ReCoin - Restoring our environment and businesses in parallel

Related tags

Text Data & NLPReCoin
Overview

Shashank Ojha, Sabrina Button, Abdellah Ghassel, Joshua Gonzales

"Reduce Reuse Recoin"

Theme Covered:

The themes covered in this project include post pandemic restoration for both the environment, small buisnesses, and personal finance! The app pitched uses an extensivly trained AI system to detect trash and sort it to the proper bin from your smartphone. While using the app, users will be incentivized to use the app and recover the environment through the opportunity to earn points, which will be redeemable in partnering stores.

Problem Statment:

As our actions continue to damage the environment, it is important that we invest in solutions that help restore our community in more sustainable practices. Moreover, an average person creates over 4 pounds of trash a day, and the EPA has found that over 75% of the waste we create are recyclable. As garbage sorting is so niche from town-to-town, students have reportable agreed to the difficulty of accurately sorting garbage, thus causing this significant misplacement of garbage.

Our passion to make our community globally and locally more sustainable has fueled us to use artificial intelligence to develop an app that not only makes sorting garbage as easy as using Snapchat, but also rewards individuals for sorting their garbage properly.

For this reason, we would like to introduce Recoin. This intuitive app allows a person to scan any product and easily find the bin that the trash belongs based off their location. Furthermore, if they attempt to sell their product, or use our app, they will earn points which will be redeemable in partnering stores that advocate for the environment. The more the user uses the app, the more points they receive, resulting in better items to redeem in stores. With this app we will not only help recover the environment, but also increase sales in small businesses which struggled during the pandemic to recover.

About the App:

Incentive Breakdown:

Please note that these expenses are estimated expectations for potential benefit packages but are not defined yet.

We are proposing a $1 discount for participating small businesses when 100 coffee/drink cups are returned to participating restaurants. This will be easy for small companies to uphold financially, while providing a motivation for individuals to use our scanner.

Amazon costs around $0.5 to $2 on packaging, so we are proposing that Amazon provides a $15 gift card per 100 packages returned to Amazon. As the 100 packages can cost from $50 to $200, this incentive will save Amazon resources by 5 to 100 times the amount, while providing positive public perception for reusing.

As recycling plastic for 3D filament is an up-and-coming technology that can revolutionize environment sustainability, we would like to create a system where providing materials for such causes can give the individuals benefits.

Lastly, as metals become more valuable, we hope to provide recyclable metals to companies to reduce their expenses through our platform.

The next steps to this endeavor will be to provide benefits for individuals that provide batteries and electronics with some sort of incentive as well.

User Interface:

#add user stuff!!!!!!!!!!!1

Technological Specifics and Next Steps:

Frontend

----ADDDDDDDDDDDD GRAPHHHHHHHHHHHHHHHHHHHHHHHH____ We used to React.JS to develop components for the webcam footage and capture screen shots. It was also utilized to create the rest of the overall UI design.

Backend

Trash Detection AI:

On Pytorch, we utilized an open-source trash detection AI software and data, to train the trash detection system originally developed by IamAbhinav03. The system utilizes over 2500 images to train, test, and validate the system. To improve the system, we increased the number of epochs to 8 rather than 5 (number of passes the training system has completed) to train it for an additional four hours than required. This allowed the accuracy to increase by 4% more than the original system. We also modified the test train and split amounts to 70%, 10%, and 20% respectively, as more prominent AI studies have found this distribution to receive the best results.

Currently, the system is predicted to have a 94% accuracy, but in the future, we plan on using reinforcement learning in our beta testing to continuously improve our algorithm. Reinforcement learning allows for the data to be more accurate, through learning from user correction. This will allow AI to become more precise as it gains more popularity.

Other Systems:

By using Matbox API and the Google Suite/API, we will be creating maps to find recycling locations and an extensively thorough Recoin currency system that can easily be transferred to real time money for consumers and businesses.

Stakeholders:

After the completion of this project, we intend to continue to pursue the app to improve our communities’ sustainability. After looking at the demographic of interest in our school itself, we know that students will be interested in this app, not only from convenience but also through the reward system. Local cafes and Starbucks already have initiatives to improve public perspective and support the environment (i.e., using paper straws and cups), therefore supporting this new endeavor will be an interest to them. As branding is everything in a business, having a positive public perspective will increase sales.

Amazon:

As Amazon continues to be the leading online marketplace, more packages will continue to be made, which can be detrimental to the world's limited resources. We will be training the UI to track packages that are Amazon based. With such training, we would like to be able to implement a system where the packaging can be sent back to Amazon to be reused for credit. This will allow Amazon to form a more environmentally friendly corporate image, while also saving on resources.

Small Businesses:

As the pandemic has caused a significant decline in small business revenue, we intend to mainly partner with small businesses in this project. The software will also help increase small business sales as by supporting the app, students will be more inclined to go to their store due to a positive public image, and the additive discounts will attract more customers. In the future, we wish to train AI to also detect trash of value (i.e.. Broken smartphones, precious metals), so that consumers can sell it in a bundle to local companies that can benefit from the material (ex: 3D-printing companies that convert used plastic to filament)

Timeline:

The following timeline will be used to ensure that our project will be on the market as soon as possible:

