Login Page
Customer Details
Technician View
Customer View
GUI
GUI Maintenance

Auto Pulse

Inspiration

As a team of Computer Science and Electrical & Computer Engineering majors, we wanted to bridge both disciplines to create a solution that optimizes vehicle health and connectivity. Our goal was to develop an AI-driven tool to enhance automotive diagnostics, ensuring real-time insights for smarter maintenance.

What it does

Auto Pulse uses AI to optimize vehicle diagnostics by:

Analyzing synthetic data
Providing real-time health monitoring

It connects through a controller and offers a user-friendly web application to access vehicle performance insights.

How we built it

We followed these steps to build Auto Pulse:

Algorithm Creation: Developed an algorithm to generate synthetic data.
AI Training: Trained our AI models using the synthetic data.
Backend Setup: Built a Python backend using Flask to handle data processing.
Frontend Development: Connected the backend to a React-based web application via an API.
Data Access: The web application displays vehicle health data for the user.

Challenges we ran into

Some challenges we encountered were:

Integration issues between the Python backend and the React frontend.
Hardware limitations for input/output compatibility.
The steep learning curve of machine learning and AI training within a 24-hour window.

Accomplishments that we're proud of

We successfully built an end-to-end system in just 24 hours.
We integrated AI with real-time data optimization for vehicle diagnostics.
Overcoming technical challenges like backend/frontend integration was a significant achievement.

What we learned

Key lessons we learned include:

Time management is crucial in a fast-paced environment.
The importance of effective team communication to keep the project on track.
We gained practical experience in:
- AI training
- Python-React integration
- Managing hardware limitations

What's next for Auto Pulse

Future plans for Auto Pulse:

Expansion to other transportation sectors like aviation and marine applications.
Development of a mobile application for commercial fleet management, enabling real-time monitoring of a fleet of vehicles across multiple platforms.

Built With

Submitted to

MHacks 2024

Created by

I played a key role in project management, where I guided the team in creating and executing a comprehensive plan to ensure smooth project delivery. In addition to overseeing the planning process, I worked extensively on both front-end and back-end development for the full-stack web application, ensuring its functionality, performance, and user experience were optimized. I was also involved in testing the application to identify and resolve any issues, ensuring high-quality performance. Furthermore, I contributed to the AI training process, helping the team refine and improve its learning capabilities.

Nuha A
Developed the algorithms backend and communication infrastructure for a predictive vehicle maintenance application. My contributions span across multiple aspects of the project. Flask API development to receive Realtime vehicle data inputs. Integrated the machine learning model into the flask application, ensuring that vehicle data is preprocessed and analyzed. I implemented a client side script to send vehicle data through the client portal and immediately get vehicle health condition. Implemented error handling within the API to ensure that the system gracefully handles invalid inputs and provides meaningful error messages to the client.

Rupesh Kanna Kaviyasree Narayanan
I worked on storing the user data in a MySQL database. I am not too familiar with databases, but I did learn a lot about MySQL and mongodb while coding.

Tejaswini Ravula

Updates

Nuha A started this project — Sep 29, 2024 11:36 AM EDT

Leave feedback in the comments!

Log in or sign up for Devpost to join the conversation.