Music Therapy for Depression is a cutting-edge AI application designed to diagnose depression and recommend music therapy solutions. The app leverages machine learning algorithms to classify the severity of depression based on user input and suggests therapeutic music.
📍 Click Here to try app! 🚀
 |
Depression, a common yet serious mood disorder, can lead to various emotional and physical problems. It often goes undiagnosed and untreated, exacerbating its impact. Music therapy, a clinical and evidence-based practice, has proven effective in mood enhancement and stress reduction.
Our objective is to develop an AI solution capable of diagnosing depression from user inputs, categorizing its severity, and providing music therapy recommendations.
We utilized a dataset in CSV format, sourced from research studies. It was cleaned, wrangled, and prepared for use in our machine learning models.
- Programming: Python, JavaScript
- Data Wrangling: Pandas, Numpy
- Data Analysis and Visualization: Numpy, Stat, Seaborn, Matplotlib
- Machine Learning / Deep Learning: Tensorflow, Scikit Learn, XGBoost
- Backend Development: Flask
- Frontend Development: HTML, CSS, Bootstrap
- Cloud Deployment: Render, Heroku
The application is structured as follows:
static/: Contains static assets like CSS and JavaScript files.templates/: HTML templates for the web interface.Jupyter_Notebook.ipynb: Jupyter notebook with data analysis and model training.app.py: Main Flask application script defining routes and logic.data.csv: Dataset used for training the machine learning model.requirements.txt: Lists all Python libraries required for the project.runtime.txt: Specifies the Python runtime version for the application.
- Python 3.x
- Pip (Python package manager)
-
Clone the GitHub repository: bash git clone https://github.com/Ajisco/Sami-Depression.git
-
Navigate to the project directory: bash cd Sami-Depression
-
Install the required dependencies: bash pip install -r requirements.txt
To run the application locally: bash python app.py
Access the app at http://localhost:5000.
- Symptom input form for diagnosis.
- AI-based depression diagnosis and classification.
- Option to select a preferred music genre.
- Music suggestions based on depression type and genre (using YouTube Music API).
- Links to additional information resources.
- Compatible with various devices.
The application is deployed on Render and can be accessed Here.
- Limited dataset size may affect generalization.
- Slower startup times due to free hosting on Render.
- Limited music genres currently available.
- Expand the dataset for better model training.
- Add more music genres and refine music selection algorithms.
We invite collaboration. If interested, please:
- Create a pull request with a detailed explanation.
- Or, contact us through the following:
