rel="noopener noreferrer"><strong><span data-preserver-spaces="true">Frontend Engineers</span></strong></a><strong><span data-preserver-spaces="true">, and a </span></strong><a class="editor-rtfLink" href="" target="_blank" rel="noopener noreferrer"><strong><span data-preserver-spaces="true">Senior Infrastructure Engineer</span></strong></a><strong><span data-preserver-spaces="true">. Join Appsilon and work on groundbreaking projects with the world's most influential Fortune 500 companies.</span></strong></p>

Contact us!
Damian's Avatar
Damian Rodziewicz
Head of Sales
Thank you! Your submission has been received!
Oops! Something went wrong while submitting the form.
data for good