Skip to content

MonkeyPox Detection Using Machine Learning Approach and Explainable AI

License

Notifications You must be signed in to change notification settings

Al-Shafi-Github/MonkeyPox-Detection

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

23 Commits
 
 
 
 
 
 
 
 

Repository files navigation

MonkeyPox-Detection Using Machine Learning Approach and Explainable AI

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.

Segmented image of Drive and Chase Dataset

Introduction

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.

Dataset

Monkey Pox Dataset

Pre-processing

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.
After Pre-processing

Exploratory Data Analysis (EDA)

We have conducted EDA on the dataset and generated images that provide valuable insights.

EDA EDA

EDA EDA

Co-relation Matrix

To understand the relationships between different features, we present the correlation matrix

Co-relation

Machine Learning Algorithms Used

We experimented with the following algorithms for MonkeyPox detection:

  • Decision Tree
  • Random Forest
  • Logistic Regression
  • Support Vector Machine
  • Naive Bayes

Grid Search and Random Search

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.

Grid Search SVM

Confusion Matrix

The confusion matrix is a performance evaluation tool for classification models.

It helps us understand true positives, true negatives, false positives, and false negatives.

SVM

Explainable AI

Explainable AI helps us understand how our models make predictions.

It provides insights into the reasons behind model decisions, increasing transparency and trust.

SVM

Feel free to explore my repository

If you have any questions or suggestions, please let me know. Happy coding!