NeuroFlirt introduces a groundbreaking approach to online dating by leveraging brain activity to ensure deep compatibility between users. By focusing on brain activity-informed scores, we streamline the search process, enhance match quality, and reduce overwhelm in the dating app landscape. Our solution addresses the divide in online dating experiences, offering a scientifically informed pathway to meaningful connections.
Link to Presentation
- Focused Interactions: Matches are based on brain activity, streamlining searches and saving time.
- Enhanced Match Quality: A brain activity-based scoring system guarantees deep compatibility.
- Reduced Overwhelm: Limits choices by focusing on quality, simplifying decisions.
- Live Emotional Feedback: Provides real-time tracking of emotions such as attraction and happiness during conversations.
- Subjects: 28 total subjects participating in 4 different games.
- Data: ~4,000,000 rows of brain activity data processed using Muse with 4 electrode channels.
- Data Processing: Utilizes regional averaging for clarity from 14 electrode channels.
- Model: LightGBM with predictions made every 30 seconds and a regression model achieving ~2 RMSE on a scale of 0 - 8.
- Model Pipeline: Included in model/neuroflirt_model.ipynb
We prioritize privacy, consent, data security, and algorithmic fairness to ensure a safe and equitable user experience.
NeuroFlirt's technology also has potential applications in healthcare, education, market research, and couple therapy.
Clone the repo, then use the following code to setup a virtual environment and install all dependencies.
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
The application requires a connection to MindMonitor. It is possible to find alternatives but it will require adjustments to the code. Once a connection is set up and data is streaming to the local device, you can launch the app locally using the following command.
python3 -m streamlit app.pyCreated for the purpose of Neuroengineering Hackathon, March 3, 2024.
Gunn Chun
Nathan Chen
Ethan Kawahara
Michael Petta