Code Refrences

https://medium.datadriveninvestor.com/deploy-your-pytorch-model-to-production-f69460192217

https://narainsreehith.medium.com/upload-image-video-to-flask-backend-from-react-native-app-expo-app-1aac5653d344

https://pytorch.org/tutorials/beginner/saving_loading_models.html

https://pytorch.org/tutorials/intermediate/flask_rest_api_tutorial.html

https://pytorch.org/get-started/locally/

https://www.kdnuggets.com/2019/03/deploy-pytorch-model-production.html

Refrences for Information

https://www.rubicon.com/blog/trash-reason-statistics-facts/

https://www.dosomething.org/us/facts/11-facts-about-recycling

https://www.forbes.com/sites/forbesagencycouncil/2016/10/31/why-brand-image-matters-more-than-you-think/?sh=6a4b462e10b8

https://www.channelreply.com/blog/view/ebay-amazon-packaging-costs

Owner
sabrina button
First Year Engineering Student at Queen's University (she/her)
sabrina button
PG-19 Language Modelling Benchmark

PG-19 Language Modelling Benchmark This repository contains the PG-19 language modeling benchmark. It includes a set of books extracted from the Proje

DeepMind 161 Oct 30, 2022
An ActivityWatch watcher to pose questions to the user and record her answers.

aw-watcher-ask An ActivityWatch watcher to pose questions to the user and record her answers. This watcher uses Zenity to present dialog boxes to the

Bernardo Chrispim Baron 33 Dec 03, 2022
Research Code for NeurIPS 2020 Spotlight paper "Large-Scale Adversarial Training for Vision-and-Language Representation Learning": UNITER adversarial training part

VILLA: Vision-and-Language Adversarial Training This is the official repository of VILLA (NeurIPS 2020 Spotlight). This repository currently supports

Zhe Gan 109 Dec 31, 2022
Sequence-to-Sequence learning using PyTorch

Seq2Seq in PyTorch This is a complete suite for training sequence-to-sequence models in PyTorch. It consists of several models and code to both train

Elad Hoffer 514 Nov 17, 2022
NL. The natural language programming language.

NL A Natural-Language programming language. Built using Codex. A few examples are inside the nl_projects directory. How it works Write any code in pur

2 Jan 17, 2022
ADCS cert template modification and ACL enumeration

Purpose This tool is designed to aid an operator in modifying ADCS certificate templates so that a created vulnerable state can be leveraged for privi

Fortalice Solutions, LLC 78 Dec 12, 2022
GraphNLI: A Graph-based Natural Language Inference Model for Polarity Prediction in Online Debates

GraphNLI: A Graph-based Natural Language Inference Model for Polarity Prediction in Online Debates Vibhor Agarwal, Sagar Joglekar, Anthony P. Young an

Vibhor Agarwal 2 Jun 30, 2022
A 30000+ Chinese MRC dataset - Delta Reading Comprehension Dataset

Delta Reading Comprehension Dataset 台達閱讀理解資料集 Delta Reading Comprehension Dataset (DRCD) 屬於通用領域繁體中文機器閱讀理解資料集。 本資料集期望成為適用於遷移學習之標準中文閱讀理解資料集。 本資料集從2,108篇

272 Dec 15, 2022
Common Voice Dataset explorer

Common Voice Dataset Explorer Common Voice Dataset is by Mozilla Made during huggingface finetuning week Usage pip install -r requirements.txt streaml

Ceyda Cinarel 22 Nov 16, 2022
Bidirectional LSTM-CRF and ELMo for Named-Entity Recognition, Part-of-Speech Tagging and so on.

anaGo anaGo is a Python library for sequence labeling(NER, PoS Tagging,...), implemented in Keras. anaGo can solve sequence labeling tasks such as nam

Hiroki Nakayama 1.5k Dec 05, 2022
Open-source offline translation library written in Python. Uses OpenNMT for translations

Open source neural machine translation in Python. Designed to be used either as a Python library or desktop application. Uses OpenNMT for translations and PyQt for GUI.

Argos Open Tech 1.6k Jan 01, 2023
BeautyNet is an AI powered model which can tell you whether you're beautiful or not.

BeautyNet BeautyNet is an AI powered model which can tell you whether you're beautiful or not. Download Dataset from here:https://www.kaggle.com/gpios

Ansh Gupta 0 May 06, 2022
Yet Another Sequence Encoder - Encode sequences to vector of vector in python !

Yase Yet Another Sequence Encoder - encode sequences to vector of vectors in python ! Why Yase ? Yase enable you to encode any sequence which can be r

Pierre PACI 12 Aug 19, 2021
A library for Multilingual Unsupervised or Supervised word Embeddings

MUSE: Multilingual Unsupervised and Supervised Embeddings MUSE is a Python library for multilingual word embeddings, whose goal is to provide the comm

Facebook Research 3k Jan 06, 2023
Long text token classification using LongFormer

Long text token classification using LongFormer

abhishek thakur 161 Aug 07, 2022
Nateve compiler developed with python.

Adam Adam is a Nateve Programming Language compiler developed using Python. Nateve Nateve is a new general domain programming language open source ins

Nateve 7 Jan 15, 2022
String Gen + Word Checker

Creates random strings and checks if any of them are a real words. Mostly a waste of time ngl but it is cool to see it work and the fact that it can generate a real random word within10sec

1 Jan 06, 2022
🤗🖼️ HuggingPics: Fine-tune Vision Transformers for anything using images found on the web.

🤗 🖼️ HuggingPics Fine-tune Vision Transformers for anything using images found on the web. Check out the video below for a walkthrough of this proje

Nathan Raw 185 Dec 21, 2022
Fidibo.com comments Sentiment Analyser

Fidibo.com comments Sentiment Analyser Introduction This project first asynchronously grab Fidibo.com books comment data using grabber.py and then sav

Iman Kermani 3 Apr 15, 2022