MonkeyPox Detection Using Machine Learning Approach and Explainable AI
CSE445 is an introductory course on Macchine Learning, which was offered by DR. RIASAT KHAN during FALL 2022 semester at North South University, Dhaka, Bangladesh. This repository contains the Project and other projet related assignments that were completed during this course.
Monkeypox is a rare viral disease that causes skin rashes and flu-like symptoms. Key symptoms include fever, headache, muscle aches, and a rash. Early detection is crucial for effective treatment.
Before training the models, we applied two pre-processing techniques:
- Duplicate Drop: Removed duplicate rows from the dataset.
- Null Value Drop: Eliminated rows with missing values.
- One Hot Encoding
- Feature Selection: Selected relevant features for training.
We have conducted EDA on the dataset and generated images that provide valuable insights.
To understand the relationships between different features, we present the correlation matrix
We experimented with the following algorithms for MonkeyPox detection:
- Decision Tree
- Random Forest
- Logistic Regression
- Support Vector Machine
- Naive Bayes
We used Grid Search and Random Search for hyperparameter tuning in our models.
Grid Search exhaustively searches over a predefined hyperparameter space, while Random Search selects hyperparameters randomly.
The confusion matrix is a performance evaluation tool for classification models.
It helps us understand true positives, true negatives, false positives, and false negatives.
Explainable AI helps us understand how our models make predictions.
It provides insights into the reasons behind model decisions, increasing transparency and trust.
Feel free to explore my repository
If you have any questions or suggestions, please let me know. Happy coding!