Skip to content

kevinkchen1/Sorta

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 
 
 
 
 
 
 

Repository files navigation

Sorta

Update

Won 2nd Place for "Sustainability" Category at CruzHacks

Inspiration

The inspiration behind Sorta stems from the growing need to better manage our waste and protect the environment. With increasing levels of pollution and waste, it's becoming increasingly important to educate people and provide practical solutions to reduce waste and promote sustainability. Sorta was created with the goal of making waste management easy, accessible, and impactful for everyone. By providing a simple and convenient platform for waste management, Sorta aims to inspire and empower individuals to take action and make a difference in their communities.

What it does

Sorta provides a comprehensive waste management solution, including a machine learning model that accurately determines what type of waste you have, SMS updates on recycling, trash, pollution, and the environment, and general information about waste management. We also have a chatbot to assist users in navigating the platform and learn more about waste management.

How we built it

Sorta was built using a combination of machine learning, natural language processing, and web development technologies. The machine learning model, which accurately determines what type of waste someone has, was built using TensorFlow, one of the leading open-source platforms for machine learning. Collecting and training samples was a crucial aspect of developing the model, and we worked hard to ensure the model was highly accurate and reliable. Integrating the machine learning model into our website was a challenge, but our team of experts worked together to create a seamless and user-friendly experience.

Challenges we ran into

One of the biggest challenges we faced was developing the machine learning model to accurately determine what type of waste someone has. This required collecting and training a large dataset of waste samples and using TensorFlow to build and optimize the model. Integrating the model into our website was also a challenge, as we had to ensure that the user experience was seamless and user-friendly. Nevertheless, we persevered and are proud of the result.

Accomplishments that we're proud of

We're proud to have created a platform that not only makes waste management easier but also promotes sustainability and environmental awareness. Our machine learning model, built with TensorFlow, is highly accurate and continues to improve, and our SMS updates are helping people stay informed about waste management in their communities. We've received positive feedback from users who appreciate the convenience and simplicity of Sorta, and we're proud to be making a difference in the world.

What we learned

We learned that there is a growing need for practical solutions in waste management and that people are eager to learn more about how they can make a positive impact on the environment. We also learned the importance of using technology, such as machine learning and TensorFlow, to create solutions that are both effective and user-friendly. Additionally, we learned the importance of collecting and training high-quality datasets to improve the accuracy of our machine-learning models.

What's next for Sorta

We're continually improving and expanding Sorta to reach more people and make a bigger impact. In the future, we hope to expand into new areas, provide even more personalized and relevant information, and work with communities to create sustainable waste management solutions. We're also exploring new ways to improve the accuracy and reliability of our machine-learning models and to integrate them into other waste management systems. The possibilities are endless, and we're excited to continue making a positive impact on the world with Sorta.

About

Project for CruzHacks

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • CSS 83.4%
  • HTML 9.0%
  • SCSS 6.2%
  • JavaScript 1.4%