The Respiratory Diagnosis Assistant is a tool designed to assist in diagnosing respiratory conditions based on audio recordings. It utilizes Amazon S3 for storing audio files and MongoDB for managing data.
- Amazon S3: Used for storing audio files. For information on how to set up and use Amazon S3, please refer to the official documentation.
- MongoDB Atlas: Used for managing data. The application is configured to connect to a MongoDB Atlas cluster running version 7.0.8. For more information on MongoDB Atlas and how to set it up, please refer to the official documentation.
- Python version 3.11 or higher
- Access to MongoDB (Contact mkim925@gatech.edu for access)
-
Clone the repository:
git clone https://github.com/nabinkim0318/Respiratory-Diagnosis-Assistant.git
-
Navigate to the project directory and create a virtual environment:
cd Respiratory-Diagnosis-Assistant python -m venv venv -
Activate the virtual environment:
- macOS:
source venv/bin/activate - Windows:
venv\Scripts\activate
- macOS:
-
Install required libraries:
pip install -r requirements.txt
-
Run the Django application:
python manage.py runserver
-
Open a web browser and go to http://127.0.0.1:8000/ to access the application.
This option outputs the top 5 audio files that best match the provided condition, along with additional demographic information.
This option outputs the condition and confidence score based on the provided audio file, along with additional demographic information.
-
Sample Dataset: A small dataset sample is located in the directory
Respiratory-Diagnosis-Assistant/respiratory_diagnosis_assistant/media/audio_files. -
Data Loading Scripts: Scripts to load data into the MongoDB database are available:
python manage.py import_script # load dataset into MongoDB python manage.py average_calc # calculate average cycle duration
Please note that you do not need to run these scripts as the data are already loaded into the system.