Inspiration
In 2021, in the US there were over half a million large truck accidents, where over 100,000 of them caused injury and 4444 caused fatalities. One of the team members in our group has a cousin that was severely injured in a truck accident involving his car. Truck drivers often work long hours to deliver shipments and are susceptible to driver fatigue, hence we have created an application to help bring awareness and perhaps more harmony between truck drivers and their employers.
What it does
DriveSafe is an innovative web application that classifies a driver’s state of consciousness using EEG data obtained from a wearable headband integrated into a hat. It uses machine learning algorithms to identify if the driver is in a normal or drowsy state and provides a real-time dashboard that displays the current state, live location, and options to send alerts to the driver if drowsiness is detected. This system is tailored for trucking companies to monitor their drivers and ensure safer journeys.
How we built it
Machine Learning: A classification model trained on EEG data to detect states of consciousness.
Backend: Implemented Django for server-side processing.
Frontend: Created with React to display the real-time dashboard.
Data Streaming: Real-time data transfer using RESTful APIs.
Location Tracking: Integration of geolocation services for live tracking.
Alerts System: A notification service to send immediate alerts when drowsiness is detected.
Challenges we ran into
Training an accurate model took some time and setting up an emulator to constantly send data to the backend was also tricky.
Accomplishments that we're proud of
We are proud that we have an accurate model and we have the app fully working.
What we learned
This project taught us a lot about the practical implementation of machine learning models with real-time data streams and how to integrate various technologies into a cohesive system.
What's next for DriveSafe
We plan to introduce a feature to detect drunkenness and make it more applicable for the government so they can monitor people with a history of drunk driving.
Log in or sign up for Devpost to join the conversation.