Mehmet Yiğit Turalı's repositories
AFS_BM-Algorithm
This project provides a comprehensive toolset for feature selection using LightGBM, a gradient boosting framework that uses tree-based learning algorithms. The primary goal is to improve model performance by selecting the most relevant features and discarding the redundant ones.
Shell_App
Shell_App is an integrated data analysis and modeling platform, featuring scripts for EDA, ensemble techniques, LightGBM, and SARIMAX modeling. Designed for comprehensive data processing, the repository also includes deployment capabilities via Streamlit for interactive model interactions.
JointNet
JointNET is a deep learning model designed to predict active inflammation in sacroiliac joints using radiographs. Developed using a dataset of 1,537 grade 0 SIJs, the model showcases superior accuracy compared to human observers. This repository contains the code used in the development and validation of JointNET.